Generating tasks for study of struggling search

Luyan Xu, Xuan Zhou

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

5 Scopus citations

Abstract

Interactive information-seeking systems are designed to help users with their struggling during the searching for complex fact checking tasks, where a searcher may have clear information needs but experience difficulty in collecting required information. However, evaluation and comparison of such systems requires a large number of such tasks, which are difficult to collect or make up. To the best of our knowledge, there has not been a commonly used task set for evaluating struggling search of this kind. This paper proposes a convenient method to generate complex fact checking tasks. Each of the generated task has a clearly defined goal, which however takes an average searcher a significant amount of effort to reach. We conducted lab user studies to verify the feasibility of this method. The results confirmed its feasibility and efficiency.

Original languageEnglish
Title of host publicationCHIIR 2019 - Proceedings of the 2019 Conference on Human Information Interaction and Retrieval
PublisherAssociation for Computing Machinery, Inc
Pages267-270
Number of pages4
ISBN (Electronic)9781450360258
DOIs
StatePublished - 8 Mar 2019
Event4th ACM SIGIR Conference on Information Interaction and Retrieval, CHIIR 2019 - Glasgow, United Kingdom
Duration: 10 Mar 201914 Mar 2019

Publication series

NameCHIIR 2019 - Proceedings of the 2019 Conference on Human Information Interaction and Retrieval

Conference

Conference4th ACM SIGIR Conference on Information Interaction and Retrieval, CHIIR 2019
Country/TerritoryUnited Kingdom
CityGlasgow
Period10/03/1914/03/19

Keywords

  • Struggling search
  • Task design
  • User behavior analysis

Fingerprint

Dive into the research topics of 'Generating tasks for study of struggling search'. Together they form a unique fingerprint.

Cite this