Patterns of Search Result Examination

Abualsaud, Mustafa; Smucker, Mark D.

doi:10.1145/3357384.3358041

Cited by 5 publications

(9 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It has been found that the top result often receives the most visual attention in mobile search (Lewandowski and Kammerer, 2020). The user type, query quality and search results' length also influence users' visual attention and examination behavior (Abualsaud and Smucker, 2019;Sachse, 2019). Additionally, users' visual patterns differ among search devices with different screen sizes, as users have fewer eye movements with a smaller screen (Kim et al, 2015(Kim et al, , 2016.…”

Section: Literature Review 21 User Interaction Behavior In Mobile Searchmentioning

confidence: 99%

Does visual attention help? Towards better understanding and predicting users’ good abandonment behavior in mobile search

Zhang

2022

LHT

View full text Add to dashboard Cite

PurposeGood abandonment behavior refers to users obtaining direct answers via search engine results pages (SERPs) without clicking any search result, which occurs commonly in mobile search. This study aims to better understand users' good abandonment behavior and perception, and then construct a good abandonment prediction model for mobile search with improved performance.Design/methodology/approachIn this study, an in situ user mobile search experiment (N = 43) and a crowdsourcing survey (N = 1,379) were conducted. Good abandonment behavior was analyzed from a quantitative perspective, exploring users' search behavior characteristics from four aspects: session and query, SERPs, gestures and eye-tracking data.FindingsUsers show less engagement with SERPs in good abandonment, spending less time and using fewer gestures, and they pay more visual attention to answer-like results. It was also found that good abandonment behavior is often related to users' perceived difficulty of the searching tasks and trustworthiness in the search engine. A good abandonment prediction model in mobile search was constructed with a high accuracy (97.14%).Originality/valueThis study is the first to explore eye-tracking characteristics of users' good abandonment behavior in mobile search, and to explore users' perception of their good abandonment behavior. Visual attention features are introduced into good abandonment prediction in mobile search for the first time and proved to be important predictors in the proposed model.

show abstract

Section: Literature Review 21 User Interaction Behavior In Mobile Searchmentioning

confidence: 99%

Does visual attention help? Towards better understanding and predicting users’ good abandonment behavior in mobile search

Zhang

2022

LHT

View full text Add to dashboard Cite

show abstract

“…We used the TREC 2019 Decision Track [58] benchmark dataset for fine-tuning our specific quality dimension models. The TREC 2019 Decision Track benchmark dataset contains 51 topics evaluated across three dimensions: relevance, effectiveness and credibility.…”

Section: Domain Adaptation Implementationmentioning

confidence: 99%

“…The 2019 track uses the ClueWeb12-B13 [60,61] corpus, which contains 50 million pages. More details on the TREC 2019 Decision Track [58] benchmark are provided in Appendix 1 Table A2.…”

Section: Domain Adaptation Implementationmentioning

confidence: 99%

“…The CLEF eHealth Lab Series proposed a benchmark to evaluate models according to the relevance, readability, and credibility of the retrieved information [20]. The TREC Health Misinformation Track (2019-2021) proposed further metrics to evaluate models according to the relevance, efficacy, credibility, usefulness, correctness, and supportiveness of the retrieved information [21][22][23]. These metrics are one of the first efforts to quantitatively assess the effectiveness of information retrieval engines to retrieve high-quality information, moving away from the traditional querydocument relevance paradigm [24,25].…”

Section: Introductionmentioning

confidence: 99%

“…Further to this, multi-stage ranking systems [30,31] have been proposed, which couple the system with a label prediction model or employ T5 [33] to re-rank BM25 results. Particularly, Lima et al [29] consider the stance of the search query and engage two assessors for an interactive search, integrating a continuous active learning method [58]. This approach sets a baseline of human effort in separating helpful from harmful Web content.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Online health search via multi-dimensional information quality assessment based on deep language models

Zhang

Naderi

Mishra

et al. 2023

Preprint

View full text Add to dashboard Cite

Background: The presence of widespread misinformation in Web resources and the limited quality control provided by search engines can lead to serious implications for individuals seeking health advice. Objective: We aimed to investigate a multi-dimensional information quality assessment model based on deep learning to enhance the reliability of online healthcare information search results. Methods: In this retrospective study, we simulated online health information search scenarios with a topic set of 35 different health-related inquiries and a corpus containing one billion Web documents from the April 2019 snapshot of Common Crawl. Using state-of-the-art pre-trained language models, we inferred the usefulness, supportiveness, and credibility quality dimensions of the retrieved documents for a given search query. Results: The usefulness model provided the largest distinction between help and harm compatibility documents with a difference of 0.053. The supportiveness model achieved the best harm compatibility (0.024), while the combination of usefulness, supportiveness, and credibility models achieved the best help and harm compatibility on helpful topics. Conclusions: Our results suggest that integrating automatic ranking models created for specific information quality dimensions can increase the effectiveness of health-related information retrieval for decision-making.

show abstract

Cognitive Biases in Search

Azzopardi

2021

Proceedings of the 2021 Conference on Human Information Interaction and Retrieval

130

View full text Add to dashboard Cite

People are susceptible to an array of cognitive biases, which can result in systematic errors and deviations from rational decision making. Over the past decade, an increasing amount of attention has been paid towards investigating how cognitive biases influence information seeking and retrieval behaviours and outcomes. In particular, how such biases may negatively affect decisions because, for example, searchers may seek confirmatory but incorrect information or anchor on an initial search result even if its incorrect. In this perspectives paper, we aim to: (1) bring together and catalogue the emerging work on cognitive biases in the field of Information Retrieval; and (2) provide a critical review and reflection on these studies and subsequent findings. During our analysis we report on over thirty studies, that empirically examined cognitive biases in search, providing over forty key findings related to different domains (e.g. health, web, socio-political) and different parts of the search process (e.g. querying, assessing, judging, etc.). Our reflection highlights the importance of this research area, and critically discusses the limitations, difficulties and challenges when investigating this phenomena along with presenting open questions and future directions in researching the impact -both positive and negative -of cognitive biases in Information Retrieval.

show abstract

Patterns of Search Result Examination

Cited by 5 publications

References 14 publications

Does visual attention help? Towards better understanding and predicting users’ good abandonment behavior in mobile search

Does visual attention help? Towards better understanding and predicting users’ good abandonment behavior in mobile search

Online health search via multi-dimensional information quality assessment based on deep language models

Cognitive Biases in Search

Contact Info

Product

Resources

About