{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,24]],"date-time":"2025-12-24T12:26:34Z","timestamp":1766579194276,"version":"3.41.2"},"reference-count":44,"publisher":"Emerald","issue":"4","license":[{"start":{"date-parts":[[2023,4,11]],"date-time":"2023-04-11T00:00:00Z","timestamp":1681171200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.emerald.com\/insight\/site-policies"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["AJIM"],"published-print":{"date-parts":[[2024,6,26]]},"abstract":"<jats:sec><jats:title content-type=\"abstract-subheading\">Purpose<\/jats:title><jats:p>Turn-taking is beneficial to conversational search success, but the increase in turns and time can also increase the cognitive load of the user. Therefore, in this research paper, the authors view conversational search sessions through the lens of economic theory and use the economic models of search to analyze the various costs and benefits of information-seeking interactions.<\/jats:p><\/jats:sec><jats:sec><jats:title content-type=\"abstract-subheading\">Design\/methodology\/approach<\/jats:title><jats:p>First, the authors built a cost-benefit model for conversational search sessions by defining action types and performing an intellectual mapping of actual sessions into sequences of these actions (using thematic analyses). The authors used the hypothesized cost and benefit actions (obtained from the user-system dialogs), along with the number of turns, utterances and time-related parameters, to propose the mathematical model. Next, the authors tested the model empirically by comparing the model scores to the user satisfaction and task success scores (collected through questionnaires). By representing each session as a bag of actions, the authors developed linear regression models to predict task success and user satisfaction.<\/jats:p><\/jats:sec><jats:sec><jats:title content-type=\"abstract-subheading\">Findings<\/jats:title><jats:p>Through feature analysis and significance testing, the authors identify the different parameters that contribute significantly to user satisfaction and task success scores. Error analysis shows that the model predicts task success and user satisfaction reasonably well, with the average prediction error being 0.5 for both (on a 5-point scale).<\/jats:p><\/jats:sec><jats:sec><jats:title content-type=\"abstract-subheading\">Originality\/value<\/jats:title><jats:p>The authors' research is an initial step toward building a mathematical model for predicting user satisfaction and task success in conversational search sessions.<\/jats:p><\/jats:sec>","DOI":"10.1108\/ajim-08-2022-0368","type":"journal-article","created":{"date-parts":[[2023,4,7]],"date-time":"2023-04-07T23:40:10Z","timestamp":1680910810000},"page":"613-628","source":"Crossref","is-referenced-by-count":2,"title":["Exploring the economics of\u00a0conversational search sessions"],"prefix":"10.1108","volume":"76","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1610-9038","authenticated-orcid":false,"given":"Souvick","family":"Ghosh","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1951-6280","authenticated-orcid":false,"given":"Julie","family":"Gogoi","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9779-0437","authenticated-orcid":false,"given":"Kristen","family":"Chua","sequence":"additional","affiliation":[]}],"member":"140","published-online":{"date-parts":[[2023,4,11]]},"reference":[{"first-page":"475","article-title":"Asking clarifying questions in open-domain information-seeking conversations","year":"2019","key":"key2024062606170501400_ref001"},{"first-page":"16","article-title":"Analysing mixed initiatives and search strategies during conversational search","year":"2021","key":"key2024062606170501400_ref002"},{"issue":"5","key":"key2024062606170501400_ref003","doi-asserted-by":"crossref","first-page":"14","DOI":"10.1109\/5254.796083","article-title":"Mixed-initiative interaction","volume":"14","year":"1999","journal-title":"IEEE Intelligent Systems and Their Applications"},{"first-page":"1","article-title":"An architecture for more realistic conversational systems","year":"2001","key":"key2024062606170501400_ref004"},{"volume-title":"A Taxonomy for Learning, Teaching, and Assessing: A Revision of Bloom\u2019s Taxonomy of Educational Objectives","year":"2001","key":"key2024062606170501400_ref005"},{"issue":"5","key":"key2024062606170501400_ref006","doi-asserted-by":"crossref","first-page":"460","DOI":"10.1007\/s10791-010-9133-9","article-title":"Expected reading effort in focused retrieval evaluation","volume":"13","year":"2010","journal-title":"Information Retrieval"},{"first-page":"15","article-title":"The economics in interactive information retrieval","year":"2011","key":"key2024062606170501400_ref007"},{"first-page":"3","article-title":"Modelling interaction with economic models of search","year":"2014","key":"key2024062606170501400_ref008"},{"first-page":"59","article-title":"An analysis of the cost and benefit of search interactions","year":"2016","key":"key2024062606170501400_ref009"},{"first-page":"23","article-title":"How query cost affects search behavior","year":"2013","key":"key2024062606170501400_ref010"},{"first-page":"1321","article-title":"cwl_eval: an evaluation tool for information retrieval","year":"2019","key":"key2024062606170501400_ref011"},{"first-page":"31","article-title":"Towards building economic models of conversational search","year":"2022","key":"key2024062606170501400_ref012"},{"first-page":"903","article-title":"System effectiveness, user models, and user utility: a conceptual framework for investigation","year":"2011","key":"key2024062606170501400_ref013"},{"issue":"4","key":"key2024062606170501400_ref014","doi-asserted-by":"crossref","first-page":"291","DOI":"10.1108\/eb026436","article-title":"Opening the black box of \u2018relevance\u2019","volume":"23","year":"1967","journal-title":"Journal of Documentation"},{"issue":"2","key":"key2024062606170501400_ref015","doi-asserted-by":"crossref","first-page":"87","DOI":"10.1002\/asi.4630240204","article-title":"On selecting a measure of retrieval effectiveness","volume":"24","year":"1973","journal-title":"Journal of the American Society for Information Science"},{"year":"2020","key":"key2024062606170501400_ref016","article-title":"Conversational strategies: impact on search performance in a goal-oriented task"},{"year":"2020","key":"key2024062606170501400_ref017"},{"issue":"1","key":"key2024062606170501400_ref046","doi-asserted-by":"crossref","first-page":"173","DOI":"10.1002\/pra2.446","article-title":"\u2018Can you search for me?\u2019: understanding and improving user\u2010system dialogues for complex search tasks","volume":"58","year":"2021","journal-title":"Proceedings of the Association for Information Science and Technology"},{"key":"key2024062606170501400_ref045","doi-asserted-by":"crossref","first-page":"267","DOI":"10.1145\/3406522.3446057","article-title":"Classifying speech acts using multi-channel deep attention network for task-oriented conversational search agents","volume-title":"Proceedings of the 2021 Conference on Human Information Interaction and Retrieval","year":"2021"},{"issue":"4","key":"key2024062606170501400_ref018","doi-asserted-by":"crossref","first-page":"612","DOI":"10.1109\/TE.2005.856149","article-title":"AutoTutor: an intelligent tutoring system with mixed-initiative dialogue","volume":"48","year":"2005","journal-title":"IEEE Transactions on Education"},{"issue":"4","key":"key2024062606170501400_ref019","doi-asserted-by":"crossref","first-page":"422","DOI":"10.1145\/582415.582418","article-title":"Cumulated gain-based evaluation of IR techniques","volume":"20","year":"2002","journal-title":"ACM Transactions on Information Systems (TOIS)"},{"key":"key2024062606170501400_ref020","doi-asserted-by":"crossref","unstructured":"J\u00e4rvelin, K. and Kek\u00e4l\u00e4inen, J. (2017), \u201cIR evaluation methods for retrieving highly relevant documents\u201d, ACM SIGIR Forum, ACM, New York, NY, Vol.\u00a051 No. 2, pp.\u00a0243-250.","DOI":"10.1145\/3130348.3130374"},{"first-page":"4","article-title":"Discounted cumulated gain based evaluation of multiple-query IR sessions","year":"2008","key":"key2024062606170501400_ref021"},{"first-page":"1257","article-title":"Toward voice query clarification","year":"2018","key":"key2024062606170501400_ref022"},{"first-page":"45","article-title":"Predicting user satisfaction with intelligent assistants","year":"2016","key":"key2024062606170501400_ref023"},{"first-page":"129","article-title":"Analysing the effect of clarifying questions on document ranking in conversational search","year":"2020","key":"key2024062606170501400_ref024"},{"issue":"4","key":"key2024062606170501400_ref025","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3451160","article-title":"How am I doing?: evaluating conversational search systems offline","volume":"39","year":"2021","journal-title":"ACM Transactions on Information Systems (TOIS)"},{"first-page":"923","article-title":"Investigating cognitive effects in session-level search user satisfaction","year":"2019","key":"key2024062606170501400_ref026"},{"year":"2021","key":"key2024062606170501400_ref027","article-title":"Ranking clarifying questions based on predicted user engagement"},{"key":"key2024062606170501400_ref028","first-page":"71","article-title":"Good computational manners: mixed-initiative dialog in conversational agents","author":"Tutoring Research Group","year":"2002"},{"first-page":"313","article-title":"Searching and stopping: an analysis of stopping rules and strategies","year":"2015","key":"key2024062606170501400_ref029"},{"first-page":"659","article-title":"Users versus models: what observation tells us about effectiveness metrics","year":"2013","key":"key2024062606170501400_ref030"},{"first-page":"117","article-title":"A theoretical framework for conversational search","year":"2017","key":"key2024062606170501400_ref031"},{"volume":"II","article-title":"A field experimental approach to the study of relevance assessments in relation to document searching","year":"1967","key":"key2024062606170501400_ref032"},{"year":"2018","key":"key2024062606170501400_ref033","article-title":"Learning to ask good questions: ranking clarification questions using neural expected value of perfect information"},{"volume-title":"User Experience in the Library: A Case Study","year":"2008","key":"key2024062606170501400_ref034"},{"first-page":"473","article-title":"Summaries, ranked retrieval and sessions: a unified framework for information access evaluation","year":"2013","key":"key2024062606170501400_ref035"},{"key":"key2024062606170501400_ref036","unstructured":"Smucker, M.D. and Clarke, C.L. (2012), \u201cThe fault, dear researchers, is not in Cranfield, but in our metrics, that they are unrealistic\u201d, EuroHCIR, pp.\u00a011-12."},{"issue":"3","key":"key2024062606170501400_ref037","doi-asserted-by":"crossref","first-page":"213","DOI":"10.1086\/258464","article-title":"The economics of information","volume":"69","year":"1961","journal-title":"Journal of Political Economy"},{"first-page":"239","article-title":"Modeling decision points in user search behavior","year":"2014","key":"key2024062606170501400_ref038"},{"first-page":"325","article-title":"How do people interact in conversational speech-only search tasks: a preliminary analysis","year":"2017","key":"key2024062606170501400_ref039"},{"first-page":"115","article-title":"Portfolio theory of information retrieval","year":"2009","key":"key2024062606170501400_ref040"},{"issue":"7","key":"key2024062606170501400_ref041","doi-asserted-by":"crossref","first-page":"961","DOI":"10.1002\/asi.20361","article-title":"Relevance judgment: what do information users consider beyond topicality?","volume":"57","year":"2006","journal-title":"Journal of the American Society for Information Science and Technology"},{"first-page":"280","article-title":"Understandability biased evaluation for information retrieval","year":"2016","key":"key2024062606170501400_ref042"}],"container-title":["Aslib Journal of Information Management"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.emerald.com\/insight\/content\/doi\/10.1108\/AJIM-08-2022-0368\/full\/xml","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.emerald.com\/insight\/content\/doi\/10.1108\/AJIM-08-2022-0368\/full\/html","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,7,24]],"date-time":"2025-07-24T23:01:10Z","timestamp":1753398070000},"score":1,"resource":{"primary":{"URL":"http:\/\/www.emerald.com\/ajim\/article\/76\/4\/613-628\/1216973"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,4,11]]},"references-count":44,"journal-issue":{"issue":"4","published-online":{"date-parts":[[2023,4,11]]},"published-print":{"date-parts":[[2024,6,26]]}},"alternative-id":["10.1108\/AJIM-08-2022-0368"],"URL":"https:\/\/doi.org\/10.1108\/ajim-08-2022-0368","relation":{},"ISSN":["2050-3806"],"issn-type":[{"type":"print","value":"2050-3806"}],"subject":[],"published":{"date-parts":[[2023,4,11]]}}}