Investigating the Relationship between <scp>In‐Situ</scp> User Expectations and Web Search Behavior

Wang, Ben; Liu, Jiqun

doi:10.1002/pra2.740

Cited by 6 publications

(3 citation statements)

References 23 publications

(19 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It reveals that expectations generally exceed actual behaviors (except for dwell time), with less variation. to initial results reported in our previous research, the expectations have skewed distributions, and actual behaviors are correlated with expectations (Wang & Liu, 2022, 2023. To examine the relationship between expectation-behavior gaps and confirmation levels, Figure 4 illustrates the distributions of expectations and actual behaviors across perceived gain and cost levels.…”

Section: Expectation-behavior Gaps and Confirmation Statesmentioning

confidence: 72%

See 1 more Smart Citation

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

Section: Expectation-behavior Gaps and Confirmation Statesmentioning

confidence: 72%

“…Recent studies involved users' cognitive biases and perceptions to analyze and model users' search interactions (Liu & Han, 2020;Wang & Liu, 2022, 2023. These studies involved ECT and referencedependent effects investigating users' relative and implicit states.…”

Section: Expectation-confirmation Effectsmentioning

confidence: 99%

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

show abstract

“…Users encounter difficulties in query formulation or interpreting search results, often due to cognitive barriers, which are common when initializing and refining prompts during interactions with LLMs [23,34]. These barriers often stem from task context and user perceptions, such as lack of prior knowledge, low familiarity level with the topic, high complexity, and inappropriate expectations, leading to potential misconceptions about how LLMs interpret and respond [6,7,19,23,30,31].…”

Section: Llms As Information Access Systemsmentioning

confidence: 99%

Task Supportive and Personalized Human-Large Language Model Interaction: A User Study

Wang,

Liu,

Karimnazarov

et al. 2024

Proceedings of the 2024 ACM SIGIR Conference on Human Information Interaction and Retrieval

Self Cite

View full text Add to dashboard Cite

Large language model (LLM) applications, such as ChatGPT, are a powerful tool for online information-seeking (IS) and problem-solving tasks. However, users still face challenges initializing and refining prompts, and their cognitive barriers and biased perceptions further impede task completion. These issues reflect broader challenges identified within the fields of IS and interactive information retrieval (IIR). To address these, our approach integrates task context and user perceptions into human-ChatGPT interactions through prompt engineering. We developed a ChatGPT-like platform integrated with supportive functions, including perception articulation, prompt suggestion, and conversation explanation. Our findings of a user study demonstrate that the supportive functions help users manage expectations, reduce cognitive loads, better refine prompts, and increase user engagement. This research enhances our comprehension of designing proactive and user-centric systems with LLMs. It offers insights into evaluating human-LLM interactions and emphasizes potential challenges for under served users.CCS Concepts: • Information systems → Retrieval tasks and goals; Personalization; • Human-centered computing → Natural language interfaces.

show abstract

Information search process model based on costs and benefits: a behavioural economics perspective

Qi,

Han,

Hansen

2024

View full text Add to dashboard Cite

PurposeThis study constructed an information search process model based on costs and benefits to reflect different information search processes under different decisions from a behavioural economics perspective.Design/methodology/approachThis study used a deductive approach to conceptualise the costs, benefits, and uncertainties of the information search process. Subsequently, we constructed an information search process model based on the costs and benefits using graphical reasoning, loss aversion theory, bounded rationality theory, the satisficing theory of behavioural economics, and the uncertainty changes of information search process.FindingsThe model revealed four types of user behaviours in the information search process: (1) avoiding search at the initiation of the search process; (2) exiting in the middle of a search; (3) stopping at the point of satisficing; and (4) continuing the search until experiencing physical discomfort.Originality/valueThe model constructed in this study treats the information search as a process based on costs and benefits with uncertainty. This model integrates information search avoidance and stopping into an information search process model. The model identifies users’ bounded rationality by evaluating ideal and real situations. Moreover, the model explains relative and absolute information overloads and the area beyond the user’s bounded rationality. These findings could help improve users’ information literacy and optimise information systems.

show abstract

Investigating the Relationship between In‐Situ User Expectations and Web Search Behavior

Cited by 6 publications

References 23 publications

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

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

Task Supportive and Personalized Human-Large Language Model Interaction: A User Study

Information search process model based on costs and benefits: a behavioural economics perspective

Contact Info

Product

Resources

About