Domain-Specific Modeling of User Knowledge in Informational Search Sessions

Research output: Chapter in book/report/conference proceedingConference contributionResearchpeer review

Authors

  • Rui Tang
  • Ran Yu
  • Markus Rokicki
  • Ralph Ewerth
  • Stefan Dietze

Research Organisations

External Research Organisations

  • Ping An Technology
  • University of Bonn
  • GESIS - Leibniz Institute for the Social Sciences
  • University Hospital Düsseldorf
View graph of relations

Details

Original languageEnglish
Title of host publicationCIKM 2021 Workshops
Subtitle of host publicationProceedings of the CIKM 2021 Workshops co-located with 30th ACM International Conference on Information and Knowledge Management (CIKM 2021)
Publication statusPublished - 2021
Event2021 International Conference on Information and Knowledge Management Workshops, CIKMW 2021 - Gold Coast, Australia
Duration: 1 Nov 20215 Nov 2021

Publication series

NameCEUR Workshop Proceedings
PublisherCEUR Workshop Proceedings
Volume3052
ISSN (Print)1613-0073

Abstract

Users frequently search on the Web to fulfill information needs with learning intent. In this context, usefulness of the search results depends strongly on the knowledge state of the user. In order to satisfy learning needs effectively, it is necessary to take users' knowledge gain and knowledge state within learning-oriented Web search sessions into account. Previous works studied the use of supervised models to predict a user's knowledge gain and knowledge state. However, the impact of knowledge domains of the search topics on a user's learning process have not been adequately explored. In this paper, we suggest domain detection techniques for search sessions and build domain-specific knowledge prediction models accordingly. Experimental evaluation results demonstrate that our approach outperforms the state-of-the-art baseline.

Keywords

    Informational search, Knowledge gain, Search as learning

ASJC Scopus subject areas

Cite this

Domain-Specific Modeling of User Knowledge in Informational Search Sessions. / Tang, Rui; Yu, Ran; Rokicki, Markus et al.
CIKM 2021 Workshops: Proceedings of the CIKM 2021 Workshops co-located with 30th ACM International Conference on Information and Knowledge Management (CIKM 2021). 2021. (CEUR Workshop Proceedings; Vol. 3052).

Research output: Chapter in book/report/conference proceedingConference contributionResearchpeer review

Tang, R, Yu, R, Rokicki, M, Ewerth, R & Dietze, S 2021, Domain-Specific Modeling of User Knowledge in Informational Search Sessions. in CIKM 2021 Workshops: Proceedings of the CIKM 2021 Workshops co-located with 30th ACM International Conference on Information and Knowledge Management (CIKM 2021). CEUR Workshop Proceedings, vol. 3052, 2021 International Conference on Information and Knowledge Management Workshops, CIKMW 2021, Gold Coast, Australia, 1 Nov 2021. <https://ceur-ws.org/Vol-3052/paper8.pdf>
Tang, R., Yu, R., Rokicki, M., Ewerth, R., & Dietze, S. (2021). Domain-Specific Modeling of User Knowledge in Informational Search Sessions. In CIKM 2021 Workshops: Proceedings of the CIKM 2021 Workshops co-located with 30th ACM International Conference on Information and Knowledge Management (CIKM 2021) (CEUR Workshop Proceedings; Vol. 3052). https://ceur-ws.org/Vol-3052/paper8.pdf
Tang R, Yu R, Rokicki M, Ewerth R, Dietze S. Domain-Specific Modeling of User Knowledge in Informational Search Sessions. In CIKM 2021 Workshops: Proceedings of the CIKM 2021 Workshops co-located with 30th ACM International Conference on Information and Knowledge Management (CIKM 2021). 2021. (CEUR Workshop Proceedings).
Tang, Rui ; Yu, Ran ; Rokicki, Markus et al. / Domain-Specific Modeling of User Knowledge in Informational Search Sessions. CIKM 2021 Workshops: Proceedings of the CIKM 2021 Workshops co-located with 30th ACM International Conference on Information and Knowledge Management (CIKM 2021). 2021. (CEUR Workshop Proceedings).
Download
@inproceedings{20375ca7a8304f6b9a959c835793c43f,
title = "Domain-Specific Modeling of User Knowledge in Informational Search Sessions",
abstract = "Users frequently search on the Web to fulfill information needs with learning intent. In this context, usefulness of the search results depends strongly on the knowledge state of the user. In order to satisfy learning needs effectively, it is necessary to take users' knowledge gain and knowledge state within learning-oriented Web search sessions into account. Previous works studied the use of supervised models to predict a user's knowledge gain and knowledge state. However, the impact of knowledge domains of the search topics on a user's learning process have not been adequately explored. In this paper, we suggest domain detection techniques for search sessions and build domain-specific knowledge prediction models accordingly. Experimental evaluation results demonstrate that our approach outperforms the state-of-the-art baseline.",
keywords = "Informational search, Knowledge gain, Search as learning",
author = "Rui Tang and Ran Yu and Markus Rokicki and Ralph Ewerth and Stefan Dietze",
note = "Funding Information: Part of this work is supported by the Leibniz Association, Germany (Leibniz Competition 2018, funding line {"}Collaborative Excellence{"}, project SALIENT [K68/2017]). ; 2021 International Conference on Information and Knowledge Management Workshops, CIKMW 2021 ; Conference date: 01-11-2021 Through 05-11-2021",
year = "2021",
language = "English",
series = "CEUR Workshop Proceedings",
publisher = "CEUR Workshop Proceedings",
booktitle = "CIKM 2021 Workshops",

}

Download

TY - GEN

T1 - Domain-Specific Modeling of User Knowledge in Informational Search Sessions

AU - Tang, Rui

AU - Yu, Ran

AU - Rokicki, Markus

AU - Ewerth, Ralph

AU - Dietze, Stefan

N1 - Funding Information: Part of this work is supported by the Leibniz Association, Germany (Leibniz Competition 2018, funding line "Collaborative Excellence", project SALIENT [K68/2017]).

PY - 2021

Y1 - 2021

N2 - Users frequently search on the Web to fulfill information needs with learning intent. In this context, usefulness of the search results depends strongly on the knowledge state of the user. In order to satisfy learning needs effectively, it is necessary to take users' knowledge gain and knowledge state within learning-oriented Web search sessions into account. Previous works studied the use of supervised models to predict a user's knowledge gain and knowledge state. However, the impact of knowledge domains of the search topics on a user's learning process have not been adequately explored. In this paper, we suggest domain detection techniques for search sessions and build domain-specific knowledge prediction models accordingly. Experimental evaluation results demonstrate that our approach outperforms the state-of-the-art baseline.

AB - Users frequently search on the Web to fulfill information needs with learning intent. In this context, usefulness of the search results depends strongly on the knowledge state of the user. In order to satisfy learning needs effectively, it is necessary to take users' knowledge gain and knowledge state within learning-oriented Web search sessions into account. Previous works studied the use of supervised models to predict a user's knowledge gain and knowledge state. However, the impact of knowledge domains of the search topics on a user's learning process have not been adequately explored. In this paper, we suggest domain detection techniques for search sessions and build domain-specific knowledge prediction models accordingly. Experimental evaluation results demonstrate that our approach outperforms the state-of-the-art baseline.

KW - Informational search

KW - Knowledge gain

KW - Search as learning

UR - http://www.scopus.com/inward/record.url?scp=85122885935&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:85122885935

T3 - CEUR Workshop Proceedings

BT - CIKM 2021 Workshops

T2 - 2021 International Conference on Information and Knowledge Management Workshops, CIKMW 2021

Y2 - 1 November 2021 through 5 November 2021

ER -