Paper presentation @ WWW 2017 (Web Mining track)
Paper by Dominik Kowald, Subhash Pujari and Elisabeth Lex @ Know-Center and Graz University of Technology
Twitter has brought much attention recently as a hot research topic in the domain of sentiment analysis. Training sentiment classifiers from tweets data often faces the data sparsity problem partly due to the large variety of short and irregular forms introduced to tweets because of the 140-character limit. In this work we propose using two different sets of features to alleviate the data sparseness problem. One is the semantic feature set where we extract semantically hidden concepts from tweets and then incorporate them into classifier training through interpolation. Another is the sentiment-topic feature set where we extract latent topics and the associated topic sentiment from tweets, then augment the original feature space with these sentiment-topics. Experimental results on the Stanford Twitter Sentiment Dataset show that both feature sets outperform the baseline model using unigrams only. Moreover, using semantic features rivals the previously reported best result. Using sentiment-topic features achieves 86.3% sentiment classification accuracy, which outperforms existing approaches.
Durkheim Project: Social Media Risk & Bayesian CountersDataWorks Summit
Cited by a 2012 TIME Magazine cover story (“One A Day”) suicide, particularly the military, is a severe public health problem: Veteran suicide rates, nearly double those of adults in the general U.S. population. And to date there has been a lack of success so far in military efforts to understand and address the suicide crisis: “No program, outreach or initiative has worked against the surge in Army suicides, and no one knows why nothing works.” (Time) In this talk we will describe how we have built a real time risk assessment framework with the US Veterans Administration. As well as how Hadoop and HBase are being used to build further systems based on our new Bayesian Counters framework to predict realtime risk. Bayesian Counters framework was, in part, developed to predict military mental health risks. Trying to help to solve this complicated puzzle, towards the goal of reducing suicidality among those who have served the nation.
1. Current tag recommendation algorithms are designed in a purely data-driven way and rely on dense/broad folksonomy structures, but most real-world folksonomies are sparse/narrow.
2. The authors investigate how cognitive processes like frequency, recency, and semantic context influence tag reuse based on the ACT-R cognitive architecture.
3. They develop a tag recommendation algorithm based on the ACT-R activation equation and show it outperforms other methods in narrow/broad folksonomies by overcoming the imbalance between recommendations and real folksonomies.
PhD defense presentation of Dominik Kowald: Modeling Activation Processes in Human Memory to Improve Tag Recommendations. Presented at Know-Center / Graz University of Technology (Austria)
This document analyzes the Twitter usage of 37 astrophysicists. It finds that on average, 23% of their tweets contained hashtags. The top 10 hashtags were identified, with #fb being the most common. Regular Twitter users tended to include hashtags more than infrequent users. However, the astrophysicist community did not strongly share hashtags, as many were only used once, suggesting hashtags were not used to build communities. This analysis provides insight into how scholars are using Twitter affordances like hashtags, but their value for altmetrics and scholarly communication requires more understanding.
HT2016: Influence of Frequency, Recency and Semantic Context on Tag ReuseDominik Kowald
This document discusses factors that influence tag reuse in social tagging systems. An empirical study showed that the probability of a tag being reused increases with its frequency of past use, recency of past use, and similarity to tags in the current context. A prediction study found that combining these factors into recommendation algorithms worked best at predicting tag reuse, and that the importance of recency decreased for broader folksonomy types while social influence became more important. Future work is proposed to further analyze social influence and semantic context.
Twitter has brought much attention recently as a hot research topic in the domain of sentiment analysis. Training sentiment classifiers from tweets data often faces the data sparsity problem partly due to the large variety of short and irregular forms introduced to tweets because of the 140-character limit. In this work we propose using two different sets of features to alleviate the data sparseness problem. One is the semantic feature set where we extract semantically hidden concepts from tweets and then incorporate them into classifier training through interpolation. Another is the sentiment-topic feature set where we extract latent topics and the associated topic sentiment from tweets, then augment the original feature space with these sentiment-topics. Experimental results on the Stanford Twitter Sentiment Dataset show that both feature sets outperform the baseline model using unigrams only. Moreover, using semantic features rivals the previously reported best result. Using sentiment-topic features achieves 86.3% sentiment classification accuracy, which outperforms existing approaches.
Durkheim Project: Social Media Risk & Bayesian CountersDataWorks Summit
Cited by a 2012 TIME Magazine cover story (“One A Day”) suicide, particularly the military, is a severe public health problem: Veteran suicide rates, nearly double those of adults in the general U.S. population. And to date there has been a lack of success so far in military efforts to understand and address the suicide crisis: “No program, outreach or initiative has worked against the surge in Army suicides, and no one knows why nothing works.” (Time) In this talk we will describe how we have built a real time risk assessment framework with the US Veterans Administration. As well as how Hadoop and HBase are being used to build further systems based on our new Bayesian Counters framework to predict realtime risk. Bayesian Counters framework was, in part, developed to predict military mental health risks. Trying to help to solve this complicated puzzle, towards the goal of reducing suicidality among those who have served the nation.
1. Current tag recommendation algorithms are designed in a purely data-driven way and rely on dense/broad folksonomy structures, but most real-world folksonomies are sparse/narrow.
2. The authors investigate how cognitive processes like frequency, recency, and semantic context influence tag reuse based on the ACT-R cognitive architecture.
3. They develop a tag recommendation algorithm based on the ACT-R activation equation and show it outperforms other methods in narrow/broad folksonomies by overcoming the imbalance between recommendations and real folksonomies.
PhD defense presentation of Dominik Kowald: Modeling Activation Processes in Human Memory to Improve Tag Recommendations. Presented at Know-Center / Graz University of Technology (Austria)
This document analyzes the Twitter usage of 37 astrophysicists. It finds that on average, 23% of their tweets contained hashtags. The top 10 hashtags were identified, with #fb being the most common. Regular Twitter users tended to include hashtags more than infrequent users. However, the astrophysicist community did not strongly share hashtags, as many were only used once, suggesting hashtags were not used to build communities. This analysis provides insight into how scholars are using Twitter affordances like hashtags, but their value for altmetrics and scholarly communication requires more understanding.
HT2016: Influence of Frequency, Recency and Semantic Context on Tag ReuseDominik Kowald
This document discusses factors that influence tag reuse in social tagging systems. An empirical study showed that the probability of a tag being reused increases with its frequency of past use, recency of past use, and similarity to tags in the current context. A prediction study found that combining these factors into recommendation algorithms worked best at predicting tag reuse, and that the importance of recency decreased for broader folksonomy types while social influence became more important. Future work is proposed to further analyze social influence and semantic context.
This study proposes methods to automatically extract and recommend popular and relevant URLs from Twitter to support serendipitous learning for software developers. The researchers collected tweets from seed Twitter users and extracted URLs, calculating 14 features for each. URLs were labeled for relevance and a supervised learning-to-rank model and unsupervised Borda count approach were used to recommend URLs. The supervised approach achieved better performance with an NDCG of 0.832. Future work includes automatically categorizing URLs and building a full recommendation system.
Recommending Tags with a Model of Human CategorizationChristoph Trattner
Social tagging involves complex processes of human categorization that have been the topic of much research in the cognitive sciences. In this paper we present a recommender approach for social tags whose principles are derived from some of the more prominent and empirically well-founded models from this research tradition. The basic architecture is a simple three-layers connectionist model. The input layer encodes patterns of semantic features of a user-specific re- source, which are either latent topics elicited through Latent Dirichlet Allocation (LDA) or available external categories. The hidden layer categorizes the resource by matching the encoded pattern against already learned exemplar patterns. The latter are composed of unique feature patterns and associated tag distributions. Finally, the output layer samples tags from the associated tag distributions to verbalize the preceding categorization process. We have evaluated this approach on a real-world folksonomy gathered from Wikipedia bookmarks in Delicious. In the experiment our approach outperformed LDA, a well-established algorithm. We at- tribute this to the fact that our approach processes seman- tic information (either latent topics or external categories) across the three different layers, and this substantially enhances the recommendation performance. With this paper, we demonstrate that a theoretically guided design of algorithms not only holds potential for improving existing recommendation mechanisms, but it also allows us to derive more generalizable insights about how human information interaction on the Web is determined by both semantic and verbal processes.
Slides from a practical workshop on gathering customer insights from social media using Social Network Analysis (SNA) with NodeXL and Twitter. SNA allows you to gain insight from thousands of tweets and messages on a range of topics for marketing research or academic use. NodeXL reports can be used for measuring and monitoring an organisation’s own performance as well as a competitors´ performance. At the highest level, a SNA approach allows social media managers to recognize what their audience looks like.
Towards identifying Collaborative Learning groups using Social MediaSelver Softic
This document discusses using social media data to identify collaborative learning groups. It outlines a methodology to cluster users based on interests inferred from hashtags and mentions in tweets. Cosine similarity and thresholds would evaluate similarity between user interest vectors. A prototype implementation clusters 100 users discussing e-learning using their last 250 tweets from a database of 1600 users and 4.7 million tweets. Evaluation shows potential but could be improved with additional clustering methods and qualitative analysis of formed groups regarding collaborative learning.
Wimmics Research Team 2015 Activity ReportFabien Gandon
Extract of the activity report of the Wimmics joint research team between Inria Sophia Antipolis - Méditerranée and I3S (CNRS and Université Nice Sophia Antipolis). Wimmics stands for web-instrumented man-machine interactions, communities and semantics. The team focuses on bridging social semantics and formal semantics on the web.
This document proposes creating an open dataset of 600 million anonymized Swedish tweets and establishing a collaborative research center to conduct interdisciplinary studies of digital media using computational analysis. It identifies challenges of accessing commercial social media data, requiring technical skills, and enabling collaboration. Example research areas discussed include mapping information diffusion, identifying topics in shared links, measuring social media's role in constructing identity, and analyzing writing styles. The proposal seeks long-term funding to host the dataset and support technical, ethical and administrative needs.
Survey on Common Strategies of Vocabulary Reuse in Linked Open Data Modeling ...JohannWanja
The choice of which vocabulary to reuse when modeling and publishing Linked Open Data (LOD) is far from trivial. There is no study that investigates the different strategies of reusing vocabularies for LOD modeling and publishing. In this paper, we present the results of a survey with 79 participants that examines the most preferred vocabulary reuse strategies of LOD modeling. The participants, LOD publishers and practitioners, were asked to assess different vocabulary reuse strategies and explain their ranking decision. We found significant differences between the modeling strategies that range from reusing popular vocabularies, minimizing the number of vocabularies, and staying within one domain vocabulary. A very interesting insight is that the popularity in the meaning of how frequent a vocabulary is used in a data source is more important than how often individual classes and properties are used in the LOD cloud. Overall, the results of this survey help in better understanding the strategies how data engineers reuse vocabularies and may also be used to develop future vocabulary engineering tools.
The document provides an overview of a case study analyzing big data from soccer events like the Champions League and World Cup to understand fan engagement. It discusses:
1) The goals of understanding fan communities and passions, and analyzing fan interactions to help brands engage fans.
2) The methodology used including collecting Twitter data around events, establishing keyword/hashtag seeds, and analyzing tweets to understand engagement logics.
3) The process of data collection including modifying scripts, watching events for patterns, deciding what to analyze, and preparing for future events.
4) Plans to match fan survey and ethnographic data with Twitter data to gain insights for brands around campaigns and measuring success.
ICIS Rating Scales for Collective IntelligenceIcis idea rating-v1.0-finalriedlc
The document presents research on rating scales for collective intelligence in innovation communities. It discusses how organizations face challenges in selecting the best ideas from large pools of information. The research aims to determine which rating mechanisms perform best for idea selection by examining the effects of rating scale granularity on rating accuracy and user satisfaction. An experiment compares a promote/demote scale, 5-star scale, and complex scale in their ability to correctly rate ideas. Results find the complex scale leads to higher rating accuracy and user satisfaction than simpler scales. The findings have implications for designing effective rating systems and extending theories of collective intelligence and creativity.
- The document discusses open science and various techniques used in the Data4Impact project such as text analysis, social media data collection from Twitter, and linked open data.
- It provides an overview of science norms and compares traditional CUDOS norms to more open PLACE norms.
- Data4Impact aims to build a knowledge graph linking different data sources to analyze the impact of research and innovation funding through new metrics and indicators. Machine learning and linked open data techniques are applied.
New Methodologies for Capturing and Working with Publicly Available Twitter DataAxel Bruns
This document proposes new methodologies for capturing and analyzing publicly available Twitter data. It discusses using tools like yourTwapperkeeper and Gawk to gather and process Twitter data at scale. Potential research questions are exploring how online publics form through hashtags and what structures emerge. Metrics for analyzing hashtags, timeframes, and users are presented. Challenges in working with big Twitter data at scale are also discussed.
WSDM 2018 Tutorial on Influence Maximization in Online Social NetworksCigdem Aslay
In this tutorial, we extensively survey the research on social influence propagation and maximization, with a focus on the recent algorithmic and theoretical advances. To this end, we provide detailed reviews of the latest research effort devoted to (i) improving the efficiency and scalability of the influence maximization algorithms; (ii) context-aware modeling of the influence maximization problem to better capture real-world marketing scenarios; (iii) modeling and learning of real-world social influence; (iv) bridging the gap between social advertising and viral marketing.
This document discusses cross-platform profiling as a method for studying issues across multiple online spaces. It provides examples of profiling controversies and issues like Fukushima, the economic crisis, hashtags on climate change, and the WCIT conference. Profiling involves analyzing actor composition, key platforms, framing, and variation over time. It demonstrates profiling using tools like the Google scraper and TCAT associational profiler to map word frequencies, co-occurrence networks, and changing associations for issues on Google, Twitter and other platforms. The document raises questions about how media liveliness relates to issue liveliness and how profiling can capture social dynamics and platform specificities.
Impact the UX of Your Website with Contextual InquiryRachel Vacek
A contextual inquiry is a research study that involves in-depth interviews where users walk through common tasks in the physical environment in which they typically perform them. It can be used to better understand the intents and motivations behind user behavior. In this session, learn what’s needed to conduct a contextual inquiry and how to analyze the ethnographic data once collected. We'll cover how to synthesize and visualize your findings as sequence models and affinity diagrams that directly inform the development of personas and common task flows. Finally, learn how this process can help guide your design and content strategy efforts while constructing a rich picture of the user experience.
Twitter analysis - Data as factor for designing the right communication star...Pere Claver Llimona
This document describes an interactive Twitter analysis application that analyzes tweets related to an organization. The application displays tweets in graphical panels that show word clouds, top words, topics, sentiment, and interactions. The goal is to monitor Twitter activity, understand trends, and help plan an effective communication strategy. The analysis can be refined by adjusting the number of days and tweets analyzed. Potential improvements include comparing campaigns, filtering time periods, and expanding to other social networks.
SIGIR 2016 presentation slide for paper: Xin Qian, Jimmy Lin, and Adam Roegiest. Interleaved Evaluation for Retrospective Summarization and Prospective Notification on Document Streams. Proceedings of the 39th Annual International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR 2016), pages 175-184, July 2016, Pisa, Italy.
The TagRec framework is an open-source toolkit for developing and evaluating tag-based recommender systems. It has been used in two large European research projects and 17 research papers. The framework includes datasets from social media sites, recommendation algorithms, evaluation metrics, and a modular architecture. Example applications demonstrated in the document include cognitive-inspired tag recommendations that apply the ACT-R memory model, and hashtag recommendations on Twitter integrating individual, social, and content-based signals.
This study evaluated the impact of semantic context cues on user acceptance of tag recommendations in collaborative versus individual tagging settings. It compared a context-unaware algorithm (MostPop) that recommends the most frequently used tags to a context-aware algorithm (3Layers) that incorporates categories. In an online study with university employees bookmarking resources, 3Layers had significantly higher user acceptance than MostPop in the collaborative setting, but there was no difference in the individual setting. This supports the hypothesis that semantic context cues have a greater impact on user acceptance in collaborative tagging scenarios.
More Related Content
Similar to Temporal Effects on Hashtag Reuse in Twitter
This study proposes methods to automatically extract and recommend popular and relevant URLs from Twitter to support serendipitous learning for software developers. The researchers collected tweets from seed Twitter users and extracted URLs, calculating 14 features for each. URLs were labeled for relevance and a supervised learning-to-rank model and unsupervised Borda count approach were used to recommend URLs. The supervised approach achieved better performance with an NDCG of 0.832. Future work includes automatically categorizing URLs and building a full recommendation system.
Recommending Tags with a Model of Human CategorizationChristoph Trattner
Social tagging involves complex processes of human categorization that have been the topic of much research in the cognitive sciences. In this paper we present a recommender approach for social tags whose principles are derived from some of the more prominent and empirically well-founded models from this research tradition. The basic architecture is a simple three-layers connectionist model. The input layer encodes patterns of semantic features of a user-specific re- source, which are either latent topics elicited through Latent Dirichlet Allocation (LDA) or available external categories. The hidden layer categorizes the resource by matching the encoded pattern against already learned exemplar patterns. The latter are composed of unique feature patterns and associated tag distributions. Finally, the output layer samples tags from the associated tag distributions to verbalize the preceding categorization process. We have evaluated this approach on a real-world folksonomy gathered from Wikipedia bookmarks in Delicious. In the experiment our approach outperformed LDA, a well-established algorithm. We at- tribute this to the fact that our approach processes seman- tic information (either latent topics or external categories) across the three different layers, and this substantially enhances the recommendation performance. With this paper, we demonstrate that a theoretically guided design of algorithms not only holds potential for improving existing recommendation mechanisms, but it also allows us to derive more generalizable insights about how human information interaction on the Web is determined by both semantic and verbal processes.
Slides from a practical workshop on gathering customer insights from social media using Social Network Analysis (SNA) with NodeXL and Twitter. SNA allows you to gain insight from thousands of tweets and messages on a range of topics for marketing research or academic use. NodeXL reports can be used for measuring and monitoring an organisation’s own performance as well as a competitors´ performance. At the highest level, a SNA approach allows social media managers to recognize what their audience looks like.
Towards identifying Collaborative Learning groups using Social MediaSelver Softic
This document discusses using social media data to identify collaborative learning groups. It outlines a methodology to cluster users based on interests inferred from hashtags and mentions in tweets. Cosine similarity and thresholds would evaluate similarity between user interest vectors. A prototype implementation clusters 100 users discussing e-learning using their last 250 tweets from a database of 1600 users and 4.7 million tweets. Evaluation shows potential but could be improved with additional clustering methods and qualitative analysis of formed groups regarding collaborative learning.
Wimmics Research Team 2015 Activity ReportFabien Gandon
Extract of the activity report of the Wimmics joint research team between Inria Sophia Antipolis - Méditerranée and I3S (CNRS and Université Nice Sophia Antipolis). Wimmics stands for web-instrumented man-machine interactions, communities and semantics. The team focuses on bridging social semantics and formal semantics on the web.
This document proposes creating an open dataset of 600 million anonymized Swedish tweets and establishing a collaborative research center to conduct interdisciplinary studies of digital media using computational analysis. It identifies challenges of accessing commercial social media data, requiring technical skills, and enabling collaboration. Example research areas discussed include mapping information diffusion, identifying topics in shared links, measuring social media's role in constructing identity, and analyzing writing styles. The proposal seeks long-term funding to host the dataset and support technical, ethical and administrative needs.
Survey on Common Strategies of Vocabulary Reuse in Linked Open Data Modeling ...JohannWanja
The choice of which vocabulary to reuse when modeling and publishing Linked Open Data (LOD) is far from trivial. There is no study that investigates the different strategies of reusing vocabularies for LOD modeling and publishing. In this paper, we present the results of a survey with 79 participants that examines the most preferred vocabulary reuse strategies of LOD modeling. The participants, LOD publishers and practitioners, were asked to assess different vocabulary reuse strategies and explain their ranking decision. We found significant differences between the modeling strategies that range from reusing popular vocabularies, minimizing the number of vocabularies, and staying within one domain vocabulary. A very interesting insight is that the popularity in the meaning of how frequent a vocabulary is used in a data source is more important than how often individual classes and properties are used in the LOD cloud. Overall, the results of this survey help in better understanding the strategies how data engineers reuse vocabularies and may also be used to develop future vocabulary engineering tools.
The document provides an overview of a case study analyzing big data from soccer events like the Champions League and World Cup to understand fan engagement. It discusses:
1) The goals of understanding fan communities and passions, and analyzing fan interactions to help brands engage fans.
2) The methodology used including collecting Twitter data around events, establishing keyword/hashtag seeds, and analyzing tweets to understand engagement logics.
3) The process of data collection including modifying scripts, watching events for patterns, deciding what to analyze, and preparing for future events.
4) Plans to match fan survey and ethnographic data with Twitter data to gain insights for brands around campaigns and measuring success.
ICIS Rating Scales for Collective IntelligenceIcis idea rating-v1.0-finalriedlc
The document presents research on rating scales for collective intelligence in innovation communities. It discusses how organizations face challenges in selecting the best ideas from large pools of information. The research aims to determine which rating mechanisms perform best for idea selection by examining the effects of rating scale granularity on rating accuracy and user satisfaction. An experiment compares a promote/demote scale, 5-star scale, and complex scale in their ability to correctly rate ideas. Results find the complex scale leads to higher rating accuracy and user satisfaction than simpler scales. The findings have implications for designing effective rating systems and extending theories of collective intelligence and creativity.
- The document discusses open science and various techniques used in the Data4Impact project such as text analysis, social media data collection from Twitter, and linked open data.
- It provides an overview of science norms and compares traditional CUDOS norms to more open PLACE norms.
- Data4Impact aims to build a knowledge graph linking different data sources to analyze the impact of research and innovation funding through new metrics and indicators. Machine learning and linked open data techniques are applied.
New Methodologies for Capturing and Working with Publicly Available Twitter DataAxel Bruns
This document proposes new methodologies for capturing and analyzing publicly available Twitter data. It discusses using tools like yourTwapperkeeper and Gawk to gather and process Twitter data at scale. Potential research questions are exploring how online publics form through hashtags and what structures emerge. Metrics for analyzing hashtags, timeframes, and users are presented. Challenges in working with big Twitter data at scale are also discussed.
WSDM 2018 Tutorial on Influence Maximization in Online Social NetworksCigdem Aslay
In this tutorial, we extensively survey the research on social influence propagation and maximization, with a focus on the recent algorithmic and theoretical advances. To this end, we provide detailed reviews of the latest research effort devoted to (i) improving the efficiency and scalability of the influence maximization algorithms; (ii) context-aware modeling of the influence maximization problem to better capture real-world marketing scenarios; (iii) modeling and learning of real-world social influence; (iv) bridging the gap between social advertising and viral marketing.
This document discusses cross-platform profiling as a method for studying issues across multiple online spaces. It provides examples of profiling controversies and issues like Fukushima, the economic crisis, hashtags on climate change, and the WCIT conference. Profiling involves analyzing actor composition, key platforms, framing, and variation over time. It demonstrates profiling using tools like the Google scraper and TCAT associational profiler to map word frequencies, co-occurrence networks, and changing associations for issues on Google, Twitter and other platforms. The document raises questions about how media liveliness relates to issue liveliness and how profiling can capture social dynamics and platform specificities.
Impact the UX of Your Website with Contextual InquiryRachel Vacek
A contextual inquiry is a research study that involves in-depth interviews where users walk through common tasks in the physical environment in which they typically perform them. It can be used to better understand the intents and motivations behind user behavior. In this session, learn what’s needed to conduct a contextual inquiry and how to analyze the ethnographic data once collected. We'll cover how to synthesize and visualize your findings as sequence models and affinity diagrams that directly inform the development of personas and common task flows. Finally, learn how this process can help guide your design and content strategy efforts while constructing a rich picture of the user experience.
Twitter analysis - Data as factor for designing the right communication star...Pere Claver Llimona
This document describes an interactive Twitter analysis application that analyzes tweets related to an organization. The application displays tweets in graphical panels that show word clouds, top words, topics, sentiment, and interactions. The goal is to monitor Twitter activity, understand trends, and help plan an effective communication strategy. The analysis can be refined by adjusting the number of days and tweets analyzed. Potential improvements include comparing campaigns, filtering time periods, and expanding to other social networks.
SIGIR 2016 presentation slide for paper: Xin Qian, Jimmy Lin, and Adam Roegiest. Interleaved Evaluation for Retrospective Summarization and Prospective Notification on Document Streams. Proceedings of the 39th Annual International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR 2016), pages 175-184, July 2016, Pisa, Italy.
Similar to Temporal Effects on Hashtag Reuse in Twitter (20)
The TagRec framework is an open-source toolkit for developing and evaluating tag-based recommender systems. It has been used in two large European research projects and 17 research papers. The framework includes datasets from social media sites, recommendation algorithms, evaluation metrics, and a modular architecture. Example applications demonstrated in the document include cognitive-inspired tag recommendations that apply the ACT-R memory model, and hashtag recommendations on Twitter integrating individual, social, and content-based signals.
This study evaluated the impact of semantic context cues on user acceptance of tag recommendations in collaborative versus individual tagging settings. It compared a context-unaware algorithm (MostPop) that recommends the most frequently used tags to a context-aware algorithm (3Layers) that incorporates categories. In an online study with university employees bookmarking resources, 3Layers had significantly higher user acceptance than MostPop in the collaborative setting, but there was no difference in the individual setting. This supports the hypothesis that semantic context cues have a greater impact on user acceptance in collaborative tagging scenarios.
AFEL-REC: A Recommender System for Providing Learning Resource Recommendation...Dominik Kowald
In this paper, we present preliminary results of AFEL-REC, a recommender system for social learning environments. AFEL-REC is build upon a scalable software architecture to provide recommendations of learning resources in near real-time. Furthermore, AFEL-REC can cope with any kind of data that is present in social learning environments such as resource metadata, user interactions or social tags. We provide a preliminary evaluation of three recommendation use cases implemented in AFEL-REC and we find that utilizing social data in form of tags is helpful for not only improving recommendation accuracy but also coverage. This paper should be valuable for both researchers and practitioners interested in providing resource recommendations in social learning environments.
The Social Semantic Server Tool Support in Learning LayersDominik Kowald
Slides presented by Tobias Ley at the 3rd Learning Layers reviews meeting about how the Social Semantic Server (SSS) support the Layers tools in the Healthcare and Construction areas.
WWW'15: A Hybrid Resource Recommender Mimicking Attention-Interpretation Dyna...Dominik Kowald
This document summarizes a hybrid recommender system that combines user-based collaborative filtering with a computational model of human category learning called SUSTAIN. The approach trains a SUSTAIN network for each user based on their activities, then applies the network to rank candidate recommendations generated through collaborative filtering. Evaluation on three datasets found it improves over collaborative filtering alone by leveraging the SUSTAIN model of how users' attentional focus shapes interpretation and decision making during recommendation. The open-source TagRec framework implements the approach and baselines to further personalized and accurate resource recommendation.
WWW2014: Long Time No See: The Probability of Reusing Tags as a Function of F...Dominik Kowald
WWW2014 - WebScience Track
Long Time No See: The Probability of Reusing Tags as a Function of Frequency and Recency
Dominik Kowald, Paul Seitlinger, Christoph Trattner, Tobias Ley
The Influence of Green Tax Implementation and Social Responsibility Programs ...AJHSSR Journal
ABSTRACT : The issue of climate change related to carbon emissions has become an alarming global
phenomenon. The manufacturing sector contributes significantly to global greenhouse gas emissions. Therefore,
efforts to mitigate climate change through the implementation of green taxes and Social Responsibility
Programsare important for manufacturing industry. This research aims to analyze the effect of implementing
green tax and Social Responsibility Programs on environmentally sustainable development in manufacturing
industry. A quantitative approach is used with the research object of manufacturing industry listed on the
Indonesia Stock Exchange in 2020-2022. Analyzed using Partial Least Square (PLS) method. The research
results show that the implementation of green tax has a significant effect on environmentally sustainable
development, while Social Responsibility Programsdo not have a significant effect. These findings indicate that
green tax policies are effective in encouraging companies to switch to more environmentally friendly business
practices, but Social Responsibility Programshave not been fully integrated with environmental sustainability
efforts. This research contributes to the literature related to fiscal policy instruments and corporate social
responsibility practices in supporting environmentally sound sustainable development in the manufacturing
sector.
KEYWORDS: Green tax; Social responsibility; Environmentally sustainable development; Manufacturing
industry
Creating Immersive Language Learning Environments for Young LearnersAJHSSR Journal
ABSTRACT: Creating immersive language learning environments for young learners in English as a Foreign
Language (EFL) contexts has been a topic of considerable interest and debate among educators. Despite
numerous constraints such as time, curriculum, and stakeholder expectations, it is feasible to develop effective
immersive environments. This paper explores the concept of immersion language learning, tracing its historical
development and highlighting its benefits, particularly for young learners. It discusses the distinctions between
total, partial, and dual-immersion programs, emphasizing the critical role of using the target language as the
medium of instruction. Furthermore, it examines the cognitive and academic advantages documented in seminal
immersion programs like Saint-Lambert and Coral Way. By synthesizing research and offering practical
strategies for EFL settings, this paper underscores the importance of teacher commitment, the selection of
appropriate materials, and the adoption of Content and Language Integrated Learning (CLIL) principles.
Ultimately, the findings affirm that immersive environments significantly enhance language proficiency,
cognitive flexibility, and academic achievement, advocating for their broader implementation in EFL
classrooms.
KEYWORDS : CLIL, EFL, immersion, young learners
TACKLING ILLEGAL LOGGING: PROBLEMS AND CHALLENGESAJHSSR Journal
ABSTRACT: Illegal logging poses significant environmental, economic, and social challenges worldwide. This
research explores the problems associated with illegal logging in the present and future, shedding light on the
multifaceted nature of this issue and the accompanying challenges faced by governments, organizations, and
communities. The study employs a comprehensive literature review to analyze the current state of illegal
logging, its causes, and its consequences. It examines the environmental impact of deforestation, including
biodiversity loss, habitat degradation, and climate change. The researchers identify the challenges faced in
combating illegal logging in the present and anticipate future obstacles. It considers illegal logging networks'
complex and elusive nature, the limited enforcement capacity, and the need for international cooperation and
coordination. The study also examines the adoption and effectiveness of policies, regulations, and technological
advancements in curbing illegal logging practices in Davao City.
Keywords -Problems and Challenges, Cultural Disruptions, Anticipate future problems.
KALYAN MATKA | MATKA RESULT | KALYAN MATKA TIPS | SATTA MATKA | MATKA.COM | MATKA PANA JODI TODAY | BATTA SATKA | MATKA PATTI JODI NUMBER | MATKA RESULTS | MATKA CHART | MATKA JODI | SATTA COM | FULL RATE GAME | MATKA GAME | MATKA WAPKA | ALL MATKA RESULT LIVE ONLINE | MATKA RESULT | KALYAN MATKA RESULT | DPBOSS MATKA 143 | MAIN MATKA-❾❸❹❽❺❾❼❾❾⓿
Using Playlists to Increase YouTube Watch TimeSocioCosmos
Discover how to use playlists to keep viewers engaged and increase your watch time.
https://www.sociocosmos.com/product-category/youtube/youtube-comments/
CYBER SECURITY ENHANCEMENT IN NIGERIA. A CASE STUDY OF SIX STATES IN THE NORT...AJHSSR Journal
ABSTRACT: Security plays an important role in human life and endeavors. Securing information and
disseminating are critical challenges in the present day. This study aimed at identifying innovative technologies
that aid cybercrimes and can constitute threats to cybersecurity in North Central (Middle Belt) Nigeria covering
its six States and the FCT Abuja. A survey research design was adopted. The researchers employed the use of
Google form in administering the structured questionnaire. The instruments were faced validated by one expert
each from ICT and security. Cronbach Alpha reliability Coefficient was employed and achieved 0.83 level of
coefficient. The population of the study was 200, comprising 100 undergraduate students from computer science
and Computer/Robotics Education, 80 ICT instructors, technologists and lecturers in the University and
Technical Colleges in the Middle Belt Nigeria using innovative technologies for their daily jobs and 20 officers
of the crime agency such as: Independent Corrupt Practices Commission (ICPC) andEconomic and Financial
Crimes Commission (EFCC). Three research purposes and questions as well as the hypothesis guided the study
on Five (5) point Likert scale. Data collected were analyzed using mean and standard deviation for the three
research questions while three hypotheses were tested using t-test at 0.05 level of significance. Major findings
revealed that serious steps are needed to better secure the cybers against cybercrimes. Motivation, types, threats
and strategies for the prevention of cybercrimes were identified. The study recommends that government,
organizations and individuals should place emphasis on moral development, regular training of its employees,
regular update of software, use strong password, back up data and information, produce strong cybersecurity
policy, install antivirus soft and security surveillance (CCTV) in offices in order to safeguard its employees and
properties from being hacked and vandalized.
KEYWORDS: Cybersecurity, cybercrime, cyberattack, cybercriminal, computer virus, Virtual Private Networks
(VPN).
On Storytelling & Magic Realism in Rushdie’s Midnight’s Children, Shame, and ...AJHSSR Journal
ABSTRACT: Salman Rushdie’s novels are humorous books about serious times. His cosmopolitanism and
hybrid identity allowed him access to multiple cultures, religions, languages, dialects, and various modes of
writing. His style is often classified as magic realism, blending the imaginary with the real. He draws
inspiration from both English literature and Indian classical sources. Throughout his works, there is a lineage of
‘bastards of history’, a carnival of shameful characters scrolling all along his works. Rushdie intertwines fiction
with reality, incorporating intertextual references to Western literature in his texts, and frequently employing
mythology to explore history. This paper focuses on Rushdie’s three novels: Midnight’s Children, Shame, and
Haroun and the Sea of Stories, analyzing his postmodern storytelling techniques that aim to explore human
vices and follies while offering socio-political criticism.
KEYWORDS : Magic Realism, Rushdie, Satire, Storytelling, Transfictional Identities
9861615390 Satta Matka | Satta Matka Results | Kalyan Matka Tips | Free Matka Results | SattaMatka | Satta Matka Tips | Satta Matka Guessing | Satta Matka Number | Satta Matka 143 | Online All Satta Matka Result | Satta Matka Guessing | Satta Matka Chart | Satta Matka King | Satta Matka Trick | Satta Matka Tips | Satta Matka Number | Satta Matka Software | Matka Chart | Matka Result | Satta Matka Guessing | Kalyan Matka | Kalyan Matka Tips | Matka Result | Satta Matka Result | Satta Matka Tips | Satta Matka | Matka Tips | Satta King | Satta Game | Satta Result | Matka Result | Satta Matka Result | Satta Matka | Kalyan Matka | Kalyan Matka Tips | Matka Result | Satta Matka Result | Satta Matka Tips | Satta Matka | Matka Tips | Satta King | Satta Game | Satta Result | Matka Result | Satta Matka Result | Satta Matka | Kalyan Matka | Kalyan Matka Tips | Matka Result | Satta Matka Result | Satta Matka Tips | Satta Matka | Matka Tips | Satta King | Satta Game | Satta Result | Matka Result | Satta Matka Result | Satta Matka | Kalyan Matka | Kalyan Matka Tips | Matka Result | Satta Matka Result | Satta Matka Tips | Satta Matka | Matka Tips | Satta King | Satta Game | Satta Result | Matka Result | Satta Matka Result | Satta Matka | Kalyan Matka | Kalyan Matka Tips | Matka Result | Satta Matka Result | Satta Matka Tips | Satta Matka | Matka Tips | Satta King | Satta Game | Satta Result | Matka Result | Satta Matka Result | Satta Matka | Kalyan Matka | Kalyan Matka Tips | Matka Result | Satta Matka Result | Satta Matka Tips | Satta Matka | Matka Tips | Satta King | Satta Game | Satta Result | Matka Result | Satta Matka Result | Satta Matka | Kalyan Matka | Kalyan Matka Tips | Matka Result | Satta Matka Result | Satta Matka Tips | Satta Matka | Matka Tips | Satta King | Satta Game | Satta Result | Matka Result | Satta Matka Result | Satta Matka | Kalyan Matka | Kalyan Matka Tips | Matka Result | Satta Matka Result | Satta Matka Tips | Satta Matka | Matka Tips | Satta King | Satta Game | Satta Result | Matka Result | Satta Matka Result | Satta Matka | Kalyan Matka | Kalyan Matka Tips | Matka Result | Satta Matka Result | Satta Matka Tips | Satta Matka | Matka Tips | Satta King | Satta Game | Satta Result | Matka Result | Satta Matka Result | Satta Matka | Kalyan Matka | Kalyan Matka Tips | Matka Result | Satta Matka Result | Satta Matka Tips | Satta Matka | Matka Tips | Satta King | Satta Game | Satta Result | Matka Result | Satta Matka Result | Satta Matka | Kalyan Matka | Kalyan Matka Tips | Matka Result | Satta Matka Result | Satta Matka Tips | Satta Matka | Matka Tips | Satta King | Satta Game | Satta Result | Matka Result | Satta Matka Result | Satta Matka | Kalyan Matka | Kalyan Matka Tips | Matka Result | Satta Matka Result | Satta Matka Tips | Satta Matka | Matka Tips | Satta King | Satta Game | Satta Result | Matka Result | Satta Matka Result | Satta Matka | Kalyan Matka | Kalyan Matka Tips | Matka Result | Satta Matka Result | Satta Matka Tips
Facebook Fan Page Profits to boost your profits today!Rohit Gupta
Discover how to turn your Facebook Fan Page into a powerful tool for generating profits! Whether you're an entrepreneur, marketer, or small business owner, learn proven strategies to engage your audience, increase followers, and monetize your fan page effectively. From content creation and engagement tactics to advertising and conversion optimization, unlock the secrets to maximizing your business's success on Facebook. Start leveraging your fan page to boost your profits today!
Welcome to our captivating YouTube channel, where the past comes alive with intriguing history, fascinating fun facts, and inspiring motivational content. Join us on a journey through time as we unravel the mysteries of the past, share delightful nuggets of knowledge, and ignite the spark of motivation within you. Get ready to explore the depths of history, uncover hidden gems of information, and embark on a quest for personal growth and inspiration. Subscribe now for a blend of education, entertainment, and empowerment that will leave you enlightened and uplifted after every video.
1. 1
S C I E N C E n P A S S I O N n T E C H N O L O G Y
u www.tugraz.at u www.know-center.at
Temporal Effects on Hashtag
Reuse in Twitter:
A Cognitive-Inspired Hashtag
Recommendation Approach
Dominik Kowald, Subhash Pujari & Elisabeth Lex
Know-Center & Graz University of Technology (Austria)
WWW’17, Perth, Australia
April, 7th, 2017
2. 22
Motivation
• Microblogging platform Twitter
• Post messages (tweets) with max 140 characters
• Subscribe to tweets of other users (followees)
• Other users subscribe to your tweets (followers)
• Contextualize tweets with freely-chosen keywords
(hashtags)
• Hashtags can be searched to receive content of a
specific topic or event (e.g., #recsys)
Temporal Effects on Hashtag Reuse in Twitter: A Cognitive-Inspired Hashtag Recommendation Approach
Dominik Kowald, Know-Center & Graz University of Technology
3. 33
Motivation (II)
Temporal Effects on Hashtag Reuse in Twitter: A Cognitive-Inspired Hashtag Recommendation Approach
Dominik Kowald, Know-Center & Graz University of Technology
4. 44
Hashtag Recommendations in Twitter
• Scenario 1: Hashtag rec. w/o current tweet
• For a given user u, predict the set of hashtags u
will use next
• Foresee the topics a user will tweet about
• Scenario 2: Hashtag rec. w/ current tweet
• For a given user u and tweet t, predict the set of
hashtags u will use to annotate t
• Support a user in finding descriptive hashtags
• We propose an approach for both scenarios
Temporal Effects on Hashtag Reuse in Twitter: A Cognitive-Inspired Hashtag Recommendation Approach
Dominik Kowald, Know-Center & Graz University of Technology
5. 55
Our Previous Work: Tag Recommendations
based on a Model of Human Memory
• Support users in social bookmarking systems with
tag recommendations [Kowald et al., 2014)
• Base-Level Learning (BLL) equation of the
cognitive architecture ACT-R [Anderson et al., 2004]
• Quantifies the usefulness of information (e.g., a
word or tag) in human memory
• Can we also use it for hashtag recommendations?
Temporal Effects on Hashtag Reuse in Twitter: A Cognitive-Inspired Hashtag Recommendation Approach
Dominik Kowald, Know-Center & Graz University of Technology
6. 66
Datasets
• 2 datasets: CompSci and Random
• Crawling strategy
• (i) Crawl seed users [Hadgu & Jäschke, 2014]
• (ii) Crawl followees
• (iii) Crawl tweets
• (iv) Extract hashtag assignments
Temporal Effects on Hashtag Reuse in Twitter: A Cognitive-Inspired Hashtag Recommendation Approach
Dominik Kowald, Know-Center & Graz University of Technology
7. 77
Hashtag Reuse Types
• How are people reusing hashtags in Twitter?
• 66% and 81% of hashtag assignments can be
explained by individual or social hashtag reuse
Temporal Effects on Hashtag Reuse in Twitter: A Cognitive-Inspired Hashtag Recommendation Approach
Dominik Kowald, Know-Center & Graz University of Technology
8. 88
Temporal Effects on Hashtag Reuse
• Do temporal effects have an influence on
individual and social hashtag reuse?
• People tend to reuse hashtags that were used very
recently by their own or by their followees
Temporal Effects on Hashtag Reuse in Twitter: A Cognitive-Inspired Hashtag Recommendation Approach
Dominik Kowald, Know-Center & Graz University of Technology
9. 99
Temporal Effects on Hashtag Reuse (II)
• Is a power or an exponential function better suited
to model this time-dependent decay?
• Log-likelihood ratio test [Clauset et al., 2009]
• The time-dependent decay of hashtag reuse follows
a power-law distribution à BLL equation (d à α)
Temporal Effects on Hashtag Reuse in Twitter: A Cognitive-Inspired Hashtag Recommendation Approach
Dominik Kowald, Know-Center & Graz University of Technology
10. 1010
A Hashtag Recommendation Approach using
the BLL Equation
Temporal Effects on Hashtag Reuse in Twitter: A Cognitive-Inspired Hashtag Recommendation Approach
Dominik Kowald, Know-Center & Graz University of Technology
11. 1111
Evaluation
• Evaluation protocol
• For each seed user, put most recent tweet into
test set à the rest is used for training
• Evaluation metrics
• Precision, Recall, F1-score, MRR, MAP, nDCG
• Baseline algorithms
• MostPopular (MP), MostRecent (MR), FolkRank
(FR), Collaborative Filtering (CF), SimRank (SR),
TemporalCombInt (TCI) [Harvey & Crestani, 2015]
• TagRec open-source framework:
https://github.com/learning-layers/TagRec
Temporal Effects on Hashtag Reuse in Twitter: A Cognitive-Inspired Hashtag Recommendation Approach
Dominik Kowald, Know-Center & Graz University of Technology
12. 1212
Results (Scenario 1)
• Can we predict the hashtags of a given user using
the BLL equation?
• BLLI > MPI, MRI
• BLLS > MPS, MRS
• BLLI,S > MP, FR, CF
Temporal Effects on Hashtag Reuse in Twitter: A Cognitive-Inspired Hashtag Recommendation Approach
Dominik Kowald, Know-Center & Graz University of Technology
13. 1313
Results (Scenario 2)
• Can we predict the hashtags of a given user and a
given tweet using the BLL equation?
• TCI, BLLI,S,C > SR
• BLLI,S,C > TCI
• Random dataset > CompSci dataset
• More external hashtags in CompSci dataset
Temporal Effects on Hashtag Reuse in Twitter: A Cognitive-Inspired Hashtag Recommendation Approach
Dominik Kowald, Know-Center & Graz University of Technology
14. 1414
Conclusion
• Temporal effects have an important influence on
individual and social hashtag reuse
• A Power function is better suited to model this time-
dependent decay than an exponential one
• The BLL equation provides a suitable model for
personalized hashtag recommendations
• Without (BLLI,S) and with the current tweet (BLLI,S,C)
• Future Work
• Incorporate social connections (e.g., edge weight)
• Use additional knowledge source to cope with
external hashtags (e.g., trending hashtags)
Temporal Effects on Hashtag Reuse in Twitter: A Cognitive-Inspired Hashtag Recommendation Approach
Dominik Kowald, Know-Center & Graz University of Technology
15. 1515
Thank you for your attention!
Do you have questions?
Dominik Kowald
• Mail: dkowald [AT] know-center.at
• Web: www.dominikkowald.info
Subhash Chandra Pujari
• Mail: subhash.pujari [AT] gmail.com
Elisabeth Lex
• Mail: elisabeth.lex [AT] tugraz.at
• Web: www.elisabethlex.info
Temporal Effects on Hashtag Reuse in Twitter: A Cognitive-Inspired Hashtag Recommendation Approach
Dominik Kowald, Know-Center & Graz University of Technology
16. 1616
References
• [Anderson et al., 2004] J. R. Anderson, D. Bothell, M. D. Byrne, S.
Douglass, C. Lebiere, and Y. Qin. An integrated theory of the mind.
Psychological review, 111(4):1036, 2004.
• [Clauset et al., 2009] A. Clauset, C. R. Shalizi, and M. E. Newman. Power-
law distributions in empirical data. SIAM review (SIREV), 51(4):661-703,
2009.
• [Hadgu & Jäschke, 2014] A. T. Hadgu and R. Jäschke. Identifying and
analyzing researchers on twitter. In Proc. of WebSci '14, pages 23-30, New
York, NY, USA, 2014.
• [Harvey & Crestani, 2015] M. Harvey and F. Crestani. Long time, no tweets!
Time-aware personalised hashtag suggestion. In Proc. Of ECIR'15, pages
581-592. Springer, 2015.
• [Kowald et al., 2014] D. Kowald, P. Seitlinger, C. Trattner, and T. Ley. Long
time no see: The probability of reusing tags as a function of frequency and
recency. In Proc. of WWW '14 companion, pages 463-468. ACM, 2014.
Temporal Effects on Hashtag Reuse in Twitter: A Cognitive-Inspired Hashtag Recommendation Approach
Dominik Kowald, Know-Center & Graz University of Technology
17. 1717
Appendix: Formalization of Hashtag
Recommendations using the BLL Equation
Modeling hashtag reuse:
Combining individual and social hashtag reuse (BLLI,S):
Combining BLLi,s with TF-IDF (BLLI,S,C):
Temporal Effects on Hashtag Reuse in Twitter: A Cognitive-Inspired Hashtag Recommendation Approach
Dominik Kowald, Know-Center & Graz University of Technology
18. 1818
Appendix: Results (Precision / Recall Plots)
Temporal Effects on Hashtag Reuse in Twitter: A Cognitive-Inspired Hashtag Recommendation Approach
Dominik Kowald, Know-Center & Graz University of Technology