Recent research shows that Collaborative Information Retrieval (CIR), in which two or more users collaborate on the same search task, has become increasingly popular. The presence of both search and collaboration behaviors makes CIR a complex search format, which further drives a critical need to understand CIR's search context. The contextual support for CIR should consider search contexts derived from both team members' search histories (including users' own search histories and partners' search histories) and their explicit collaboration (e.g., chatting). As it stands, existing studies on contextual search support only focus on Individual Information Retrieval (IIR) and only utilize individuals' own search histories. In this paper, we examine the unique search contexts (e.g., partners' search histories and team collaboration histories) in CIR. Based on a user study data collection with 54 participants, we find that compared to the use of individuals' own search histories, CIR contextual support is more effective when utilizing partners' search histories and teams' collaboration behaviors. More interestingly, though the explicit communication information (i.e., chat content) often involves massive noisy information, involving such noise does not affect the ranking of relevant documents since it also does not appear in relevant documents.
Multimodal Learning Analytics for Collaborative Learning Understanding and Su...Sambit Praharaj
This project has multiple focus points: using the help of Multimodal Learning Analytics to understand how co-located collaboration takes place, what are the indicators of collaboration (such as pointing at peer, looking at peer, making
constructive interruptions, etc.); then we try to form a Collaboration Framework (CF)
which defines the aspects of successful collaboration and forms a model. These
insights help us to build the support framework to enable efficient real-time feedback
during a group activity to facilitate collaboration.
This was part of the Doctoral Consortium presentation in the ICMI Conference 2019 at Suzhou, China on 14th October, 2019. Collaboration is an important skill of the 21st century. It can take place in an online (or remote) setting or in a colocated
(or face-to-face) setting. With the large scale adoption
of sensor use, studies on co-located collaboration (CC) has
gained momentum. CC takes place in physical spaces where
the group members share each other’s social and epistemic
space. This involves subtle multimodal interactions such
as gaze, gestures, speech, discourse which are complex in
nature. The aim of this PhD is to detect these interactions
and then use these insights to build an automated real-time
feedback system to facilitate co-located collaboration
協作資訊尋求系統 Collaborative Information Seeking SystemsJames Chuang
本投影片為協作資訊尋求系統(Collaborative Information Seeking Systems)之文獻回顧。目的在於檢視近十年協作資訊尋求系統之相關研究,梳理系統的研究方向與發展,了解目前系統的設計概念與運作方式。協作資訊尋求系統的研究主要分為兩個方向發展:系統中介(System-mediated)或演算法中介(Algorithmically-mediated),以系統背後的演算法支持協作;以及使用者中介(User-mediated)或介面中介(Interface-mediated),透過介面設計支持使用者協作。此外,本報告亦討論協作資訊系統需要注重的因素,以及發展上的議題,最後統整對於未來發展方向上的建議。
Multimodal Learning Analytics for Collaborative Learning Understanding and Su...Sambit Praharaj
This project has multiple focus points: using the help of Multimodal Learning Analytics to understand how co-located collaboration takes place, what are the indicators of collaboration (such as pointing at peer, looking at peer, making
constructive interruptions, etc.); then we try to form a Collaboration Framework (CF)
which defines the aspects of successful collaboration and forms a model. These
insights help us to build the support framework to enable efficient real-time feedback
during a group activity to facilitate collaboration.
This was part of the Doctoral Consortium presentation in the ICMI Conference 2019 at Suzhou, China on 14th October, 2019. Collaboration is an important skill of the 21st century. It can take place in an online (or remote) setting or in a colocated
(or face-to-face) setting. With the large scale adoption
of sensor use, studies on co-located collaboration (CC) has
gained momentum. CC takes place in physical spaces where
the group members share each other’s social and epistemic
space. This involves subtle multimodal interactions such
as gaze, gestures, speech, discourse which are complex in
nature. The aim of this PhD is to detect these interactions
and then use these insights to build an automated real-time
feedback system to facilitate co-located collaboration
協作資訊尋求系統 Collaborative Information Seeking SystemsJames Chuang
本投影片為協作資訊尋求系統(Collaborative Information Seeking Systems)之文獻回顧。目的在於檢視近十年協作資訊尋求系統之相關研究,梳理系統的研究方向與發展,了解目前系統的設計概念與運作方式。協作資訊尋求系統的研究主要分為兩個方向發展:系統中介(System-mediated)或演算法中介(Algorithmically-mediated),以系統背後的演算法支持協作;以及使用者中介(User-mediated)或介面中介(Interface-mediated),透過介面設計支持使用者協作。此外,本報告亦討論協作資訊系統需要注重的因素,以及發展上的議題,最後統整對於未來發展方向上的建議。
Multimodal Analytics for Real-time Feedback in Co-located Collaboration, EC-T...Sambit Praharaj
This presentation was part of the EC-TEL conference in Leeds, UK. The full research paper is published in the Springer LNCS proceedings and can be found here:
https://link.springer.com/chapter/10.1007/978-3-319-98572-5_15
An Advanced IR System of Relational Keyword Search Techniquepaperpublications3
Abstract: Now these days keyword search to relational data set becomes an area of research within the data base and Information Retrieval. There is no standard process of information retrieval, which will clearly show the accurate result also it shows keyword search with ranking. Execution time is retrieving of data is more in existing system. We propose a system for increasing performance of relational keyword search systems. In the proposed system we combine schema-based and graph-based approaches and propose a Relational Keyword Search System to overcome the mentioned disadvantages of existing systems and manage the information and user access the information very efficiently. Keyword Search with the ranking requires very low execution time. Execution time of retrieving information and file length during Information retrieval can be display using chart.Keywords: Keyword Search, Datasets, Information Retrieval Query Workloads, Schema-based Systems, Graph-based Systems, ranking, relational databases.
Title: An Advanced IR System of Relational Keyword Search Technique
Author: Dhananjay A. Gholap, Gumaste S. V
ISSN 2350-1022
International Journal of Recent Research in Mathematics Computer Science and Information Technology
Paper Publications
Educational Technology Research Trends: Examining Six SSCI-indexed Refereed ...Yu-Chang Hsu
This study applied text mining methods to examine the abstracts of 2,997 international research articles published between 2000 and 2010 by six journals included in the Social Science Citation Index (SSCI) in the field of Educational Technology (EDTECH). A total of 19 clusters of research areas were identified, and these clusters were further analyzed in terms of productivity by country and by journal. The analysis revealed research areas with rising trends, stable status, and low attention. This study also identified areas of research emphasis by journal and research strength by country. A discussion of results through the lens of Critical Theory of Technology is also included. The authors hope to inform the EDTECH community about the trends of EDTECH research on topics and regions of research contributions. The authors also believe that such examination of trends can help facilitate fruitful discussions of directions for future research, and possible international collaboration across various geographical regions.
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)
SEMANTIC ANALYSIS OVER LESSONS LEARNED CONTAINED IN SOCIAL NETWORKS FOR GENER...cscpconf
This paper shows the construction of an organizational memory metamodel focused on R&D centers. The metamodel uses lessons learned extracted from corporative social networks; the metamodel aims to promote learning and management of organizational knowledge at these types of organizations. The analysis is applied initially from lessons learned on topics of R&D in the Spanish language. The metamodel use natural languages processing together with ontologies
for analyze the semantic and lexical the each lesson learned. The final result involves a knowledge base integrated by RDF files interrogated by SPARQL queries.
Semantic Analysis Over Lessons Learned Contained in Social Networks for Gener...csandit
This paper shows the construction of an organizatio
nal memory metamodel focused on R&D
centers. The metamodel uses lessons learned extract
ed from corporative social networks; the
metamodel aims to promote learning and management o
f organizational knowledge at these
types of organizations. The analysis is applied ini
tially from lessons learned on topics of R&D
in Spanish language. The metamodel use natural lang
uages processing together with ontologies
for analyze the semantic and lexical the each lesso
n learned. The final result involves a
knowledge base integrated by RDF files interrogated
by SPARQL queries.
Observability Concepts EVERY Developer Should Know -- DeveloperWeek Europe.pdfPaige Cruz
Monitoring and observability aren’t traditionally found in software curriculums and many of us cobble this knowledge together from whatever vendor or ecosystem we were first introduced to and whatever is a part of your current company’s observability stack.
While the dev and ops silo continues to crumble….many organizations still relegate monitoring & observability as the purview of ops, infra and SRE teams. This is a mistake - achieving a highly observable system requires collaboration up and down the stack.
I, a former op, would like to extend an invitation to all application developers to join the observability party will share these foundational concepts to build on:
Multimodal Analytics for Real-time Feedback in Co-located Collaboration, EC-T...Sambit Praharaj
This presentation was part of the EC-TEL conference in Leeds, UK. The full research paper is published in the Springer LNCS proceedings and can be found here:
https://link.springer.com/chapter/10.1007/978-3-319-98572-5_15
An Advanced IR System of Relational Keyword Search Techniquepaperpublications3
Abstract: Now these days keyword search to relational data set becomes an area of research within the data base and Information Retrieval. There is no standard process of information retrieval, which will clearly show the accurate result also it shows keyword search with ranking. Execution time is retrieving of data is more in existing system. We propose a system for increasing performance of relational keyword search systems. In the proposed system we combine schema-based and graph-based approaches and propose a Relational Keyword Search System to overcome the mentioned disadvantages of existing systems and manage the information and user access the information very efficiently. Keyword Search with the ranking requires very low execution time. Execution time of retrieving information and file length during Information retrieval can be display using chart.Keywords: Keyword Search, Datasets, Information Retrieval Query Workloads, Schema-based Systems, Graph-based Systems, ranking, relational databases.
Title: An Advanced IR System of Relational Keyword Search Technique
Author: Dhananjay A. Gholap, Gumaste S. V
ISSN 2350-1022
International Journal of Recent Research in Mathematics Computer Science and Information Technology
Paper Publications
Educational Technology Research Trends: Examining Six SSCI-indexed Refereed ...Yu-Chang Hsu
This study applied text mining methods to examine the abstracts of 2,997 international research articles published between 2000 and 2010 by six journals included in the Social Science Citation Index (SSCI) in the field of Educational Technology (EDTECH). A total of 19 clusters of research areas were identified, and these clusters were further analyzed in terms of productivity by country and by journal. The analysis revealed research areas with rising trends, stable status, and low attention. This study also identified areas of research emphasis by journal and research strength by country. A discussion of results through the lens of Critical Theory of Technology is also included. The authors hope to inform the EDTECH community about the trends of EDTECH research on topics and regions of research contributions. The authors also believe that such examination of trends can help facilitate fruitful discussions of directions for future research, and possible international collaboration across various geographical regions.
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)
SEMANTIC ANALYSIS OVER LESSONS LEARNED CONTAINED IN SOCIAL NETWORKS FOR GENER...cscpconf
This paper shows the construction of an organizational memory metamodel focused on R&D centers. The metamodel uses lessons learned extracted from corporative social networks; the metamodel aims to promote learning and management of organizational knowledge at these types of organizations. The analysis is applied initially from lessons learned on topics of R&D in the Spanish language. The metamodel use natural languages processing together with ontologies
for analyze the semantic and lexical the each lesson learned. The final result involves a knowledge base integrated by RDF files interrogated by SPARQL queries.
Semantic Analysis Over Lessons Learned Contained in Social Networks for Gener...csandit
This paper shows the construction of an organizatio
nal memory metamodel focused on R&D
centers. The metamodel uses lessons learned extract
ed from corporative social networks; the
metamodel aims to promote learning and management o
f organizational knowledge at these
types of organizations. The analysis is applied ini
tially from lessons learned on topics of R&D
in Spanish language. The metamodel use natural lang
uages processing together with ontologies
for analyze the semantic and lexical the each lesso
n learned. The final result involves a
knowledge base integrated by RDF files interrogated
by SPARQL queries.
Observability Concepts EVERY Developer Should Know -- DeveloperWeek Europe.pdfPaige Cruz
Monitoring and observability aren’t traditionally found in software curriculums and many of us cobble this knowledge together from whatever vendor or ecosystem we were first introduced to and whatever is a part of your current company’s observability stack.
While the dev and ops silo continues to crumble….many organizations still relegate monitoring & observability as the purview of ops, infra and SRE teams. This is a mistake - achieving a highly observable system requires collaboration up and down the stack.
I, a former op, would like to extend an invitation to all application developers to join the observability party will share these foundational concepts to build on:
Threats to mobile devices are more prevalent and increasing in scope and complexity. Users of mobile devices desire to take full advantage of the features
available on those devices, but many of the features provide convenience and capability but sacrifice security. This best practices guide outlines steps the users can take to better protect personal devices and information.
GridMate - End to end testing is a critical piece to ensure quality and avoid...ThomasParaiso2
End to end testing is a critical piece to ensure quality and avoid regressions. In this session, we share our journey building an E2E testing pipeline for GridMate components (LWC and Aura) using Cypress, JSForce, FakerJS…
A tale of scale & speed: How the US Navy is enabling software delivery from l...sonjaschweigert1
Rapid and secure feature delivery is a goal across every application team and every branch of the DoD. The Navy’s DevSecOps platform, Party Barge, has achieved:
- Reduction in onboarding time from 5 weeks to 1 day
- Improved developer experience and productivity through actionable findings and reduction of false positives
- Maintenance of superior security standards and inherent policy enforcement with Authorization to Operate (ATO)
Development teams can ship efficiently and ensure applications are cyber ready for Navy Authorizing Officials (AOs). In this webinar, Sigma Defense and Anchore will give attendees a look behind the scenes and demo secure pipeline automation and security artifacts that speed up application ATO and time to production.
We will cover:
- How to remove silos in DevSecOps
- How to build efficient development pipeline roles and component templates
- How to deliver security artifacts that matter for ATO’s (SBOMs, vulnerability reports, and policy evidence)
- How to streamline operations with automated policy checks on container images
Alt. GDG Cloud Southlake #33: Boule & Rebala: Effective AppSec in SDLC using ...James Anderson
Effective Application Security in Software Delivery lifecycle using Deployment Firewall and DBOM
The modern software delivery process (or the CI/CD process) includes many tools, distributed teams, open-source code, and cloud platforms. Constant focus on speed to release software to market, along with the traditional slow and manual security checks has caused gaps in continuous security as an important piece in the software supply chain. Today organizations feel more susceptible to external and internal cyber threats due to the vast attack surface in their applications supply chain and the lack of end-to-end governance and risk management.
The software team must secure its software delivery process to avoid vulnerability and security breaches. This needs to be achieved with existing tool chains and without extensive rework of the delivery processes. This talk will present strategies and techniques for providing visibility into the true risk of the existing vulnerabilities, preventing the introduction of security issues in the software, resolving vulnerabilities in production environments quickly, and capturing the deployment bill of materials (DBOM).
Speakers:
Bob Boule
Robert Boule is a technology enthusiast with PASSION for technology and making things work along with a knack for helping others understand how things work. He comes with around 20 years of solution engineering experience in application security, software continuous delivery, and SaaS platforms. He is known for his dynamic presentations in CI/CD and application security integrated in software delivery lifecycle.
Gopinath Rebala
Gopinath Rebala is the CTO of OpsMx, where he has overall responsibility for the machine learning and data processing architectures for Secure Software Delivery. Gopi also has a strong connection with our customers, leading design and architecture for strategic implementations. Gopi is a frequent speaker and well-known leader in continuous delivery and integrating security into software delivery.
GraphSummit Singapore | The Art of the Possible with Graph - Q2 2024Neo4j
Neha Bajwa, Vice President of Product Marketing, Neo4j
Join us as we explore breakthrough innovations enabled by interconnected data and AI. Discover firsthand how organizations use relationships in data to uncover contextual insights and solve our most pressing challenges – from optimizing supply chains, detecting fraud, and improving customer experiences to accelerating drug discoveries.
Epistemic Interaction - tuning interfaces to provide information for AI supportAlan Dix
Paper presented at SYNERGY workshop at AVI 2024, Genoa, Italy. 3rd June 2024
https://alandix.com/academic/papers/synergy2024-epistemic/
As machine learning integrates deeper into human-computer interactions, the concept of epistemic interaction emerges, aiming to refine these interactions to enhance system adaptability. This approach encourages minor, intentional adjustments in user behaviour to enrich the data available for system learning. This paper introduces epistemic interaction within the context of human-system communication, illustrating how deliberate interaction design can improve system understanding and adaptation. Through concrete examples, we demonstrate the potential of epistemic interaction to significantly advance human-computer interaction by leveraging intuitive human communication strategies to inform system design and functionality, offering a novel pathway for enriching user-system engagements.
In the rapidly evolving landscape of technologies, XML continues to play a vital role in structuring, storing, and transporting data across diverse systems. The recent advancements in artificial intelligence (AI) present new methodologies for enhancing XML development workflows, introducing efficiency, automation, and intelligent capabilities. This presentation will outline the scope and perspective of utilizing AI in XML development. The potential benefits and the possible pitfalls will be highlighted, providing a balanced view of the subject.
We will explore the capabilities of AI in understanding XML markup languages and autonomously creating structured XML content. Additionally, we will examine the capacity of AI to enrich plain text with appropriate XML markup. Practical examples and methodological guidelines will be provided to elucidate how AI can be effectively prompted to interpret and generate accurate XML markup.
Further emphasis will be placed on the role of AI in developing XSLT, or schemas such as XSD and Schematron. We will address the techniques and strategies adopted to create prompts for generating code, explaining code, or refactoring the code, and the results achieved.
The discussion will extend to how AI can be used to transform XML content. In particular, the focus will be on the use of AI XPath extension functions in XSLT, Schematron, Schematron Quick Fixes, or for XML content refactoring.
The presentation aims to deliver a comprehensive overview of AI usage in XML development, providing attendees with the necessary knowledge to make informed decisions. Whether you’re at the early stages of adopting AI or considering integrating it in advanced XML development, this presentation will cover all levels of expertise.
By highlighting the potential advantages and challenges of integrating AI with XML development tools and languages, the presentation seeks to inspire thoughtful conversation around the future of XML development. We’ll not only delve into the technical aspects of AI-powered XML development but also discuss practical implications and possible future directions.
Communications Mining Series - Zero to Hero - Session 1DianaGray10
This session provides introduction to UiPath Communication Mining, importance and platform overview. You will acquire a good understand of the phases in Communication Mining as we go over the platform with you. Topics covered:
• Communication Mining Overview
• Why is it important?
• How can it help today’s business and the benefits
• Phases in Communication Mining
• Demo on Platform overview
• Q/A
UiPath Test Automation using UiPath Test Suite series, part 6DianaGray10
Welcome to UiPath Test Automation using UiPath Test Suite series part 6. In this session, we will cover Test Automation with generative AI and Open AI.
UiPath Test Automation with generative AI and Open AI webinar offers an in-depth exploration of leveraging cutting-edge technologies for test automation within the UiPath platform. Attendees will delve into the integration of generative AI, a test automation solution, with Open AI advanced natural language processing capabilities.
Throughout the session, participants will discover how this synergy empowers testers to automate repetitive tasks, enhance testing accuracy, and expedite the software testing life cycle. Topics covered include the seamless integration process, practical use cases, and the benefits of harnessing AI-driven automation for UiPath testing initiatives. By attending this webinar, testers, and automation professionals can gain valuable insights into harnessing the power of AI to optimize their test automation workflows within the UiPath ecosystem, ultimately driving efficiency and quality in software development processes.
What will you get from this session?
1. Insights into integrating generative AI.
2. Understanding how this integration enhances test automation within the UiPath platform
3. Practical demonstrations
4. Exploration of real-world use cases illustrating the benefits of AI-driven test automation for UiPath
Topics covered:
What is generative AI
Test Automation with generative AI and Open AI.
UiPath integration with generative AI
Speaker:
Deepak Rai, Automation Practice Lead, Boundaryless Group and UiPath MVP
Removing Uninteresting Bytes in Software FuzzingAftab Hussain
Imagine a world where software fuzzing, the process of mutating bytes in test seeds to uncover hidden and erroneous program behaviors, becomes faster and more effective. A lot depends on the initial seeds, which can significantly dictate the trajectory of a fuzzing campaign, particularly in terms of how long it takes to uncover interesting behaviour in your code. We introduce DIAR, a technique designed to speedup fuzzing campaigns by pinpointing and eliminating those uninteresting bytes in the seeds. Picture this: instead of wasting valuable resources on meaningless mutations in large, bloated seeds, DIAR removes the unnecessary bytes, streamlining the entire process.
In this work, we equipped AFL, a popular fuzzer, with DIAR and examined two critical Linux libraries -- Libxml's xmllint, a tool for parsing xml documents, and Binutil's readelf, an essential debugging and security analysis command-line tool used to display detailed information about ELF (Executable and Linkable Format). Our preliminary results show that AFL+DIAR does not only discover new paths more quickly but also achieves higher coverage overall. This work thus showcases how starting with lean and optimized seeds can lead to faster, more comprehensive fuzzing campaigns -- and DIAR helps you find such seeds.
- These are slides of the talk given at IEEE International Conference on Software Testing Verification and Validation Workshop, ICSTW 2022.
Dr. Sean Tan, Head of Data Science, Changi Airport Group
Discover how Changi Airport Group (CAG) leverages graph technologies and generative AI to revolutionize their search capabilities. This session delves into the unique search needs of CAG’s diverse passengers and customers, showcasing how graph data structures enhance the accuracy and relevance of AI-generated search results, mitigating the risk of “hallucinations” and improving the overall customer journey.
Contextual support for collaborative information retrieval
1. Contextual Support for
Collaborative Information Retrieval
Shuguang Han, Daqing He, Zhen Yue
and Jiepu Jiang
1
Shuguang Han, Daqing He, Zhen Yue, and Jiepu Jiang. 2016. Contextual Support for Collaborative Information
Retrieval. In Proceedings of the 2016 ACM on Conference on Human Information Interaction and Retrieval (CHIIR
'16). ACM, New York, NY, USA, 33-42. DOI=http://dx.doi.org/10.1145/2854946.2854963
2. Motivation
Collaborative Information Retrieval (COL) VS. Individual Information Retrieval (IND)
Studies observed an increasing trend of COL, in which people search together for the same task
COL provides unique & interesting contextual factors for search support
team project
ski trip
students
family
Communication & Coordination
Shared Search History
Search
Search
2
3. Research Questions
RQ1: Are IND contextual support directly applicable in COL without
handling complex COL interactions?
3
RQ2: Can partners’ search histories be employed for contextual search
support in COL?
RQ3: Can team members’ chat content be applied for
contextual search support in COL?
4. Contextual Support for COL
Search contexts
Five types (since chat is highly
interactive and is not isolated,
we merge self- and partner-chat)
4
Contextual search support models
Document re-ranking based on search contexts
Experiment setup for contextual search support
Data about user search contexts
Ground-truth
5. Obtaining Data Collection
User study
A self-developed collaborative web search system
Search
Shared Workspace
Shared Query History
Communication & Coordination 5
6. Obtaining Data Collection
Search Tasks
T1: Academic Task
Writing a report to summarize the development of SNS
T2: Leisure Task
Planning a trip to Helsinki
User Study Procedure
Conditions: Collaborative search (COL) & Individual search (IND)
Within subject design
Each team (in COL) / individual(in IND) works 30 mins for each task
Post-task questionnaire for relevance rating of each saved document
User Study Data
18 pairs (for COL) and 18 individuals (for IND)
970 queries, 1,384 clicks and 909 saved documents
6
7. Ground-truth
● For each team {U, V}, pooling document relevance
○ Aggregating document relevance by averaging relevance judgement from other users
● Personalize ground-truth for each query q
○ Pooled relevant documents already-saved relevant documents
7
8. Utilizing Self Search Histories in COL
RQ1: Are IND contextual support directly applicable
in COL?
8
NDCG@NMAP
G: pure google results (baseline)
G + H_QUS: re-rank Google results using self query history
G + H_CLS: re-rank Google results using self click history
Take-away messages
● Self search history is also useful in COL
● QU > CL (different from [Shen et al. 2004])
○ may because of the task nature
○ may because of that self search behaviors in
COL are influenced by collaboration
9. Utilizing Self Search Histories in IND
Academic Leisure
#chat messages 21.56 (20.98) 38.86 (27.24)
#queries 12.97 (6.98) 9.25 (5.30)
#click-through 24.00 (13.23) 14.44 (7.25)
search-intensive task collaboration-intensive task 9
NDCG@NMAP
Take-away messages
● IND is consistent with COL for Academic task
● IND is inconsistent with COL for Leisure task
○ Hypothesis: Strong collaboration effect in leisure task
G: pure google results (baseline)
G + H_QUS: re-rank Google results using self query history
G + H_CLS: re-rank Google results using self click history
10. Utilizing Partners’ Search Histories in COLNDCG@N
RQ2: Can partners’ search histories be employed
for contextual search support in COL?
MAP
10
G + H_QU: re-rank Google by both (self + partner) query history
G + H_CL: re-rank Google by both (self + partner) click history
Take-away messages
● Incorporating search histories from partners
can provide a better contextual support
11. Utilizing Chat Histories in COL
Take-away messages
● Chat-based approach performs the best in the
leisure task
● Chat-based approach outperforms click-based
method in the academic task
● This finding goes beyond our expectation
○ Chat contains a lot noise (our previous study find
that 30% of chats are irrlevant to tasks)
NDCG@N
RQ3: Can team members’ chat content be applied
for contextual search support in COL?
G + H_CH: re-rank Google results by chat history
MAP
11
12. Category Description
Task social (TS) Chats concerning attitude to obtained resources
Task coordination (TC) Chats about the coordination of a task
Task content (TT) Chats related to the content of the search task
Non-task (NT) Chats that are not related to the search task
G + H_X: re-rank Google with {TS, TC, TT, NT} chat
history
NDCG@NMAP
Take-away messages
● Any type of chat (even for NT) helps improve search
● Involving all chat messages achieves the best
Categorization schema for manual chat message coding [2]
12
Utilizing Chat Histories in COL
13. Analyzing Non-Task Chat in COL
Task NT (×10-3) Others (×10-3)
T1 p(X|C) 0.520 1.936
p(X|R) 0.509 2.422
T2 p(X|C) 0.333 2.120
p(X|R) 0.346 3.139
Why NT works?
● They contain useful information. Each chat message refers to all the content a user typed in chat box
before she hits the submit button, which may cover multiple types of chat content.
● Noise in NT (e.g., lol, haha, okay) does not hurt result ranking
13
● p(NT|R) ≈ p(NT|C)
● p(Others|R) > p(Others|C)
p(X|C)
p(X|R)
corpus
relevant docs
C
R
14. Take-away Messages
Contextual support method developed in IND can be directly applied in COL
Task may affect the utility of different search contexts
Partners’ search histories can help for contextual support in COL
Combination of self and partners’ search histories provides better utility
Chat messages can help in for contextual support in COL
Noise in chat messages may not affect the utility of chat-based context
14
16. Task Social
well, hello there
yeah! we are going to Helsinki!
everything looks great so far!
Task Coordination
you do stats and I’ll do impacts on students and professionals
have you done impact yet?
Task Content
ok so outdoor activities will be hard
16
Examples of Different Chat Types
Recent studies have observed an increasing trend of COL, in which two or more people search together for the same search task. For example, a group of students may search and collaborate together on a course project and family members may search and plan together for a ski trip. Comparing to IND that only contains search activities, COL has several unique characteristics such as communication, coordination and shared search history. These are unique & interesting factors that could be useful for better contextual search support.
To understand the usefulness of each type of search context, we study the following research questions. Suppose that we have two users working on a same search task. To support query q_{2n} for u_2, we can follow the method developed in IND that utilizes u_{2}’s self query and click histories. Although they have been demonstrated to be useful in IND, it remains unclear in COL since users’ search behaviors are affected
Note that communication and collaboration will affect search behaviors of COL. This leads to RQ1. Besides self-search history, we can also obtain partners’ search history. This is a unique contextual information and we want to examine its usefulness in RQ2. Additionally, explicit communication, in this case chat, is another unique search context and we want to understand its effectiveness in RQ3.
We mentioned several times about search contexts and contextual support. Here, we provide a detailed explanation. In this paper, we care about search contexts inferred from search history and chat history, where search history can be self and partner. Then, each type of search context will be used in contextual search support. In this study, we examine how each does search context support find relevant documents, in which we apply the document re-ranking approach. Then, we evaluate the effectiveness of each search context based on MAP and nDCG re-ranked search results. However, this requires the ground-truth of relevant documents.
Since there lacks publicly-available data collections & collaborative web search systems. Our data collection is obtained through a user study based on a self-developed CIR system. Here, we show an interface to illustrate the major system functionalities. Users can search a query and system will, by default, return Google results. They can also chat, look at other users’ search queries and saved documents,
Details (537 queries from T1 and 433 from T2)
When building the ground-truth document relevance for a pair {U,V}
Here, ground-truth is changed with the change of different teams and contexts - we only care about these new & relevant documents.
Now, we talk about our experimental results. We firstly examine RQ1, in which we try to understand whether query and click history-based search contexts often applied in IND can also be used in COL. Note that users’ search behaviors will be different since collaboration can interrupt individuals’ search process. The MAP and nDCG evaluations are provided in the left diagram, where the gray means the performance for pure google-based ranking, red indicates re-ranking based on query history and blue means click history. We find that same as IND, self search history is also useful in COL. However, different from IND, QU > CL in COL which may due to: (1) the task nature, meaning that QU will also be better than CL even if in IND; (2) it may also due to that individual’s search behaviors will be affected by collaboration
To test the above two reasons, we apply the same procedure as we did for COL but examine the effectiveness of self search history for IND. Again, the results are shown in this diagram, where we find that (1) QU > CL in academic task which is consistent with COL; (2) while CL has no difference with QU and seems to be even better. This is inconsistent with COL and we think it is because of the strong collaboration effect for leisure task.
Red one uses BOTH query histories from self + partner, Blue one uses BOTH click histories from self + partner. Pink and light blue ones are self-based query and click histories. We find that including both search histories are useful.
not every chat seems relevant to the task. we want to analyze different types of chat.. This motivates us to look further for the task
find a good example for different chat types. Back up slides
too much time. even pure noise, doesn’t matter reformulate the presentation of table & figure. Boundary.
The whole conclusions & future work can be found in our paper. Here are two take-away messages we want to highlight. (Two or session -- chat & partners)