Identifying and Predicting the States of Complex Search Tasks

Liu, Jiqun; Sarkar, Shawon; Shah, Chirag

doi:10.1145/3343413.3377976

Cited by 34 publications

(20 citation statements)

References 48 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In addition, these variations of feature distributions among clusters highly accord with behavioral variations across problem‐help task states extracted in the previous research (Liu et al, 2020). This accordance helps us associate the clustering results with the problem‐help task states, which answered RQ2 .…”

Section: Resultssupporting

confidence: 84%

“…The clustering results show clusters with different distributions of behavioral features identified across several datasets. These patterns are consistent with the behavioral variations in several problem‐help task states identified by Liu, Sarkar and Shah (2020) and can help associate behavioral clusters with corresponding task states under varying search scenarios. Future work can focus on predicting task states with behavioral features and developing adaptive supports in complex search tasks.…”

Section: Discussionsupporting

confidence: 86%

“…For example, when users initiate a long query but do not have many clicks or long dwell time, their interactions might be categorized in cluster 3, while if they have many clicks and long dwell time, but not so long query, their interaction might be in cluster 2. In addition, these variations of feature distributions among clusters highly accord with behavioral variations across problem-help task states extracted in the previous research (Liu et al, 2020). This accordance helps us associate the clustering results with the problem-help task states, which answered RQ2.…”

Section: Resultssupporting

confidence: 80%

“…A large body of IIR research focuses on users' states during the search process and supporting them with problems occurring at each state (Asfari et al, 2009; Kelly et al, 2015; Li & Belkin, 2008). Users' search states are implicit in their daily search process and may affect their explicit behavioral features, such as clicks, dwell time, mouse movement, are prevalent to investigate the relationships with the implicit task states (Aliannejadi et al, 2019; Capra et al, 2018; Cole et al, 2015; Li et al, 2016; Liu, 2019; Liu et al, 2019; Liu et al, 2020). However, previous studies usually required research participants to annotate their task states as the label data for the classification, which is resource‐consuming and difficult for large‐scale experiments (Liu & Shah, 2019).…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Extracting the Implicit Search States from Explicit Behavioral Signals in Complex Search Tasks

Wang

Liu

2021

Proceedings of the Association for Information Science and Tech

Self Cite

View full text Add to dashboard Cite

In a complex search task, users often go through different search states during search interactions under complex search tasks. Automatically identify these search states from observable behavioral measures will enhance our understanding of users' cognitive variations and serve as the basis for state-aware adaptive search recommendations and evaluations. To achieve this goal, this state seeks to extract implicit search states from explicit behavioral signals and explore the possible connection between automatically clustered search states and the existing state typologies developed based on user labeling and expert annotations. The results from our preliminary work indicate that search states and the associated behavioral patterns can be extracted through clustering analysis in multiple datasets, and that the identified clusters/states can be mapped to the states identified via qualitative coding. Our study demonstrates the feasibility of automatically extracting search states and pave the path towards state-aware adaptive search systems.

show abstract

Section: Resultssupporting

confidence: 84%

Section: Discussionsupporting

confidence: 86%

Section: Resultssupporting

confidence: 80%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Extracting the Implicit Search States from Explicit Behavioral Signals in Complex Search Tasks

Wang

Liu

2021

Proceedings of the Association for Information Science and Tech

Self Cite

View full text Add to dashboard Cite

show abstract

“…As one of the key results, Li [42] identifies the most common task-related session stoppingand renewal reasons for the most recent search session, by referencing back to Lin and Belkin's eight renewal modes [22]. In another 2020 study, Liu et al [43] recognise that multi-round search iterations are integral to everyday learning, work, and problem solving. In their research, they explored the dynamic nature of complex search tasks from a process-oriented perspective by identifying and predicting implicit task states.…”

Section: ) Cross-session Searchmentioning

confidence: 99%

Research on Cross-Session and Cross-Device Search: A Systematic Literature Review

2021

View full text Add to dashboard Cite

The complex process of online information search has been of great interest to academics and practitioners, regarding its motivation, triggers, phases, and various aspects of user search behaviour. Web search spanning multiple sessions has been studied, including users switching between devices. The study presented in this paper aims to critically analyse two decades (2000 -2020) of research on cross-session and cross-device search. A systematic literature review of 29 journal papers and peer reviewed academic conference proceedings was conducted. The main results were extracted, synthesised, and presented. Topical (focus and terminology), methodological (data collection, sample size, sample type, and countries studied) and bibliometric (publication outlet and citations) aspects of online information search were evaluated and described. The paper identifies keywords for effective literature searches and adds new insights about effective research methods and sampling, the most cited publications and most influential authors in this field and the possibility of conducting interdisciplinary research. Both scholars and practitioners can use this study to gain a deeper understanding of the crosssession and cross-device search research agenda. Future research suggestions inform researchers about issues that warrant further attention.

show abstract

Understanding users' dynamic perceptions of search gain and cost in sessions: An expectation confirmation model

Wang,

Liu

2024

Asso for Info Science & Tech

Self Cite

View full text Add to dashboard Cite

Understanding the roles of search gain and cost in users' search decision‐making is a key topic in interactive information retrieval (IIR). While previous research has developed user models based on simulated gains and costs, it is unclear how users' actual perceptions of search gains and costs form and change during search interactions. To address this gap, our study adopted expectation‐confirmation theory (ECT) to investigate users' perceptions of gains and costs. We re‐analyzed data from our previous study, examining how contextual and search features affect users' perceptions and how their expectation‐confirmation states impact their following searches. Our findings include: (1) The point where users' actual dwell time meets their constant expectation may serve as a reference point in evaluating perceived gain and cost; (2) these perceptions are associated with in situ experience represented by usefulness labels, browsing behaviors, and queries; (3) users' current confirmation states affect their perceptions of Web page usefulness in the subsequent query. Our findings demonstrate possible effects of expectation‐confirmation, prospect theory, and information foraging theory, highlighting the complex relationships among gain/cost, expectations, and dwell time at the query level, and the reference‐dependent expectation at the session level. These insights enrich user modeling and evaluation in human‐centered IR.

show abstract

Identifying and Predicting the States of Complex Search Tasks

Cited by 34 publications

References 48 publications

Extracting the Implicit Search States from Explicit Behavioral Signals in Complex Search Tasks

Extracting the Implicit Search States from Explicit Behavioral Signals in Complex Search Tasks

Research on Cross-Session and Cross-Device Search: A Systematic Literature Review

Understanding users' dynamic perceptions of search gain and cost in sessions: An expectation confirmation model

Contact Info

Product

Resources

About