This document discusses the use of machine learning techniques for user modeling. It addresses four key challenges: (1) the need for large datasets to train models accurately, (2) the need for labeled training data, (3) the problem of concept drift over time, and (4) computational complexity issues. The document reviews different approaches for addressing these challenges, such as using initial models, structuring tasks to not require exact user replication, and modeling communities instead of individual users.
This document reviews and compares eight prominent models of user acceptance of information technology: the theory of reasoned action, technology acceptance model, motivational model, theory of planned behavior, combined TAM and TPB model, model of PC utilization, innovation diffusion theory, and social cognitive theory. It aims to empirically compare the models, formulate a unified model integrating elements of the eight models called UTAUT, and validate UTAUT using multiple data sets. The eight models are described and their constructs defined. Prior empirical comparisons of the models are discussed, noting limitations that the current study aims to address.
INVESTIGATION A NEW APPROACH TO DETECT AND TRACK FRAUD IN VIRTUAL LEARNING EN...ijmnct
Virtual University is the environment that with utilizes the appropriate multimedia tools and having good communication infrastructure is a provider of e-learning services, so that usually does not have require to physical location as a traditional university and students are able in any place and at any time be willing to use a lot of services provided, such as e-courses or electronic tests. There are many solutions in order to identify and detect fraud in the online environment that use of these methods can be identified took place fraud, but still is great importance of avoid discussion and fraud detection in virtual university. In this research, we aimed are to investigate a new approach to detect and track fraud in virtual learning
environments by using decision tree. (Chayd model). The results showed that the accuracy of the model is 84.54% which is indicative of high performance and high precision in predicting fraud from the teachers, students and hackers.
Investigation of new approach to detect and track fraud in virtual learningijmnct
Virtual University is the environment that with utilizes the appropriate multimedia tools and having good communication infrastructure is a provider of e-learning services, so that usually does not have require to physical location as a traditional university and students are able in any place and at any time be willing to use a lot of services provided, such as e-courses or electronic tests. There are many solutions in order to identify and detect fraud in the online environment that use of these methods can be identified took place fraud, but still is great importance of avoid discussion and fraud detection in virtual university. In this research, we aimed are to investigate a new approach to detect and track fraud in virtual learning environments by using decision tree. (Chayd model). The results showed that the accuracy of the model is 84.54% which is indicative of high performance and high precision in predicting fraud from the teachers, students and hackers.
EXTENSION OF TECHNOLOGY ACCEPTANCE MODEL (TAM): A STUDY ON INDIAN INTERNET BA...IAEME Publication
Internet banking plays significant role in the development of banking business in our country. An application of electronic service brings predominant changes in the way of doing banking transactions. In simpler terms, internet banking refers to banking through bank’s website with the help of internet connection. Internet banking provides lot of benefits to the customers as well as the banks. Internet banking provides different kinds of services to the customers in the form checking balances, account statement, pay utility bills etc
The quasimoderating effect of perceived affective quality on an extending Tec...alabrictyn
This document discusses an empirical study that tests an extended Technology Acceptance Model (TAM) to understand factors influencing learner acceptance of the WebCT e-learning system. The study incorporates additional constructs of perceived affective quality (PAQ), flow, perceived usefulness (PU), and perceived ease of use (PEOU) to predict behavioral intention to use WebCT. Structural equation modeling is used to analyze relationships between constructs and test hypotheses. Results support that PU, PEOU, and flow positively impact intention to use WebCT, and that PAQ has a moderating effect on the relationships in the extended TAM.
The document discusses the Technology Acceptance Model (TAM) and its viability for determining acceptance of e-learning technologies in higher education institutions. TAM identifies perceived usefulness and perceived ease of use as key factors influencing attitudes toward and use of new technologies. The document reviews literature on TAM and its constructs. It also presents two case studies that applied TAM to evaluate student acceptance of online technologies for communication and public relations courses. Both case studies found TAM to be an effective model for predicting technology use.
FACTORS INFLUENCING THE ADOPTION OF E-GOVERNMENT SERVICES IN PAKISTANMuhammad Ahmad
E-government provides opportunities to deliver various services more effectively and better serve citizens. In developing countries, e-government initiatives provide services that have been previously inaccessible to their citizens. However, e-government initiatives in developing countries are still in their infancy and face a wide range of barriers that restrict wide-spread use. Like many other developing countries, Pakistan has a low level of e-government services adoption. Previous research has investigated e-government services in developing countries from the organizational perspective. However, the research stream suffers from an absence of studies that have investigated e-government from a citizen’s perspective. The success of e-government services depends on government support as well as on citizen’s adoption. This paper aims to fill this gap by exploring the challenges and barriers of e-government services from the user’s perspective. In this study, an amended version of the UTAUT model is used to investigate the factors influencing the uptake of e-government services in Pakistan. The results show that the factors influencing the adoption of e-government services in Pakistan are related to ease of use, usefulness, social influence, technological issues, lack of awareness, data privacy, and trust. Implications for e-businesses and government policy decision makers are also considered in this study.
Digital Transformation in Higher Education – New Cohorts, New Requirements?. ...eraser Juan José Calderón
The document discusses digital transformation in higher education and how usage of digital platforms differs between groups in a university setting. A qualitative study was conducted through semi-structured interviews of bachelor students, master students, PhD students, and employees. The interviews aimed to understand how factors like team experience, task complexity, and technology accessibility influence platform usage. Preliminary results found bachelor and master students prefer social media for collaboration while PhD students and employees do not, and communication between groups still relies heavily on email.
This document reviews and compares eight prominent models of user acceptance of information technology: the theory of reasoned action, technology acceptance model, motivational model, theory of planned behavior, combined TAM and TPB model, model of PC utilization, innovation diffusion theory, and social cognitive theory. It aims to empirically compare the models, formulate a unified model integrating elements of the eight models called UTAUT, and validate UTAUT using multiple data sets. The eight models are described and their constructs defined. Prior empirical comparisons of the models are discussed, noting limitations that the current study aims to address.
INVESTIGATION A NEW APPROACH TO DETECT AND TRACK FRAUD IN VIRTUAL LEARNING EN...ijmnct
Virtual University is the environment that with utilizes the appropriate multimedia tools and having good communication infrastructure is a provider of e-learning services, so that usually does not have require to physical location as a traditional university and students are able in any place and at any time be willing to use a lot of services provided, such as e-courses or electronic tests. There are many solutions in order to identify and detect fraud in the online environment that use of these methods can be identified took place fraud, but still is great importance of avoid discussion and fraud detection in virtual university. In this research, we aimed are to investigate a new approach to detect and track fraud in virtual learning
environments by using decision tree. (Chayd model). The results showed that the accuracy of the model is 84.54% which is indicative of high performance and high precision in predicting fraud from the teachers, students and hackers.
Investigation of new approach to detect and track fraud in virtual learningijmnct
Virtual University is the environment that with utilizes the appropriate multimedia tools and having good communication infrastructure is a provider of e-learning services, so that usually does not have require to physical location as a traditional university and students are able in any place and at any time be willing to use a lot of services provided, such as e-courses or electronic tests. There are many solutions in order to identify and detect fraud in the online environment that use of these methods can be identified took place fraud, but still is great importance of avoid discussion and fraud detection in virtual university. In this research, we aimed are to investigate a new approach to detect and track fraud in virtual learning environments by using decision tree. (Chayd model). The results showed that the accuracy of the model is 84.54% which is indicative of high performance and high precision in predicting fraud from the teachers, students and hackers.
EXTENSION OF TECHNOLOGY ACCEPTANCE MODEL (TAM): A STUDY ON INDIAN INTERNET BA...IAEME Publication
Internet banking plays significant role in the development of banking business in our country. An application of electronic service brings predominant changes in the way of doing banking transactions. In simpler terms, internet banking refers to banking through bank’s website with the help of internet connection. Internet banking provides lot of benefits to the customers as well as the banks. Internet banking provides different kinds of services to the customers in the form checking balances, account statement, pay utility bills etc
The quasimoderating effect of perceived affective quality on an extending Tec...alabrictyn
This document discusses an empirical study that tests an extended Technology Acceptance Model (TAM) to understand factors influencing learner acceptance of the WebCT e-learning system. The study incorporates additional constructs of perceived affective quality (PAQ), flow, perceived usefulness (PU), and perceived ease of use (PEOU) to predict behavioral intention to use WebCT. Structural equation modeling is used to analyze relationships between constructs and test hypotheses. Results support that PU, PEOU, and flow positively impact intention to use WebCT, and that PAQ has a moderating effect on the relationships in the extended TAM.
The document discusses the Technology Acceptance Model (TAM) and its viability for determining acceptance of e-learning technologies in higher education institutions. TAM identifies perceived usefulness and perceived ease of use as key factors influencing attitudes toward and use of new technologies. The document reviews literature on TAM and its constructs. It also presents two case studies that applied TAM to evaluate student acceptance of online technologies for communication and public relations courses. Both case studies found TAM to be an effective model for predicting technology use.
FACTORS INFLUENCING THE ADOPTION OF E-GOVERNMENT SERVICES IN PAKISTANMuhammad Ahmad
E-government provides opportunities to deliver various services more effectively and better serve citizens. In developing countries, e-government initiatives provide services that have been previously inaccessible to their citizens. However, e-government initiatives in developing countries are still in their infancy and face a wide range of barriers that restrict wide-spread use. Like many other developing countries, Pakistan has a low level of e-government services adoption. Previous research has investigated e-government services in developing countries from the organizational perspective. However, the research stream suffers from an absence of studies that have investigated e-government from a citizen’s perspective. The success of e-government services depends on government support as well as on citizen’s adoption. This paper aims to fill this gap by exploring the challenges and barriers of e-government services from the user’s perspective. In this study, an amended version of the UTAUT model is used to investigate the factors influencing the uptake of e-government services in Pakistan. The results show that the factors influencing the adoption of e-government services in Pakistan are related to ease of use, usefulness, social influence, technological issues, lack of awareness, data privacy, and trust. Implications for e-businesses and government policy decision makers are also considered in this study.
Digital Transformation in Higher Education – New Cohorts, New Requirements?. ...eraser Juan José Calderón
The document discusses digital transformation in higher education and how usage of digital platforms differs between groups in a university setting. A qualitative study was conducted through semi-structured interviews of bachelor students, master students, PhD students, and employees. The interviews aimed to understand how factors like team experience, task complexity, and technology accessibility influence platform usage. Preliminary results found bachelor and master students prefer social media for collaboration while PhD students and employees do not, and communication between groups still relies heavily on email.
An Examination of the Prior Use of E-Learning Within an Extended Technology A...Maurice Dawson
The purpose of this empirical study was to test specific factors of behavioral intention to use m-learning in a community college setting using a modified technology acceptance model and antecedent factors suggested by the researcher’s review of the literature. In addition, the study’s purpose was to expand understanding of behavioral intention to use m-learning and to contribute to the growing body of research. This research model was based on relevant technology acceptance literature. The study examines the significance of “prior use of e-learning” and correlation with the behavioral intention to use m-learning. Existing models have looked at prior use of e-learning in other domains, but not specifically m-learning. Other models and studies have primarily looked at the prior use of e-learning variable as a moderating variable and not one that is directly related to attitude and behavioral intention. The study found that there is a relationship between prior use of e-learning and behavioral intention to use m-learning. This research direction was proposed by Lu and Viehland.
1. The document discusses the Technology Acceptance Model (TAM), which aims to explain and predict user acceptance of technology. TAM focuses on how perceived ease of use and perceived usefulness influence attitudes, behavioral intention, and actual technology use.
2. The document reviews several studies that have applied TAM across different contexts like education. It finds that TAM is useful for understanding factors that influence teacher and student acceptance of educational technologies.
3. However, the document also notes some weaknesses of TAM, such as its reliance on self-reported data and the broad nature of perceived ease of use and usefulness constructs. It suggests TAM needs more research in primary/secondary school settings.
The UTAUT model aims to explain user intentions to use information systems and subsequent usage behavior. It was developed by reviewing and consolidating eight previous models of technology acceptance. The UTAUT model proposes four key constructs that influence usage intention and behavior: performance expectancy, effort expectancy, social influence, and facilitating conditions. Gender, age, experience, and voluntariness of use are hypothesized to moderate the impact of the four constructs. Several studies have applied the UTAUT model to domains such as mobile service adoption, social media adoption, and computer use frequency. Some researchers have also extended the UTAUT model by adding additional constructs. However, others have critiqued the UTAUT model for having many independent variables and
This presentation is about UTAUT and UTAUT 2. In this slide also discuss briefly about UTAUT and changes made in UTAUT 2. It also discuss about how it can be applied in the classroom and the strength and weakness of using it.
José Carlos Sánchez Prieto, Susana Olmos Migueláñez and Francisco J. García-Peñalvo.
Research Group in InterAction and eLearning (GRIAL)
IUCE
University of Salamanca
_mobile learning lecturers versus students on usage and perception using the ...Lenandlar Singh
This study investigated the usage and perceptions of mobile learning (m-learning) among lecturers and students at the University of Guyana using the Unified Theory of Acceptance and Use of Technology (UTAUT) model. Surveys were administered to 508 students and 63 lecturers to examine factors influencing attitudes and intentions to use m-learning technologies. Path analysis found performance expectancy and facilitating conditions significantly influenced behavioral intention for students, while effort expectancy was most influential for lecturers. Overall, students showed higher levels of performance expectancy, effort expectancy, social influence, and attitudes toward m-learning compared to lecturers. The study recommends further research with larger lecturer samples and addressing facilitating conditions to influence lecturer use of m-learning.
Ubiquitous learning website scaffolding learners by mobile devices with info ...Seid Yesuf Ali
This document describes a system that aims to create a ubiquitous learning environment by integrating mobile devices and a web-based learning system. It discusses three key modules: 1) A learning status awareness module that analyzes student performance and sends messages about unfamiliar concepts via mobile devices. 2) A schedule reminder module that manages course schedules and reminds students of upcoming tasks. 3) A mentor arrangement module that recommends peer mentors for consultation via mobile communication. An experiment with 54 college students found that the system enhanced academic performance, task completion rates, and achievement of learning goals.
Validating Measurements of Perceived Ease Comprehension and Ease of Navigatio...drboon
Many universities are realizing that the implementation and use of online learning tool become a competitive advantage to address the actual learning needs. The purpose of this study is to determine the factors that influence users’ perceived ease of use of Webct an online learning tool. We administrated a questionnaire to undergraduate students from an university in Quebec, Canada. The results tend to corroborate that ease of comprehension and ease of navigation are the key factors which influence the perceived ease of use of WebCT. More specifically, the terms used in educational web applications must be as simple and relevant as possible. Jargon and technical terms in the wording of text used for links should be carefully avoided. This research is extending the finding of IT adoption studies by specifying what make an online tool easy to use.
This study examines factors that influence students' intention to adopt e-learning technology using an extended Technology Acceptance Model (TAM). The model incorporates perceived usefulness, perceived ease of use, social norms, and self-efficacy as determinants of behavioral intention. It also considers age and gender as moderators. The study surveyed 604 students at Brunel University who used a web-based learning system. Results found perceived usefulness, ease of use, social norms, and self-efficacy significantly influenced behavioral intention. Age moderated the effects of perceived ease of use, usefulness, and self-efficacy on intention, while gender moderated ease of use and social norms. The model explained 62% of variance in intention, out
This document discusses mobile phones as mediating tools for learning within augmented contexts. It argues that the design of mobile learning experiences needs to be re-examined to take advantage of mobile devices' affordances. Design research is presented as an approach that is iterative, interventionist, and contributes to theory building. An example of augmented contexts for development places context as a core construct for collaborative, location-based, problem solving using mobile devices. The paper concludes by outlining how design principles and implications for theory will be developed.
This document analyzes the relationship between student achievement in classic academic subjects (e.g. language arts, math, history, science) and computer-related subjects. The study examines grade data from freshman students in 2000-2001. Results show the average grade across subjects was a B, and computer grades tended to reflect trends in classic subjects. For example, students whose classic grades increased also tended to have higher computer grades. However, males on average saw declining grades overall compared to females. The document concludes the computer subject grade can often indicate trends in a student's overall academic performance.
A Multimedia Data Mining Framework for Monitoring E-Examination Environmentijma
Academic dishonesty has been a growing concern in e-learning environment due to the fact that eexamination takes place under supervised and unsupervised learning environment despite its huge advantages. The e-examination environment has faced various security breaches such as academic dishonesty (impersonation), identity theft, unauthorised access and illegal assistance as a result of inefficient measures employed. Hence, an efficient framework which will aid the monitoring of the eexamination is needed. This paper reviews the process of mining multimedia data and propose a framework for monitoring the e-examination environment in order to extract images and audio features. The framework has four major phases: data pre-processing, mining, association and post processing. The
pre-processing phases carries out the extraction and transformation of multimedia data features, the mining phase does the classification and clustering of these features, the association does pattern matching while the post processing carries out the knowledge interpretation and reporting. The approach presented in this study will allow for efficient and accurate monitoring of e-examination environment which will help provide adequate security and reduce unethical behaviour in e-examination environment.
Extending UTAUT to explain social media adoption by microbusinessesDebashish Mandal
This paper establishes inadequacies of the Unified Theory of Acceptance and Use of Technology (UTAUT) theory to explain social media adoption by microbusinesses. Literature review confirms the explaining power of UTAUT in variety of technology adoption by businesses. This paper uses UTAUT theory to implement social media technology in microbusinesses. Canonical action research method is adopted to introduce social media in microbusinesses. A post positivist approach is used to report the results based on a predetermined premise. It was found that the major constructs of performance and effort expectancy played insignificant role in establishing behavioural and adoption intention of social media by microbusinesses. Social influence and facilitating condition did not influence the behavioural intentions of the microbusiness owners. Individual characteristics and codification effort dominated the use behaviour. Goal of gaining customers leads to behavioural modification resulting in replacing of behavioural intention with goals as a superior method of predicting adoption behaviour within the context of microbusinesses. This paper extends the UTAUT to explain social media adoption in microbusinesses.
The document discusses the politics of e-learning standardization. It argues that unlike social science disciplines, e-learning standards are generally seen as neutral artifacts rather than social constructions that embody specific interests. The document surveys how standards can be understood as enabling uniformity, objectivity, and justice. While standards aim to make actions comparable over time and space, education is profoundly local and contextual, resisting rationalization through standardized content and processes.
Invited talk: Using Social Media and Mobile Devices to Mediate Informal, Professional, Work-Based Learning
John Cook
Bristol Centre for Research
in Lifelong Learning and Education (BRILLE)
University of the West of England (UWE)
http://www.uwe.ac.uk/research/brille/
http://people.uwe.ac.uk/Pages/person.aspx?accountname=campus\jn-cook
Invited talk: Centre for Learning, Knowing and Interactive Technologies, Graduate School of Education, University of Bristol
26th February, 12.30 to 13.45
This document summarizes key lessons from 11 qualitative studies of enterprise mobility conducted between 2001-2007. It explores six aspects of how mobile information technology impacts organizations:
1. Interaction - Mobile IT can mediate remote interactions by removing time/space constraints, or support situated interactions by enabling work to be done in specific locations while maintaining remote access.
2. Management of work - Mobile IT can increase organizational control over employees or give individuals more discretion over how and when they work.
3. Collaboration - Mobile IT can support either individual or collective work arrangements.
4. Technology use - Mobile IT can be ubiquitous and transparent in everyday use, or opaque and requiring conscious engagement.
5. Impact on practices
E-learning: emerging uses,empirical results and future directions. Elizabeth T. Welsh, Connie R. Wanberg, Kenneth G. Brown and Marcia J. SimmeringThe use of network technology to deliver training is the latesttrend in the training and development industry and has beenheralded as the ‘e-learning revolution.’ In an effort to separatehype from reality, this paper reviews practitioner and researchliterature on e-learning, incorporating unpublished informa-tion from interviews with managers and consultants directlyinvolved in e-learning initiatives. Specific attention is given towhy organizations use e-learning, what the potential draw-backs to e-learning are, what we know from research about e-learning and what the future of e-learning may hold.
How institutions make decisions to accept or reject technology innovation has been explored by academics with the assistance of the Technology Acceptance Model (TAM). Scenarios involving successful delivery of online learning from degree granting universities guide this literature review. It examines decision processes influenced by TAM methods combined with dominant research perspectives such as Self-efficacy Theory and Universal Technology Adoption and Use Theory. This paper analyzes which variables determine perceptions of usefulness, attitude and preferences and become frequent factors to influence typical TAM results. It identifies patterns about reliable predictors of outcomes (behaviors, aligning IT and preferences) for educational investments in learning environments, content delivery and teacher preferences. Adoption of technology is a complex, inherently social process guided by perceptions or misperception of value and ease of use. Thus, facilitating a decision to adopt devices, software or processes must address emotional, cognitive, and contextual concerns of all stakeholders.
Prepared for TCC conference, 2011
Perfectessay.net research paper sample #6 apa styleDavid Smith
Modeling allows for the development of an analytical framework for understanding phenomena through representing their logical, mathematical, and physical characteristics. A model presents a conceptual representation of something that exists in the real world, like a map. It provides a quantitative representation of qualitative real-world aspects. Models are designed using empirical data and must be consistent with that data. Organizations use multiple models to better understand complex internal and external systems over time and increase efficiency. Factors like simulation, structure, and visualization are important in scientific modeling across fields like ecology, economics, and behavior.
MITIGATION TECHNIQUES TO OVERCOME DATA HARM IN MODEL BUILDING FOR MLijaia
Given the impact of Machine Learning (ML) on individuals and the society, understanding how harm might
be occur throughout the ML life cycle becomes critical more than ever. By offering a framework to
determine distinct potential sources of downstream harm in ML pipeline, the paper demonstrates the
importance of choices throughout distinct phases of data collection, development, and deployment that
extend far beyond just model training. Relevant mitigation techniques are also suggested for being used
instead of merely relying on generic notions of what counts as fairness.
An Examination of the Prior Use of E-Learning Within an Extended Technology A...Maurice Dawson
The purpose of this empirical study was to test specific factors of behavioral intention to use m-learning in a community college setting using a modified technology acceptance model and antecedent factors suggested by the researcher’s review of the literature. In addition, the study’s purpose was to expand understanding of behavioral intention to use m-learning and to contribute to the growing body of research. This research model was based on relevant technology acceptance literature. The study examines the significance of “prior use of e-learning” and correlation with the behavioral intention to use m-learning. Existing models have looked at prior use of e-learning in other domains, but not specifically m-learning. Other models and studies have primarily looked at the prior use of e-learning variable as a moderating variable and not one that is directly related to attitude and behavioral intention. The study found that there is a relationship between prior use of e-learning and behavioral intention to use m-learning. This research direction was proposed by Lu and Viehland.
1. The document discusses the Technology Acceptance Model (TAM), which aims to explain and predict user acceptance of technology. TAM focuses on how perceived ease of use and perceived usefulness influence attitudes, behavioral intention, and actual technology use.
2. The document reviews several studies that have applied TAM across different contexts like education. It finds that TAM is useful for understanding factors that influence teacher and student acceptance of educational technologies.
3. However, the document also notes some weaknesses of TAM, such as its reliance on self-reported data and the broad nature of perceived ease of use and usefulness constructs. It suggests TAM needs more research in primary/secondary school settings.
The UTAUT model aims to explain user intentions to use information systems and subsequent usage behavior. It was developed by reviewing and consolidating eight previous models of technology acceptance. The UTAUT model proposes four key constructs that influence usage intention and behavior: performance expectancy, effort expectancy, social influence, and facilitating conditions. Gender, age, experience, and voluntariness of use are hypothesized to moderate the impact of the four constructs. Several studies have applied the UTAUT model to domains such as mobile service adoption, social media adoption, and computer use frequency. Some researchers have also extended the UTAUT model by adding additional constructs. However, others have critiqued the UTAUT model for having many independent variables and
This presentation is about UTAUT and UTAUT 2. In this slide also discuss briefly about UTAUT and changes made in UTAUT 2. It also discuss about how it can be applied in the classroom and the strength and weakness of using it.
José Carlos Sánchez Prieto, Susana Olmos Migueláñez and Francisco J. García-Peñalvo.
Research Group in InterAction and eLearning (GRIAL)
IUCE
University of Salamanca
_mobile learning lecturers versus students on usage and perception using the ...Lenandlar Singh
This study investigated the usage and perceptions of mobile learning (m-learning) among lecturers and students at the University of Guyana using the Unified Theory of Acceptance and Use of Technology (UTAUT) model. Surveys were administered to 508 students and 63 lecturers to examine factors influencing attitudes and intentions to use m-learning technologies. Path analysis found performance expectancy and facilitating conditions significantly influenced behavioral intention for students, while effort expectancy was most influential for lecturers. Overall, students showed higher levels of performance expectancy, effort expectancy, social influence, and attitudes toward m-learning compared to lecturers. The study recommends further research with larger lecturer samples and addressing facilitating conditions to influence lecturer use of m-learning.
Ubiquitous learning website scaffolding learners by mobile devices with info ...Seid Yesuf Ali
This document describes a system that aims to create a ubiquitous learning environment by integrating mobile devices and a web-based learning system. It discusses three key modules: 1) A learning status awareness module that analyzes student performance and sends messages about unfamiliar concepts via mobile devices. 2) A schedule reminder module that manages course schedules and reminds students of upcoming tasks. 3) A mentor arrangement module that recommends peer mentors for consultation via mobile communication. An experiment with 54 college students found that the system enhanced academic performance, task completion rates, and achievement of learning goals.
Validating Measurements of Perceived Ease Comprehension and Ease of Navigatio...drboon
Many universities are realizing that the implementation and use of online learning tool become a competitive advantage to address the actual learning needs. The purpose of this study is to determine the factors that influence users’ perceived ease of use of Webct an online learning tool. We administrated a questionnaire to undergraduate students from an university in Quebec, Canada. The results tend to corroborate that ease of comprehension and ease of navigation are the key factors which influence the perceived ease of use of WebCT. More specifically, the terms used in educational web applications must be as simple and relevant as possible. Jargon and technical terms in the wording of text used for links should be carefully avoided. This research is extending the finding of IT adoption studies by specifying what make an online tool easy to use.
This study examines factors that influence students' intention to adopt e-learning technology using an extended Technology Acceptance Model (TAM). The model incorporates perceived usefulness, perceived ease of use, social norms, and self-efficacy as determinants of behavioral intention. It also considers age and gender as moderators. The study surveyed 604 students at Brunel University who used a web-based learning system. Results found perceived usefulness, ease of use, social norms, and self-efficacy significantly influenced behavioral intention. Age moderated the effects of perceived ease of use, usefulness, and self-efficacy on intention, while gender moderated ease of use and social norms. The model explained 62% of variance in intention, out
This document discusses mobile phones as mediating tools for learning within augmented contexts. It argues that the design of mobile learning experiences needs to be re-examined to take advantage of mobile devices' affordances. Design research is presented as an approach that is iterative, interventionist, and contributes to theory building. An example of augmented contexts for development places context as a core construct for collaborative, location-based, problem solving using mobile devices. The paper concludes by outlining how design principles and implications for theory will be developed.
This document analyzes the relationship between student achievement in classic academic subjects (e.g. language arts, math, history, science) and computer-related subjects. The study examines grade data from freshman students in 2000-2001. Results show the average grade across subjects was a B, and computer grades tended to reflect trends in classic subjects. For example, students whose classic grades increased also tended to have higher computer grades. However, males on average saw declining grades overall compared to females. The document concludes the computer subject grade can often indicate trends in a student's overall academic performance.
A Multimedia Data Mining Framework for Monitoring E-Examination Environmentijma
Academic dishonesty has been a growing concern in e-learning environment due to the fact that eexamination takes place under supervised and unsupervised learning environment despite its huge advantages. The e-examination environment has faced various security breaches such as academic dishonesty (impersonation), identity theft, unauthorised access and illegal assistance as a result of inefficient measures employed. Hence, an efficient framework which will aid the monitoring of the eexamination is needed. This paper reviews the process of mining multimedia data and propose a framework for monitoring the e-examination environment in order to extract images and audio features. The framework has four major phases: data pre-processing, mining, association and post processing. The
pre-processing phases carries out the extraction and transformation of multimedia data features, the mining phase does the classification and clustering of these features, the association does pattern matching while the post processing carries out the knowledge interpretation and reporting. The approach presented in this study will allow for efficient and accurate monitoring of e-examination environment which will help provide adequate security and reduce unethical behaviour in e-examination environment.
Extending UTAUT to explain social media adoption by microbusinessesDebashish Mandal
This paper establishes inadequacies of the Unified Theory of Acceptance and Use of Technology (UTAUT) theory to explain social media adoption by microbusinesses. Literature review confirms the explaining power of UTAUT in variety of technology adoption by businesses. This paper uses UTAUT theory to implement social media technology in microbusinesses. Canonical action research method is adopted to introduce social media in microbusinesses. A post positivist approach is used to report the results based on a predetermined premise. It was found that the major constructs of performance and effort expectancy played insignificant role in establishing behavioural and adoption intention of social media by microbusinesses. Social influence and facilitating condition did not influence the behavioural intentions of the microbusiness owners. Individual characteristics and codification effort dominated the use behaviour. Goal of gaining customers leads to behavioural modification resulting in replacing of behavioural intention with goals as a superior method of predicting adoption behaviour within the context of microbusinesses. This paper extends the UTAUT to explain social media adoption in microbusinesses.
The document discusses the politics of e-learning standardization. It argues that unlike social science disciplines, e-learning standards are generally seen as neutral artifacts rather than social constructions that embody specific interests. The document surveys how standards can be understood as enabling uniformity, objectivity, and justice. While standards aim to make actions comparable over time and space, education is profoundly local and contextual, resisting rationalization through standardized content and processes.
Invited talk: Using Social Media and Mobile Devices to Mediate Informal, Professional, Work-Based Learning
John Cook
Bristol Centre for Research
in Lifelong Learning and Education (BRILLE)
University of the West of England (UWE)
http://www.uwe.ac.uk/research/brille/
http://people.uwe.ac.uk/Pages/person.aspx?accountname=campus\jn-cook
Invited talk: Centre for Learning, Knowing and Interactive Technologies, Graduate School of Education, University of Bristol
26th February, 12.30 to 13.45
This document summarizes key lessons from 11 qualitative studies of enterprise mobility conducted between 2001-2007. It explores six aspects of how mobile information technology impacts organizations:
1. Interaction - Mobile IT can mediate remote interactions by removing time/space constraints, or support situated interactions by enabling work to be done in specific locations while maintaining remote access.
2. Management of work - Mobile IT can increase organizational control over employees or give individuals more discretion over how and when they work.
3. Collaboration - Mobile IT can support either individual or collective work arrangements.
4. Technology use - Mobile IT can be ubiquitous and transparent in everyday use, or opaque and requiring conscious engagement.
5. Impact on practices
E-learning: emerging uses,empirical results and future directions. Elizabeth T. Welsh, Connie R. Wanberg, Kenneth G. Brown and Marcia J. SimmeringThe use of network technology to deliver training is the latesttrend in the training and development industry and has beenheralded as the ‘e-learning revolution.’ In an effort to separatehype from reality, this paper reviews practitioner and researchliterature on e-learning, incorporating unpublished informa-tion from interviews with managers and consultants directlyinvolved in e-learning initiatives. Specific attention is given towhy organizations use e-learning, what the potential draw-backs to e-learning are, what we know from research about e-learning and what the future of e-learning may hold.
How institutions make decisions to accept or reject technology innovation has been explored by academics with the assistance of the Technology Acceptance Model (TAM). Scenarios involving successful delivery of online learning from degree granting universities guide this literature review. It examines decision processes influenced by TAM methods combined with dominant research perspectives such as Self-efficacy Theory and Universal Technology Adoption and Use Theory. This paper analyzes which variables determine perceptions of usefulness, attitude and preferences and become frequent factors to influence typical TAM results. It identifies patterns about reliable predictors of outcomes (behaviors, aligning IT and preferences) for educational investments in learning environments, content delivery and teacher preferences. Adoption of technology is a complex, inherently social process guided by perceptions or misperception of value and ease of use. Thus, facilitating a decision to adopt devices, software or processes must address emotional, cognitive, and contextual concerns of all stakeholders.
Prepared for TCC conference, 2011
Perfectessay.net research paper sample #6 apa styleDavid Smith
Modeling allows for the development of an analytical framework for understanding phenomena through representing their logical, mathematical, and physical characteristics. A model presents a conceptual representation of something that exists in the real world, like a map. It provides a quantitative representation of qualitative real-world aspects. Models are designed using empirical data and must be consistent with that data. Organizations use multiple models to better understand complex internal and external systems over time and increase efficiency. Factors like simulation, structure, and visualization are important in scientific modeling across fields like ecology, economics, and behavior.
MITIGATION TECHNIQUES TO OVERCOME DATA HARM IN MODEL BUILDING FOR MLijaia
Given the impact of Machine Learning (ML) on individuals and the society, understanding how harm might
be occur throughout the ML life cycle becomes critical more than ever. By offering a framework to
determine distinct potential sources of downstream harm in ML pipeline, the paper demonstrates the
importance of choices throughout distinct phases of data collection, development, and deployment that
extend far beyond just model training. Relevant mitigation techniques are also suggested for being used
instead of merely relying on generic notions of what counts as fairness.
APPLYING QUALITATIVE RESEARCH IN E-LEARNING DISCUSSION AND FINDINGS FROM THR...Monica Waters
This document summarizes three case studies that applied qualitative research methods to analyze e-learning systems implementations. The case studies explored how knowledge management theory and processes could support e-learning performance. Knowledge management approaches emphasize knowledge processes and artifacts, which can be applied to e-learning through a knowledge management lifecycle model that structures the development of learning objects. The case studies provided qualitative data to investigate this relationship between knowledge management and e-learning effectiveness.
The document describes an interactive topic modeling framework that allows non-expert users to provide feedback to iteratively refine topic models. It presents a mechanism for encoding user feedback as correlations between words to guide topic modeling. More efficient inference algorithms are developed for tree-based topic models to support interactivity. The framework is evaluated with both simulated and real users, and is shown to help users navigate datasets and understand political discourse.
Understanding the role of individual learner in adaptive and personalized e-l...journalBEEI
Dynamic learning environment has emerged as a powerful platform in a modern e-learning system. The learning situation that constantly changing has forced the learning platform to adapt and personalize its learning resources for students. Evidence suggested that adaptation and personalization of e-learning systems (APLS) can be achieved by utilizing learner modeling, domain modeling, and instructional modeling. In the literature of APLS, questions have been raised about the role of individual characteristics that are relevant for adaptation. With several options, a new problem has been raised where the attributes of students in APLS often overlap and are not related between studies. Therefore, this study proposed a list of learner model attributes in dynamic learning to support adaptation and personalization. The study was conducted by exploring concepts from the literature selected based on the best criteria. Then, we described the results of important concepts in student modeling and provided definitions and examples of data values that researchers have used. Besides, we also discussed the implementation of the selected learner model in providing adaptation in dynamic learning.
Applying Machine Learning to Agricultural Databutest
This document discusses applying machine learning techniques to agricultural data. It describes a software tool called WEKA that allows experimenting with different machine learning algorithms on real-world datasets. As a case study, the document examines using machine learning to infer rules for culling less productive cows from dairy herd data. Several machine learning methods were tested on the data and produced encouraging results for using machine learning to help solve agricultural problems.
This document discusses modeling competencies and summarizes a study aimed at better understanding these competencies. It begins by defining modeling as an authentic problem-solving process that moves between reality and mathematics. It then reviews different perspectives on modeling processes and competencies. Specifically, it discusses how modeling competencies involve sub-skills related to setting up models, mathematizing, solving mathematical problems, interpreting results, and validating solutions. The study aimed to examine how well modeling lessons help students independently conduct modeling processes and to identify what full modeling competencies entail. It analyzes student abilities and mistakes to provide insights into modeling competencies.
This document proposes "datasheets for datasets" to provide standardized documentation for machine learning datasets. It notes that currently there is no standard way to document how datasets were created, what information they contain, what tasks they should and shouldn't be used for, and any ethical concerns. To address this, the document recommends creating "datasheets" for datasets by analogy to datasheets for electronic components, which provide characteristics, test results, and recommended usage. The goal is to increase transparency and accountability in machine learning.
The document reviews the history and trends in educational data mining (EDM) research. It discusses how EDM has grown from early work analyzing student-computer interaction logs to using a variety of data mining and machine learning methods. Relationship mining was historically prominent but prediction and discovery with models have increased. The document also summarizes key applications of EDM including student modeling, knowledge modeling, pedagogical support analysis, and exploring educational theories. It analyzes the most influential early EDM papers and identifies trends like using EDM to study gaming behavior and develop student models.
please help i have 40 minsItem 1In the case below, the original .pdfsantanadenisesarin13
please help i have 40 mins
Item 1
In the case below, the original source material is given along with a sample of student work.
Determine the type of plagiarism by clicking the appropriate radio button.
Original Source Material
Student Version
There is a design methodology called rapid prototyping, which has been used successfully in
software engineering. Given similarities between software design and instructional design, we
argue that rapid prototyping is a viable method for instructional design, especially for computer-
based instruction.
References:
Tripp, S. D., & Bichelmeyer, B. A. (1990). Rapid prototyping: An alternative instructional
design strategy. Educational Technology Research and Development, 38(1), 31-44.
Tripp and Bichelmeyer (1990) suggested that rapid prototyping could be an advantageous
methodology for developing innovative computer-based instruction. They noted that this
approach has been used successfully in software engineering; hence, rapid prototyping could also
be a viable method for instructional design due to many parallels between software design and
instructional design.
References:
Tripp, S. D., & Bichelmeyer, B. A. (1990). Rapid prototyping: An alternative instructional
design strategy. Educational Technology Research and Development, 38(1), 31-44.
Which of the following is true for the Student Version above?
Word-for-Word plagiarism
Paraphrasing plagiarism
This is not plagiarism
Hints
Item 2
In the case below, the original source material is given along with a sample of student work.
Determine the type of plagiarism by clicking the appropriate radio button.
Original Source Material
Student Version
Learning is a complex set of processes that may vary according to the developmental level of the
learner, the nature of the task, and the context in which the learning is to occur. As already
indicated, no one theory can capture all the variables involved in learning.
References:
Gredler, M. E. (2001). Learning and instruction: Theory into practice (4th Ed.). Upper Saddle,
NJ: Prentice-Hall.
A learning theory, there, comprises a set of constructs linking observed changes in performance
with what is thought to bring about those changes.
References:
Driscoll, M. P. (2000). Psychology of learning for instruction (2nd Ed.). Needham Heights, MA:
Allyn & Bacon.
A learning theory is made up of a set of constructs linking observed changes in performance with
whatever is thought to bring about those changes. Therefore since learning is a complex set of
processes that may vary according to the developmental level of the learner, the nature of the
task, and the context in which the learning is to occur, it is apparent that no one theory can
capture all the variables involved in learning.
Which of the following is true for the Student Version above?
Word-for-Word plagiarism
Paraphrasing plagiarism
This is not plagiarism
Hints
Item 3
In the case below, the original source material is given along with a sample of student work.
Det.
Cognitive Computing and Education and Learningijtsrd
Its enormous potential in learning spurs Cognitive Computing. The overreaching purpose here is to devise computational frameworks to help us learn better by exploiting the learning process and activities. The research challenge recognized the broad spectrum of human learning, the complex and not fully understood human learning process, and various learning factors, such as pedagogy, technology, and social elements. From the theoretical point of view, Cognitive Computing could replace existing calculators in many applications. This paper focuses on applying data mining and learning analytics, clustering student modeling, and predicting student performance when involved in the education field with possible approaches. Latifa Rahman "Cognitive Computing and Education and Learning" Published in International Journal of Trend in Scientific Research and Development (ijtsrd), ISSN: 2456-6470, Volume-6 | Issue-3 , April 2022, URL: https://www.ijtsrd.com/papers/ijtsrd49783.pdf Paper URL: https://www.ijtsrd.com/humanities-and-the-arts/education/49783/cognitive-computing-and-education-and-learning/latifa-rahman
In the last few years user modeling has become an important research area in Human Computer Interaction. A large amount of research has been conducted in this field where different approaches on user modeling are shown. In this paper, we provide an overview of the field of user modeling and describes
the different user model namely, GOMS family of models, cognitive architecture, grammar-based model, and application specific models. We have discussed a few examples of user models in each category. This paper also discusses the future challenges of this research area.
This document introduces a special section on educational multimedia. It discusses that while multimedia in education has achieved success, there are still open questions to explore, as new technologies and their use cases emerge. Three selected articles are summarized that represent current trends - automating lecture recording, adding handwriting to intelligent tutors, and application-specific music transcription. The selection covers different topics from different world regions and involves multidisciplinary collaboration, illustrating the potential and challenges in the field.
This document summarizes a Full Sail University course on learning management systems and online education. It discusses how technological tools are changing education by allowing various forms of online interaction between teachers and students. It also explores how future developments like the semantic web and Web 3.0 could lead to more personalized and collaborative learning environments that leverage collective intelligence. The document concludes by reflecting on how the course has informed the student's upcoming thesis project.
Hello Sir
We are a premier academic writing agency with industry partners in UK, Australia and Middle East and over 15 years of experience. We are looking to establish long-term relationships with industry partners and would love to discuss this opportunity further with you.
Thanks & Regards
visit our website.
www.onlineassignmenthelp.com.au
www.freeassignmenthelp.com
www.btechndassignment.cheapassignmenthelp.co.uk
www.cheapassignmenthelp.com
www.cheapassignmenthelp.co.uk/
This is the paper written about the project carried out between September 2014 - January 2015 at University of Oulu for the Ubiquitous Computing Fundamentals course.
UbiTeach is a project carried out for the Ubiquitous Computing Fundamentals course at the University of Oulu. UbiTeach is a multi-device interactive application that supports and enhance learning and teaching experiences within a classroom by offering additional means to propose and solve exercises, gain insights and feedbacks about the students. The team went through 7 steps:
- Concept Idea
- Literature survey about the state of the art
- System design
- UI design
- Prototyping
- Evaluation in-the-wild
- Final Report
Machine Learning On Big Data: Opportunities And Challenges- Future Research D...PhD Assistance
Machine Learning (ML) is rapidly used in a variety of applications. It has risen to prominence in recent years, owing in part to the emergence of big data. When it comes to big data, ML algorithms have never been more promising. Big data allows machine learning algorithms to discover finer-grained patterns and make more timely and precise predictions than ever before; however, it also poses significant challenges to machine learning, such as model scalability and distributed computing.
Learn More: https://bit.ly/2RB1buD
Contact Us:
Website: https://www.phdassistance.com/
UK NO: +44–1143520021
India No: +91–4448137070
WhatsApp No: +91 91769 66446
Email: info@phdassistance.com
The document discusses the STyLE-OLM framework for interactive open learner modelling. STyLE-OLM addressed key challenges in open learner modelling, including designing an appropriate communication medium, managing the interaction dialogue, accommodating different learner beliefs, and assessing improvements in learner model accuracy and reflection. The framework used conceptual graphs to represent the learner model and proposed a structured language using diagrammatic representations for communication. It utilized dialogue games to manage the interactive open learner modelling dialogue in a symmetrical manner. The framework was able to maintain different views of learner beliefs and was evaluated in a user study.
This is a presentation I delivered at Enterprise Data World 2018 to make the case for developing intelligent systems using a hybrid or blended approach combining statistical-based machine learning with knowledge-based approaches that involve ontologies, taxonomies or knowledge graphs.
This document summarizes a scoping study on formative e-assessment commissioned by JISC. The study used a participatory methodology involving practitioners to develop design patterns for formative e-assessment. Through literature reviews and case studies, the study explored issues in formative assessment and the role of technology. Workshops were held to develop patterns from case stories and apply them to future scenarios. The study concluded that collaborative elicitation of patterns from cases has potential for professional development, but formative e-assessment is a complex topic that requires further work.
Similar to Machine Learning for User Modeling (20)
Este documento analiza el modelo de negocio de YouTube. Explica que YouTube y otros sitios de video online representan un nuevo modelo de negocio para contenidos audiovisuales debido al cambio en los hábitos de consumo causado por las nuevas tecnologías. Describe cómo YouTube aprovecha la participación de los usuarios para mejorar continuamente y atraer una audiencia diferente a la de los medios tradicionales.
The defense was successful in portraying Michael Jackson favorably to the jury in several ways:
1) They dressed Jackson in ornate costumes that conveyed images of purity, innocence, and humility.
2) Jackson was shown entering the courtroom as if on a red carpet, emphasizing his celebrity status.
3) Jackson appeared vulnerable, childlike, and in declining health during the trial, eliciting sympathy from jurors.
4) Defense attorney Tom Mesereau effectively presented a coherent narrative of Jackson as a victim and portrayed Neverland as a place of refuge, undermining the prosecution's arguments.
Michael Jackson was born in 1958 in Gary, Indiana and rose to fame in the 1960s as the lead singer of The Jackson 5, topping music charts in the 1970s. As a solo artist in the 1980s, his album Thriller broke music records. In the 1990s and 2000s, Jackson faced several legal issues related to child abuse allegations while continuing to release music. He married Lisa Marie Presley and Debbie Rowe and had two children before his death in 2009.
Popular Reading Last Updated April 1, 2010 Adams, Lorraine The ...butest
This document appears to be a list of popular books from various authors. It includes over 150 book titles across many genres such as fiction, non-fiction, memoirs, and novels. The books cover a wide range of topics from politics to cooking to autobiographies.
The prosecution lost the Michael Jackson trial due to several key mistakes and weaknesses in their case:
1) The lead prosecutor, Thomas Sneddon, was too personally invested in the case against Jackson, having pursued him for over a decade without success.
2) Sneddon's opening statement was disorganized and weak, failing to effectively outline the prosecution's case.
3) The accuser's mother was not credible and damaged the prosecution's case through her erratic testimony, history of lies and con artist behavior.
4) Many prosecution witnesses were not credible due to prior lawsuits against Jackson, debts owed to him, or having been fired by him. Several witnesses even took the Fifth Amendment.
Here are three examples of public relations from around the world:
1. The UK government's "Be Clear on Cancer" campaign which aims to raise awareness of cancer symptoms and encourage early diagnosis.
2. Samsung's global brand marketing and sponsorship activities which aim to increase brand awareness and favorability of Samsung products worldwide.
3. The Brazilian government's efforts to improve its international image and relations with other countries through strategic communication and diplomacy.
The three most important functions of public relations are:
1. Media relations because the media is how most organizations reach their key audiences. Strong media relationships are crucial.
2. Writing, because written communication is at the core of public relations and how most information is
Michael Jackson Please Wait... provides biographical information about Michael Jackson including his birthdate, birthplace, parents, height, interests, idols, favorite foods, films, and more. It discusses his background, career highlights including influential albums like Thriller, and films he appeared in such as The Wiz and Moonwalker. The document contains photos and details about Jackson's life and illustrious music career.
The MYnstrel Free Press Volume 2: Economic Struggles, Meet Jazzbutest
The document discusses the process of manufacturing celebrity and its negative byproducts. It argues that celebrities are rarely the best in their individual pursuits like singing, dancing, etc. but become famous due to being products of a system controlled by wealthy elites. This system stifles opportunities for worthy artists and creates feudalism. The document also asserts that manufactured celebrities should not be viewed as role models due to behaviors like drug abuse and narcissism that result from the celebrity-making process.
Michael Jackson was a child star who rose to fame with the Jackson 5 in the late 1960s and early 1970s. As a solo artist in the 1970s and 1980s, he had immense commercial success with albums like Off the Wall, Thriller, and Bad, which featured hit singles and groundbreaking music videos. However, his career and public image were plagued by controversies related to allegations of child sexual abuse in the 1990s and 2000s. He continued recording and performing but faced ongoing media scrutiny into his private life until his death in 2009.
Social Networks: Twitter Facebook SL - Slide 1butest
The document discusses using social networking tools like Twitter and Facebook in K-12 education. Twitter allows students and teachers to share short updates and can be used to give parents a window into classroom activities. Facebook allows targeted advertising that could be used to promote educational activities. Both tools could help facilitate communication between schools and communities if used properly while managing privacy and security concerns.
Facebook has over 300 million active users who log on daily, and allows brands to create public profile pages to interact with users. Pages are for brands and organizations only, while groups can be made by any user about any topic. Pages do not show admin names and have no limits on fans, while groups display admin names and are limited to 5,000 members. Content on pages should aim to provoke action from subscribers and establish a regular posting schedule using a conversational tone.
Executive Summary Hare Chevrolet is a General Motors dealership ...butest
Hare Chevrolet is a car dealership located in Noblesville, Indiana that has successfully used social media platforms like Twitter, Facebook, and YouTube to create a positive brand image. They invest significant time interacting directly with customers online to foster a sense of community rather than overtly advertising. As a result, Hare Chevrolet has built a large, engaged audience on social media and serves as a model for how brands can use online presences strategically.
Welcome to the Dougherty County Public Library's Facebook and ...butest
This document provides instructions for signing up for Facebook and Twitter accounts. It outlines the sign up process for both platforms, including filling out forms with name, email, password and other details. It describes how the platforms will then search for friends and suggest people to connect with. It also explains how to search for and follow the Dougherty County Public Library page on both Facebook and Twitter once signed up. The document concludes by thanking participants and providing a contact for any additional questions.
Paragon Software announces the release of Paragon NTFS for Mac OS X 8.0, which provides full read and write access to NTFS partitions on Macs. It is the fastest NTFS driver on the market, achieving speeds comparable to native Mac file systems. Paragon NTFS for Mac 8.0 fully supports the latest Mac OS X Snow Leopard operating system in 64-bit mode and allows easy transfer of files between Windows and Mac partitions without additional hardware or software.
This document provides compatibility information for Olympus digital products used with Macintosh OS X. It lists various digital cameras, photo printers, voice recorders, and accessories along with their connection type and any notes on compatibility. Some products require booting into OS 9.1 for software compatibility or do not support devices that need a serial port. Drivers and software are available for download from Olympus and other websites for many products to enable use with OS X.
To use printers managed by the university's Information Technology Services (ITS), students and faculty must install the ITS Remote Printing software on their Mac OS X computer. This allows them to add network printers, log in with their ITS account credentials, and print documents while being charged per page to funds in their pre-paid ITS account. The document provides step-by-step instructions for installing the software, adding a network printer, and printing to that printer from any internet connection on or off campus. It also explains the pay-in-advance printing payment system and how to check printing charges.
The document provides an overview of the Mac OS X user interface for beginners, including descriptions of the desktop, login screen, desktop elements like the dock and hard disk, and how to perform common tasks like opening files and folders. It also addresses frequently asked questions for Windows users switching to Mac OS X, such as where documents are stored, how to save or find documents, and what the equivalent of the C: drive is in Mac OS X. The document concludes with sections on file management tasks like creating and deleting folders, organizing files within applications, using Spotlight search, and an overview of the Dashboard feature.
This document provides a checklist for securing Mac OS X version 10.5, focusing on hardening the operating system, securing user accounts and administrator accounts, enabling file encryption and permissions, implementing intrusion detection, and maintaining password security. It describes the Unix infrastructure and security framework that Mac OS X is built on, leveraging open source software and following the Common Data Security Architecture model. The checklist can be used to audit a system or harden it against security threats.
This document summarizes a course on web design that was piloted in the summer of 2003. The course was a 3 credit course that met 4 times a week for lectures and labs. It covered topics such as XHTML, CSS, JavaScript, Photoshop, and building a basic website. 18 students from various majors enrolled. Student and instructor evaluations found the course to be very successful overall, though some improvements were suggested like ensuring proper software and pairing programming/non-programming students. The document also discusses implications of incorporating web design material into existing computer science curriculums.
1. User Modeling and User-Adapted Interaction 11: 19^29, 2001. 19
# 2001 Kluwer Academic Publishers. Printed in the Netherlands.
Machine Learning for User Modeling
GEOFFREY I. WEBB1, MICHAEL J. PAZZANI2 and DANIEL BILLSUS2
1
School of Computing and Mathematics, Deakin University, Geelong, Victoria 3217, Australia
2
Department of Information and Computer Science, University of California, Irvine,
Irvine, California 92697, U.S.A.
(Received: 12 November 1999; in revised form 22 May 2000)
Abstract. At ¢rst blush, user modeling appears to be a prime candidate for straightforward appli-
cation of standard machine learning techniques. Observations of the user's behavior can provide
training examples that a machine learning system can use to form a model designed to predict
future actions. However, user modeling poses a number of challenges for machine learning that
have hindered its application in user modeling, including: the need for large data sets; the need
for labeled data; concept drift; and computational complexity.This paper examines each of these
issues and reviews approaches to resolving them.
Key words: user modeling, machine learning, concept drift, computational complexity,World
Wide Web, information agents
1. Introduction
The past decade has seen research into the use of machine learning to support user
modeling (ML for UM) pass through a period of decline and then resurgence, with
the research area at the close of the twentieth century more active and vibrant than
at any previous time. It is tempting to identify the start of the ML for UM winter
as being marked by the publication of Self's (1988) paper in which he asserted that
a search problem that appeared to underlie a direct machine learning approach
to inferring possible cognitive process models for a relatively simple modeling task
was `clearly intractable'. While the paper did not argue that student modeling
was intractable per se, the phrase `the intractable problem of student modeling',
taken from the title of that paper, has been oft repeated, perhaps with less attention
to the ¢ner detail of the argument within the paper than might be desired. Without
needing to ascribe causes to the ML for UM winter, it is notable that it was preceded
by a decade of much activity. Notable examples from this period include the work of
Brown and Burton (1978), Brown and VanLehn (1980), Gilmore and Self (1988),
Langley and Ohlsson (1984), Mizoguchi et al. (1987), Reiser et al. (1985), Sleeman
(1984), VanLehn (1982), and Young and O'Shea (1981), much of it in the area
of student modeling.* In contrast, the period 1988^1994 saw relatively little activity
in the area. A strong resurgence is evidenced however by a special issue of this
* We consider student modeling to be a form of user modeling.
2. 20 GEOFFREY I. WEBB ET AL.
journal devoted to the subject (volume 8, numbers 1^2, 1998) the number of recent
workshops on the subject (Bauer et al., 1997; Bauer et al., 1999; Joachims et al.,
1999; Rudstorm et al., 1999; Papatheodorou, 1999), and sessions in major confer-
ences (Goettl et al., 1998; Jameson et al., 1997; Kay, 1999; Lajoie and Vivet, 1999.
It is, perhaps, tempting to equate the start of the thaw with the presentation of
the best paper award to Martin and VanLehn's (1993) paper on student modeling
at the 1993 World Conference on Arti¢cial Intelligence in Education.
While the ¢eld was initially dominated by research on student modeling, the
demands of electronic commerce and the world-wide-web have led to rapid growth
in research in the area of information retrieval. With vast quantities of information
available to all users on the web, the need for technologies to personalize the
web has arisen.
This paper provides a brief overview of the application of machine learning for
user modeling and reviews four critical issues that are currently limiting the real
world application of user modeling and looks at the current state of attempts to
overcome them. The four issues addressed are:
^ the need for large data sets;
^ the need for labeled data;
^ concept drift; and
^ computational complexity.
2. Machine Learning and User Modeling
The forms that a user model may take are as varied as the purposes for which user
models are formed. User models may seek to describe
(1) the cognitive processes that underlie the user's actions;
(2) the di¡erences between the user's skills and expert skills;
(3) the user's behavioral patterns or preferences; or
(4) the user's characteristics.
Early applications of machine learning in user modeling focused on the ¢rst two of
these model types, with particular emphasis paid to developing models of cognitive
processes. In contrast, recent research has predominantly pursued the third
approach, focusing on users' behavior, as advocated by Webb (1993), rather than
on the cognitive processes that underlie that behavior. Applications of machine
learning to discovering users' characteristics remain rare.
Another important dimension along which it is important to distinguish
approaches is with respect to whether they model individual users or communities
of users. Whereas much of the academic research in ML for UM concentrates
on modeling individual users, many of the emerging applications of ML for UM
in electronic commerce relate to forming generic models of user communities.
3. MACHINE LEARNING FOR USER MODELING 21
For example, very substantial increases in purchases are claimed for systems that
recommend products to users of retail web sites using models based on purchases
by other users (as exempli¢ed by Ungar and Foster, 1998).
Situations in which the user repeatedly performs a task that involves selecting
among several prede¢ned options appear ideal for using standard machine learning
techniques to form a model of the user. One example of such a task is processing
e-mail by deleting some messages and ¢ling others into folders (Segal and Kephart,
1999). Another example is to determine which news articles to read from a web
page (Billsus and Pazzani, 1999). In such situations, the information available
to the user to describe the problem and the decision made can serve as the training
data for a learning algorithm. The algorithm will create a model of a user's decision
making process that can then be used to emulate the user's decisions on future
problems. At ¢rst glance, it may be tempting to consider such user modeling prob-
lems as straightforward standard classi¢cation learning tasks. However, user
modeling presents a number of very signi¢cant challenges for machine learning
applications. The following sections address some of the key challenges that it
poses.
3. The Need for Large Data Sets
The Syskill and Webert system (Pazzani and Billsus, 1997) is a straightforward
implementation of a machine learning algorithm (a simple Bayesian classi¢er)
applied to the problem of recommending web sites. As a user browses the web,
the user indicates whether a web page is interesting (by clicking on a `thumbs
up' button on the web browser) or not interesting (by clicking on `thumbs down').
The system then annotates unseen links on the web pages with an assessment of
whether the user would be interested.
One important limitation of the straightforward application of machine learning
systems such as Syskill and Webert to real world user modeling tasks is that the
learning algorithm does not build a model with acceptable accuracy until it sees
a relatively large number of examples (e.g. 50). In most situations, it is natural that
learning algorithms require many training examples to be accurate (Valiant, 1984)
since there are typically a large number of alternative models to select from. This
problem is addressed in a variety of ways:
^ Knowledge-based learning approaches, such as theory re¢nement (Ba¡es and
Mooney, 1996), create a new model by modifying an initial model. If an accurate
model of the user is close to the initial model, few examples may be required
to transform accurately the initial model into the user model. This may be
the case in student modeling where the initial model is the `correct' model,
and the student model to be acquired is close to the correct model. This assumes,
however, that there is a single `correct' model that can serve as a suitable initial
model. Attempting to model incorrect performance as a perturbation of a
4. 22 GEOFFREY I. WEBB ET AL.
`correct' model that does not correspond to the basic underlying strategy of the
user or student may be seriously misleading. For instance, there are several
substantially di¡erent `correct' procedures for the relatively simple skill of elemen-
tary subtraction (see, for example,Young and O'Shea, 1981). Minor perturbations
of each of these procedures may result in substantial di¡erences in predictions
about future performance.
^ Some approaches to learning (e.g. nearest neighbor algorithms) can be fairly
accurate with a few examples if the new examples are very similar to the training
examples. NewsDude (Billsus and Pazzani, 1999) takes advantage of this to
recommend news stories that follow up on stories the user read previously.
^ In some cases, it is possible to structure the task so that a learned model need not
exactly replicate the user's decision. For example, the SwiftFile system
(formerly known as MailCat, Segal and Kephart, 1999) does not automatically
¢le mail into users' folders, but rather puts the three most likely folders for a
message on a prominent place on the screen. By having more than one option
available and not hindering the user from taking actions that were not
anticipated, the system does not have to have an accurate model to be useful.
4. The Need for Labeled Data
Another dif¢culty confronting direct application of machine learning to many user
modeling tasks is that the supervised machine learning approaches used require
explicitly labeled data, but the correct labels may not be readily apparent from
simple observation of the user's behavior. Consider again the example of Syskill
and Webert. It would be very dif¢cult to infer from a web user's browsing behavior
which web pages they found interesting and which they did not. However, Syskill
and Webert requires these labels in order to be able to make recommendations.
The solution in this case has been to require the user to explicitly label the data
by clicking a `thumbs up' or `thumbs down' button. The user must perform
additional work to provide explicit feedback to the system (by clicking on a button)
but is not provided with an immediate reward. Users rarely provide information
to the modeling system if they must go out of their way or if they see no immediate
bene¢t.
One approach to this problem is to infer the labels from the user's behavior. For
example, the Letizia system (Lieberman, 1995) infers that a user is interested in
a web page if a variety of actions are performed (e.g. printing the page or creating
a bookmark), while the user is not interested under other circumstances (e.g. by
quickly hitting the back button). Such implicit feedback methods allow a large
amount of data to be collected unobtrusively. One can imagine future systems that
would use the user's facial expression, body language or other forms of implicit
feedback for this purpose.
Another approach to the problem is to use a small initial body of labeled
examples to infer labels for a larger body of examples which is then used to train
5. MACHINE LEARNING FOR USER MODELING 23
the learning algorithm. This technique is related to the information retrieval
method of pseudo-feedback (Kwok and Chan, 1998) in which ¢rst the system ¢nds
documents similar to the user's query and then it ¢nds documents similar to the
retrieved documents. However, in the machine learning approach (Nigam et al.,
1998), the process of inferring the label for unseen documents is repeated until
a stable solution is found via a procedure known as expectation maximization.
As well as circumventing the problem of training sets sizes, as discussed in the
last section, this technique reduces the demand on the user to label training cases
by reducing the number of labeled cases that are required. These approaches
are currently in their infancy but are likely to have a big impact on the ¢eld into
the future.
5. Concept Drift
Early approaches to the use of machine learning for user modeling tended to
develop new, special purpose, and frequently ad hoc, machine learning techniques
to support their speci¢c needs. More recently, there has been a tendency to seek
an adequate problem representation in the form of training examples and corre-
sponding class labels in order to be able to draw on well-known algorithms
and results from the vast literature on classi¢cation learning. A potential pitfall
of this methodology is that it might lead to solutions that are not speci¢cally geared
towards the unique characteristics of user modeling applications. For example,
user modeling is known to be a very dynamic modeling task ^ attributes that
characterize a user are likely to change over time. Therefore, it is important that
learning algorithms be capable of adjusting to these changes quickly. From a
machine learning perspective, this is a challenging problem known as concept drift
(Widmer and Kubat, 1996).
In order to emphasize the importance of this problem and further clarify the
issues involved, we report on recent developments in the use of user models
for Information Retrieval (IR) applications.
As part of the advent of the World Wide Web and the recent resurgence of
machine learning for user modeling research, IR tasks have received much
attention. This problem is well illustrated by the demands of user modeling for
information retrieval. The main objective is to learn a model of the user's interests
or information need, in order to facilitate retrieval of relevant information. Most
work on content-based information ¢ltering casts the automated acquisition of
user pro¢les as a text classi¢cation task (for example, Pazzani and Billsus, 1997;
Lang, 1995; Mooney and Roy, 1998). In these systems, a set of text documents
rated by the user (e.g. interesting vs. not interesting) is used as the input for a
learning algorithm, and the resulting classi¢er can be interpreted as an auto-
matically-induced model of the user's interests. An underlying assumption often
made is that more training data leads to improved predictive performance.
However, if we take into account that a user's interests are dynamic and are likely
6. 24 GEOFFREY I. WEBB ET AL.
to change over time, this assumption does not hold. A classi¢er built from a large
number of training documents that accurately re£ect the user's past interests is
of limited practical use and might perform substantially worse than a classi¢er
limited to recent data that re£ects the user's current interests. This example illus-
trates that a good text classi¢cation algorithm is not necessarily a useful user
modeling algorithm.
As researchers have begun to take the importance of concept drift for user
modeling applications into account, a few initial solutions have emerged in the
literature. A straightforward approach is simply to place less weight on older obser-
vations of the user (for example, Webb and Kuzmycz, 1996). However, there is some
evidence that the effectiveness of this simple approach is constrained (Webb et al.,
1997). Klinkenberg and Renz (1998) explore windowing techniques similar to ideas
proposed by Widmer and Kubat (1996) in the context of Information Retrieval.
The central idea is to limit training data to an adjustable time window, where
the window size depends on observed indicators such as sudden changes in term
distributions.
Chiu and Webb (1998) have studied the induction of dual user models as an
approach for handling concept drift in the context of student modeling. In general,
user modeling is a task with inherent temporal characteristics. We can assume
recently collected user data to re£ect the current knowledge, preferences or abilities
of a user more accurately than data from previous time periods. However, restricting
models to recent data can lead to overly speci¢c models, i.e. models that classify
instances that are similar to recently collected data with high precision, but perform
poorly on instances that deviate from data used to induce the model. To overcome
this problem, Chiu and Webb use a dual model that classi¢es instances by ¢rst con-
sulting a model trained on recent data, and delegating classi¢cation to a model
trained over a longer time period if the recent model is unable to make a prediction
with suf¢cient con¢dence.
Billsus and Pazzani (1999) propose a related idea for personalized recommen-
dation of news stories. A nearest-neighbor text classi¢cation algorithm built from
recent observations forms a short-term model of the user's interests in daily news
stories. In cases where the short-term model cannot make a prediction with suf-
¢cient con¢dence, classi¢cation is delegated to a more general classi¢er based
on observations collected over a longer period of time. This architecture allows
a system to adjust to interest changes rapidly, without sacri¢cing the potential
bene¢ts of data collection over longer time periods. Furthermore, this system tries
to automatically anticipate a special case of concept drift: news stories that are
presented to the user are assumed to directly affect the user's information need.
As a result, the system tries to prevent presenting similar information multiple
times, as it is assumed that a certain piece of information is only interesting once,
and that the concept of what is considered interesting drifts at that time.
While a start has been made on tackling this challenging problem, this is an area in
which more progress is required if user modeling is to realize its full potential.
7. MACHINE LEARNING FOR USER MODELING 25
6. Computational Complexity
The current ML for UM resurgence has witnessed tremendous research activity. In
contrast, the ¢eld still has a dearth of ¢elded applications. The resulting difference
between research interest and commercially deployed systems is especially apparent
in the ¢eld of Internet-based applications. The growth of the Internet has had a
tremendous impact on the ¢eld of ML for UM over the past decade, as researchers
have realized the potential of learning techniques for automated information
retrieval assistance, resulting in a surge in research on intelligent information agents.
However, the actual impact of this technology on the average web user has been
fairly limited. We speculate that one reason for this effect is the computational com-
plexity of many approaches proposed in academic research. While the Internet has
paved the way for new opportunities to assist users through the use of detailed user
models, the sheer amount of information available as well as the number of users
online has created new challenges. It is not uncommon for big portal sites (e.g.
Yahoo, Excite or Lycos) to receive millions of visits per day. Clearly, if every
one of these users were to be assisted through the use of automatically acquired
user models, computational complexity would play a major role in the viability
of user modeling on the Internet.
In contrast, academic research in machine learning is often dominated by a com-
petitive race for improved predictive accuracy. When a new algorithm is proposed,
it is not uncommon that an empirically measured increase of a fraction of a percent
in predictive accuracy is considered a success if the result is statistically signi¢cant.
While we realize that there are domains where these subtle accuracy improvements
make a crucial difference, we think that ML for UM is not such a domain. For
example, an algorithm that recommends interesting information with a predictive
accuracy of 78% might be preferred over an algorithm that achieves 80%, if the
former algorithm requires considerably less CPU time, and therefore allows for
deployment in high-volume real-world scenarios.
At a ¢rst glance, the constraints imposed by the need for ef¢cient user modeling
algorithms seem to exclude many computationally expensive learning algorithms
and data analysis techniques from consideration for user modeling tasks. For
example, reducing the need for labeled training data through expectation
maximization (Nigam et al., 1998) leads to improved predictive performance,
but causes a signi¢cant increase in CPU time. However, computationally expensive
algorithms can still be utilized if they can be applied in scenarios where models
can be learned of£ine, i.e. without real-time constraints that would require short
response times. Initial work with a focus on computational complexity and suit-
ability for large-scale deployment is starting to emerge in the literature. While
not strictly a machine learning approach, Jester 2.0 is a collaborative ¢ltering system
that models a user's taste in humor, based on similarities to other users' ratings for
jokes (Gupta et al., 1999). The underlying idea of the proposed algorithm is to speed
up the recommendation process through the use of a preprocessing step based on
8. 26 GEOFFREY I. WEBB ET AL.
principal component- and cluster analysis. Since the preprocessing step can be
performed of£ine, online recommendations can be computed ef¢ciently. We believe
that this is a step in the right direction and hope that future research in this ¢eld
will be geared towards techniques that are directly applicable to real-world
applications in order to make the bene¢ts of ML for UM available to a broad
audience.
7. Conclusion
ML for UM has awoken from the winter of the early nineties with renewed strength
and vigor, fueled largely by the demands of the internet and other emerging infor-
mation retrieval technologies. However, despite clear potential and demand for
ML for UM technologies, they remain primarily in the research domain. We are
yet to witness the widespread appearance of ¢elded applications.
In this paper we have outlined four major issues that must be overcome before
widespread application of ML for UM will be possible:
^ the need for large data sets;
^ the need for labeled data;
^ concept drift; and
^ computational complexity.
While the dif¢culty of these problems should not be underestimated, as we indicate,
approaches to overcoming them are being actively pursued and strong progress
has been made. Looking forward it appears evident that ML for UM is a research
area on the cusp of coming-of-age and that by the time of the twentieth anniversary
of this journal, ML for UM will have taken a place as a core technology underlying
the information economy.
Acknowledgments
Pazzani's research on machine learning has been supported by National Science
Foundation Grant 9731990. The paper has bene¢ted from comments and sugges-
tions by Alfred Kobsa, Ingrid Zukerman, and David Albrecht.
References
Baffes, P. and Mooney, R.: 1996, Re¢nement-based student modeling and automated bug
library construction, Journal of Arti¢cial Intelligence in Education 7, 75^116.
Bauer, M., Pohl, W. and Webb, G. (eds.): 1997, UM97 Workshop: Machine Learning for User
Modeling. Online proceedings: http://www.dfki.uni-sb.de/$ bauer/um-ws/.
Bauer, M., Gmytrasiewicz, P. and Pohl, W. (eds.): 1999, UM99 Workshop: Machine Learning
for User Modeling. Online proceedings: http://www.dfki.de/$ bauer/um99-ws/.
9. MACHINE LEARNING FOR USER MODELING 27
Billsus, D. and Pazzani, M.: 1999, A hybrid user model for news story classi¢cation. In: User
Modeling (Proceedings of the Seventh International Conference). Banff, Canada, pp.
99^108.
Brown, J. S. and Burton, R. R.: 1978, Diagnostic models for procedural bugs in basic math-
ematical skills. Cognitive Science 2, 155^192.
Brown, J. S. and VanLehn, K.: 1980, Repair theory: A generative theory of bugs in procedural
skills. Cognitive Science 4, 379^426.
Chiu, P. and Webb, G.: 1998, Using decision trees for agent modeling: improving prediction
performance. User Modeling and User-Adapted Interaction 8, 131^152.
Gilmore, D. and Self, J.: 1988, The application of machine learning to intelligent tutoring
systems. In: J. Self (ed.): Arti¢cial Intelligence and Human Learning: Intelligent Com-
puter-Aided Learning. London: Chapman and Hall, pp. 179^196.
Goettl, B., Halff, H., Red¢eld, C. and Shute, V. (eds.): 1998, Intelligent Tutoring Systems:
Fourth International Conference, ITS'98. Berlin: Springer.
Gupta, D., DiGiovanni, M., Narita, H.and Goldberg, K.: 1999, Jester 2.0 : A new linear time
collaborative ¢ltering algorithm applied to jokes. In: Proceedings of the SIGIR-99 Work-
shop on Recommender Systems: Algorithms and Evaluation. Berkeley, CA.
Jameson, A., Paris, C. and Tasso, C. (eds.): 1997, User Modeling (Proceedings of the Sixth
International Conference UM97). New York: SpringerWien.
Joachims, T., McCallum, A., Sahami, M. and Ungar, L. (eds.): 1999, IJCAI Workshop IRF-2:
Machine Learning for Information Filtering. New York: IJCAI Inc.
Kay, J. (ed.): 1999, User Modeling: Proceedings of the Seventh International Conference
UM99. New York: SpringerWien.
Klinkenberg, R. and Renz, I.: 1998, Adaptive information ¢ltering: learning in the presence of
concept drift. In: AAAI/ICML-98 Workshop on Learning for Text Categorization. Tech-
nical Report WS-98-05. Madison, Wisc.
Kwok, K. and Chan, M.: 1998, Improving two-stage ad-hoc retrieval for short queries. In:
Proceedings of the 21st Annual International ACM SIGIR Conference on Research and
Development in Information Retrieval. Melbourne, Australia, pp. 250^256.
Lajoie, S. P. and Vivet, M. (eds.): 1999, Arti¢cial Intelligence in Education: Proceedings of the
Ninth International Conference AIEd-99. Amsterdam: IOS Press.
Lang, K.: 1995, NewsWeeder: Learning to ¢lter news. In: Proceedings of the Twelfth Inter-
national Conference on Machine Learning. Lake Tahoe, CA., pp. 331^339.
Langley, P. and Ohlsson, S.: 1984, Automated cognitive modeling. In: Proceedings of the
Second National Conference on Arti¢cial Intelligence, pp. 193^197.
Lieberman, H.: 1995, An agent that assists web browsing. In: Proceedings of the International
Joint Conference on Arti¢cial Intelligence. Montreal, Canada, pp. 924^929.
Martin, J. and VanLehn, K.: 1993, OLAE: Progress toward a multi-activity, bayesian student
modeler. In: Proceedings of the 1993 World Conference on Arti¢cial Intelligence in
Education. Edinburgh, Scotland, pp. 410^417.
Mizoguchi, R., Ikeda, M. and Kakushu, O.: 1987, An innovative framework for intelligent
tutoring systems. In: Arti¢cial Intelligence Tools in Education. Amsterdam-New York,
pp. 105^120.
Mooney, R., Bennet, P. and Roy, L.: 1998, Book recommending using text categorization with
extracted information. In: AAAI/ICML-98 Workshop on Learning for Text
Categorization. Madison, Wisc.
Nigam, K., McCallum, A., Thrun, S. and Mitchell, T.: 1998, Learning to classify text from
labeled and unlabeled documents. In: Proceedings of the 15th International Conference
on Arti¢cial Intelligence. Madison, Wisc., pp. 792^799.
10. 28 GEOFFREY I. WEBB ET AL.
Papatheodorou, C. (ed.): 1999, Machine Learning and Applications Workshop W03, Machine
Learning in User Modeling, Chania, Greece.
Pazzani, M. and Billsus, D.: 1997, Learning and revising user pro¢les: The identi¢cation of
interesting web sites. Machine Learning 27, 313^331.
Reiser, B. J., Anderson, J. R. and Farrell, R. G.: 1985, Dynamic student modelling in an
intelligent tutor for LISP programming. In: Proceedings of the Ninth International Joint
Conference on Arti¢cial Intelligence. Los Angeles, CA, pp. 8^14.
Rudstorm, A., Bauer, M., Iba, W. and Pohl, W. (eds.): 1999, IJCAI Workshop ML-4:
Learning About Users. IJCAI Inc.
Segal, R. and Kephart, M.: 1999, MailCat: An intelligent assistant for organizing e-mail. In:
Proceedings of the Third International Conference on Autonomous Agents. Seattle, WA,
pp. 276^282.
Self, J. A.: 1988, Bypassing the intractable problem of student modelling. In: Proceedings of
the Intelligent Tutoring Systems Conference. Montreal, pp. 107^123.
Sleeman, D. H.: 1984, Inferring student models for intelligent computer-aided instruction. In:
R. S. Michalski, J. G. Carbonell, and T. M. Mitchell (eds.): Machine Learning: An Arti¢cial
Intelligence Approach. Berlin: Springer-Verlag, pp. 483^510.
Ungar, L. H. and Foster, D. P.: 1998, Clustering methods for collaborative ¢ltering. In:
AAAI-98 Workshop on Recommender Systems. Madison, Wisc.
Valiant, L. G.: 1984, A theory of the learnable. Communications of the ACM 27, 1134^1142.
VanLehn, K.: 1982, Bugs are not enough: empirical studies of bugs, impasses, and repairs in
procedural skills. Journal of Mathematical Behavior 3, 3^72.
Webb, G. I.: 1993, Feature based modelling. In: Proceeding of AI-ED 93, World Conference on
Arti¢cial Intelligence in Education. Edinburgh, Scotland, pp. 497^504.
Webb, G. I., Chiu, B. C. and Kuzmycz, M.: 1997, Comparative evaluation of alternative
induction engines for Feature Based Modelling. International Journal of Arti¢cial Intelli-
gence in Education 8, 97^115.
Webb, G. I. and Kuzmycz, M.: 1996, Feature Based Modelling: A methodology for producing
coherent, consistent, dynamically changing models of agents' competencies. User Modeling
and User-Adapted Interaction 5(2), 117^150.
Widmer, G. and Kubat, M.: 1996, Learning in the presence of concept drift and hidden con-
texts. Machine Learning 23, 69^101.
Young, R. M. and O'Shea, T.: 1981, Errors in childrens' subtraction. Cognitive Science 5,
153^177.
Authors' Vitae
Geoff Webb is Professor of Computer Science at Deakin University, founder and
director of G. I. Webb and Associates Pty. Ltd. and director of the Deakin Uni-
versity Priority Area of Research in Information Technology for the Information
Economy. He received his B.A. and Ph.D. degrees in Computer Science from
La Trobe University. He has worked in several areas of arti¢cial intelligence, includ-
ing machine learning, knowledge acquisition, and user modeling.
Michael Pazzani is a professor and the chair of the Information and Computer
Science Department at the University of California, Irvine. His research interests
include data mining and intelligent agents. He received his BS and MS in computer
11. MACHINE LEARNING FOR USER MODELING 29
engineering from the University of Connecticut and his PhD in computer science
from UCLA. He is a member of the AAAI and the Cognitive Science Society.
Daniel Billsus received a diploma in computer science from the Technical University
of Berlin, Germany, and M.S. and Ph.D. degrees from the University of California,
Irvine. His research focus has been in the area of intelligent information access.
He studied the use of machine learning techniques as part of various information
agents, leading to his doctoral dissertation on ``User Model Induction for Intelligent
Information Access''.