{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,27]],"date-time":"2026-05-27T18:05:25Z","timestamp":1779905125397,"version":"3.53.1"},"reference-count":58,"publisher":"Public Library of Science (PLoS)","issue":"5","license":[{"start":{"date-parts":[[2026,5,27]],"date-time":"2026-05-27T00:00:00Z","timestamp":1779840000000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100000266","name":"Engineering and Physical Sciences Research Council","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100000266","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["www.plosdigitalhealth.org"],"crossmark-restriction":false},"short-container-title":["PLOS Digit Health"],"abstract":"<jats:p>In this paper, we present conversational longitudinal ecological assessment (CLEA), a novel conversational AI\u2013enabled method for collecting ecologically valid, temporally sensitive qualitative health data via mobile instant messaging. We report findings from an exploratory deployment of an instantiation of CLEA within a 12-week community-based weight management programme, delivered by a charity partner in an area of deprivation. Using WhatsApp, we deployed our CLEA chat-agent to conduct twice-weekly conversational data collection sessions with participants, to elicit data about their experience of the programme and associated behaviour change. This was followed by in-person semi-structured interviews (N\u2009=\u20099) to examine user experiences and perceptions of interacting with the chat-agent. Participants reported that WhatsApp\u2019s familiarity supported accessibility and sustained engagement, while the conversational format encouraged reflection directed towards the research focus. Responding to chat-agent prompts required cognitive effort, leading some participants to defer engagement until they had adequate time and mental space; however, this reflective demand was largely experienced as beneficial within the programme context. The AI\u2019s quasi-human interactional qualities fostered a sense of support while reducing social judgement, enabling more candid disclosure. Together, these findings suggest initial feasibility and acceptability of this CLEA implementation within a community-based programme in an area of deprivation. Further, while the responses in single messages were often brief, useful, relevant, and meaningful insights appeared to develop over the course of conversational sessions. The study highlights both the opportunities and trade-offs of conversational AI for qualitative data collection, including design implications for health researchers looking to implement or extend the method. Finally, we position CLEA in relation to other longitudinal methods of qualitative health data elicitation.<\/jats:p>","DOI":"10.1371\/journal.pdig.0001216","type":"journal-article","created":{"date-parts":[[2026,5,27]],"date-time":"2026-05-27T17:33:12Z","timestamp":1779903192000},"page":"e0001216","update-policy":"https:\/\/doi.org\/10.1371\/journal.pdig.corrections_policy","source":"Crossref","is-referenced-by-count":0,"title":["Conversational, Longitudinal, Ecological Assessment (CLEA): Exploring a new AI-driven method for qualitative data collection in a behavioural health context"],"prefix":"10.1371","volume":"5","author":[{"ORCID":"https:\/\/orcid.org\/0009-0007-4024-4818","authenticated-orcid":true,"given":"Samuel","family":"Downes","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Thomas","family":"Krys","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kenton","family":"O\u2019Hara","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Max","family":"Western","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lauren","family":"Thompson","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Amberly","family":"Brigden","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"340","published-online":{"date-parts":[[2026,5,27]]},"reference":[{"issue":"10","key":"pdig.0001216.ref001","doi-asserted-by":"crossref","first-page":"1316","DOI":"10.1177\/1049732307306927","article-title":"Justifying knowledge, justifying method, taking action: epistemologies, methodologies, and methods in qualitative research","volume":"17","author":"SM Carter","year":"2007","journal-title":"Qual Health Res"},{"key":"pdig.0001216.ref002","first-page":"1101","article-title":"Qualitative methods: what are they and why use them?","volume":"34","author":"S Sofaer","year":"1999","journal-title":"Health Serv Res"},{"key":"pdig.0001216.ref003","doi-asserted-by":"crossref","unstructured":"Conner TS, Mehl MR. Ambulatory assessment: methods for studying everyday life. In: Scott RA, Kosslyn SM, editors. Emerging trends in the social and behavioral sciences; 2015. https:\/\/doi.org\/10.1002\/9781118900772.etrds0010","DOI":"10.1002\/9781118900772.etrds0010"},{"key":"pdig.0001216.ref004","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1146\/annurev.clinpsy.3.022806.091415","article-title":"Ecological momentary assessment","volume":"4","author":"S Shiffman","year":"2008","journal-title":"Annu Rev Clin Psychol"},{"issue":"4","key":"pdig.0001216.ref005","article-title":"Advantages and disadvantages of four interview techniques in qualitative research","volume":"7","author":"RJG Opdenakker","year":"2006","journal-title":"Forum Qual Soc Res"},{"key":"pdig.0001216.ref006","doi-asserted-by":"crossref","DOI":"10.1177\/16094069251316745","article-title":"Comparing in-person and remote qualitative data collection methods for data quality and inclusion: a scoping review","volume":"24","author":"J Roberts","year":"2025","journal-title":"Int J Qual Methods"},{"key":"pdig.0001216.ref007","first-page":"43","article-title":"Physiological data and the study of mathematics teachers\u2019 emotions: Using GSR data to trigger teacher reflection","volume":"25","author":"J Lake","year":"2023","journal-title":"Math Teach Educ Dev"},{"issue":"1","key":"pdig.0001216.ref008","doi-asserted-by":"crossref","DOI":"10.2196\/34384","article-title":"The impact of wearable technologies in health research: scoping review","volume":"10","author":"S Huhn","year":"2022","journal-title":"JMIR Mhealth Uhealth"},{"key":"pdig.0001216.ref009","volume-title":"Intensive longitudinal methods: an introduction to diary and experience sampling research","author":"N Bolger","year":"2013"},{"key":"pdig.0001216.ref010","doi-asserted-by":"crossref","first-page":"579","DOI":"10.1146\/annurev.psych.54.101601.145030","article-title":"Diary methods: capturing life as it is lived","volume":"54","author":"N Bolger","year":"2003","journal-title":"Annu Rev Psychol"},{"key":"pdig.0001216.ref011","doi-asserted-by":"crossref","DOI":"10.1177\/16094069241296189","article-title":"Qualitative digital diary methods: participant-led values for ethical and insightful mental health research","volume":"23","author":"C McCombie","year":"2024","journal-title":"Int J Qual Methods"},{"key":"pdig.0001216.ref012","doi-asserted-by":"crossref","first-page":"100492","DOI":"10.1016\/j.ssmqr.2024.100492","article-title":"A methodological review of solicited diaries as a qualitative tool in health research in low- and middle-income countries","volume":"6","author":"T Akinreni","year":"2024","journal-title":"SSM Qual Res Health"},{"issue":"5","key":"pdig.0001216.ref013","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pone.0217150","article-title":"Involving stakeholders in the design of ecological momentary assessment research: an example from smoking cessation","volume":"14","author":"PD Soyster","year":"2019","journal-title":"PLoS One"},{"key":"pdig.0001216.ref014","doi-asserted-by":"crossref","first-page":"107","DOI":"10.1146\/annurev-clinpsy-080921-083128","article-title":"Evaluation of pressing issues in ecological momentary assessment","volume":"19","author":"AA Stone","year":"2023","journal-title":"Annu Rev Clin Psychol"},{"issue":"1","key":"pdig.0001216.ref015","doi-asserted-by":"crossref","first-page":"185","DOI":"10.1037\/pspp0000248","article-title":"How was your day? Convergence of aggregated momentary and retrospective end-of-day affect ratings across the adult life span","volume":"119","author":"AB Neubauer","year":"2020","journal-title":"J Pers Soc Psychol"},{"key":"pdig.0001216.ref016","doi-asserted-by":"crossref","first-page":"151","DOI":"10.1146\/annurev-clinpsy-050212-185510","article-title":"Ambulatory assessment","volume":"9","author":"TJ Trull","year":"2013","journal-title":"Annu Rev Clin Psychol"},{"issue":"1","key":"pdig.0001216.ref017","doi-asserted-by":"crossref","first-page":"281","DOI":"10.1093\/tbm\/ibz165","article-title":"How intensive longitudinal data can stimulate advances in health behavior maintenance theories and interventions","volume":"11","author":"GF Dunton","year":"2021","journal-title":"Transl Behav Med"},{"issue":"2","key":"pdig.0001216.ref018","first-page":"1","article-title":"Longitudinal qualitative methods in health behavior and nursing research: assumptions, analysis, design and lessons learned","volume":"17","author":"EL Tuthill","year":"2020","journal-title":"Qual Res Psychol"},{"issue":"7","key":"pdig.0001216.ref019","first-page":"1021","article-title":"Artificial intelligence augmented analysis: the way of the future?","volume":"34","author":"D Hitch","year":"2023","journal-title":"Qual Health Res"},{"issue":"13","key":"pdig.0001216.ref020","doi-asserted-by":"crossref","first-page":"1125","DOI":"10.1177\/10497323231210816","article-title":"What does ChatGPT mean for qualitative health research?","volume":"33","author":"M van Manen","year":"2023","journal-title":"Qual Health Res"},{"issue":"9","key":"pdig.0001216.ref021","first-page":"789","article-title":"Prompts, pearls, imperfections: Comparing ChatGPT and a human researcher in qualitative data analysis","volume":"35","author":"J Wachinger","year":"2024","journal-title":"Qual Health Res"},{"issue":"12","key":"pdig.0001216.ref022","doi-asserted-by":"crossref","first-page":"1191","DOI":"10.1037\/hea0000234","article-title":"Data-prompted interviews: using individual ecological data to stimulate narratives and explore meanings","volume":"34","author":"D Kwasnicka","year":"2015","journal-title":"Health Psychol"},{"key":"pdig.0001216.ref023","unstructured":"Geiecke S, Jaravel X. Conversations at scales: robust AI led interviews. 2024;\u00a01:1. Available from: https:\/\/papers.ssrn.com\/sol3\/papers.cfm?abstract_id=4974382"},{"key":"pdig.0001216.ref024","unstructured":"Wuttke T. AI Conversational Interviewing: Transforming Surveys with LLMs as Adaptive Interviewers. 2024;1:1. Available from: https:\/\/arxiv.org\/abs\/2410.01824"},{"key":"pdig.0001216.ref025","doi-asserted-by":"crossref","unstructured":"Chopra F, Haaland M. Conducting qualitative interviews with AI. 2024;1:1. Available from: https:\/\/papers.ssrn.com\/sol3\/papers.cfm?abstract_id=4583756","DOI":"10.1257\/rct.15069-1.0"},{"key":"pdig.0001216.ref026","doi-asserted-by":"crossref","first-page":"127","DOI":"10.1561\/1500000074","article-title":"Neural approaches to conversational AI","volume":"13","author":"J Gao","year":"2019","journal-title":"Found Trends Inf Retr"},{"key":"pdig.0001216.ref027","doi-asserted-by":"crossref","unstructured":"Tallyn E. The ethnobot: Gathering ethnographies in the age of IoT. In: Proceedings of the 2018 CHI conference on human factors in computing systems, 2018 Apr 21. Vol. 1, Issue 604. pp. 1\u2013 13. https:\/\/doi.org\/10.1145\/3173574.317417","DOI":"10.1145\/3173574.3174178"},{"key":"pdig.0001216.ref028","doi-asserted-by":"crossref","unstructured":"Luger E, Sellen A. \u201cLike having a really bad PA\u201d: the gulf between user expectation and experience of conversational agents. Proc SIGCHI Conf Hum Factors Comput Syst; 2016. p. 5286\u201397. https:\/\/doi.org\/10.1145\/2858036.2858288","DOI":"10.1145\/2858036.2858288"},{"issue":"3","key":"pdig.0001216.ref029","doi-asserted-by":"crossref","DOI":"10.1145\/3381804","article-title":"Tell me about yourself: using an AI-powered chatbot to conduct conversational surveys with open-ended questions","volume":"27","author":"Z Xiao","year":"2020","journal-title":"ACM Trans Comput Hum Interact"},{"key":"pdig.0001216.ref030","unstructured":"Yi Z, et al. A survey on recent advances in LLM-based multi-turn dialogue systems. arXiv [Preprint]; 2024. Available from: https:\/\/arxiv.org\/pdf\/2402.18013"},{"issue":"2","key":"pdig.0001216.ref031","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3710947","article-title":"Collecting qualitative data at scale with large language models: a case study","volume":"9","author":"A Cuevas","year":"2025","journal-title":"Proc ACM Hum-Comput Interact"},{"key":"pdig.0001216.ref032","unstructured":"Gavin S, Zheng T, Liu J, Que Q, Wang N, Yang J, et al. LongIns: a challenging long-context instruction-based exam for LLMs. arXiv:2406.17588 [Preprint]. 2024."},{"key":"pdig.0001216.ref033","unstructured":"Kuratov Y, Bulatov A, Anokhin P, Sorokin D, Sorokin A, Burtsev M. In search of needles in a 11M haystack: recurrent memory finds what LLMs miss. arXiv:2402.10790 [Preprint]. 2024."},{"key":"pdig.0001216.ref034","doi-asserted-by":"crossref","unstructured":"Pant D, et al. Technical evaluation of GPT-4 and GPT-4-Turbo reflective listening response generation. Proc AIME 2024; 2024. Available from: https:\/\/aime24.aimedicine.info\/wp-content\/uploads\/2024\/07\/AIME_2024_paper_350.pdf","DOI":"10.21203\/rs.3.rs-4769572\/v1"},{"key":"pdig.0001216.ref035","unstructured":"Bardol F. ChatGPT reads your tone and responds accordingly -- until it does not -- emotional framing induces bias in LLM outputs. arXiv preprint. 2025;1:1. Available from: https:\/\/arxiv.org\/abs\/2507.21083"},{"key":"pdig.0001216.ref036","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1177\/16094069221110317","article-title":"The qualitative research distress protocol: a participant-centered tool for navigating distress during data collection","volume":"21","author":"C Whitney","year":"2022","journal-title":"Int J Qual Methods"},{"key":"pdig.0001216.ref037","doi-asserted-by":"crossref","DOI":"10.4135\/9781529682571","volume-title":"Qualitative content analysis in practice","author":"M Schreier","year":"2012"},{"key":"pdig.0001216.ref038","first-page":"41","article-title":"Logic and conversation.","volume-title":"Syntax and semantics. Vol 3","author":"HP. Grice","year":"1975"},{"key":"pdig.0001216.ref039","unstructured":"Kuckartz U, R\u00e4diker S. Qualitative content analysis: methods, practice and software. SAGE Publications Ltd; 2023. https:\/\/doi.org\/10.4135\/9781036212940"},{"issue":"3","key":"pdig.0001216.ref040","doi-asserted-by":"crossref","first-page":"328","DOI":"10.1080\/14780887.2020.1769238","article-title":"One size fits all? What counts as quality practice in (reflexive) thematic analysis?","volume":"18","author":"V Braun","year":"2021","journal-title":"Qual Res Psychol"},{"issue":"13","key":"pdig.0001216.ref041","doi-asserted-by":"crossref","first-page":"1753","DOI":"10.1177\/1049732315617444","article-title":"Sample size in qualitative interview studies: guided by information power","volume":"26","author":"K Malterud","year":"2016","journal-title":"Qual Health Res"},{"issue":"4","key":"pdig.0001216.ref042","doi-asserted-by":"crossref","first-page":"552","DOI":"10.1037\/h0101828","article-title":"Should participants be left to their own devices? Comparing paper and smartphone diaries in psychological research","volume":"7","author":"A Laughland","year":"2018","journal-title":"J Appl Res Mem Cogn"},{"key":"pdig.0001216.ref043","doi-asserted-by":"crossref","first-page":"94","DOI":"10.1016\/j.chb.2014.04.043","article-title":"It\u2019s only a computer: virtual humans increase willingness to disclose","volume":"37","author":"GM Lucas","year":"2014","journal-title":"Comput Hum Behav"},{"key":"pdig.0001216.ref044","unstructured":"Zhou J, et al. Instruction-following evaluation for large language models. arXiv [Preprint]; 2023. Available from: https:\/\/arxiv.org\/abs\/2311.07911"},{"key":"pdig.0001216.ref045","unstructured":"Kwan WC, Zeng X, Jiang Y, Wang Y, Li L, Shang L, et al. MT-Eval: a multi-turn capabilities evaluation benchmark for large language models. 2024;1:1. Available from: https:\/\/arxiv.org\/abs\/2401.16745"},{"key":"pdig.0001216.ref046","doi-asserted-by":"crossref","unstructured":"Chitty-Venkata KT, Raskar S, Kale B, Ferdaus F, Tanikanti A, Raffenetti K, et al. LLM-inference-bench: inference benchmarking of large language models on AI accelerators. 2024;1:1. Available from: https:\/\/arxiv.org\/abs\/2411.00136","DOI":"10.1109\/SCW63240.2024.00178"},{"key":"pdig.0001216.ref047","doi-asserted-by":"crossref","DOI":"10.4135\/9781412986120","volume-title":"The active interview","author":"JA Holstein","year":"1995"},{"issue":"3","key":"pdig.0001216.ref048","first-page":"223","article-title":"Using reflexive interviewing to foster deep understanding of research participants\u2019 perspectives","volume":"19","author":"S Pessoa","year":"2019","journal-title":"Qual Res J"},{"issue":"1","key":"pdig.0001216.ref049","doi-asserted-by":"crossref","first-page":"21582440221082124","DOI":"10.1177\/21582440221082124","article-title":"The linguistic and situational features of WhatsApp messages among high-school and university canadian students","volume":"12","author":"A Alazzawie","year":"2022","journal-title":"SAGE Open"},{"key":"pdig.0001216.ref050","doi-asserted-by":"crossref","unstructured":"Nardi BA, Whittaker S, Bradner E. Interaction and outeraction: instant messaging in action. Proc ACM Conf Comput Supported Coop Work; 2000. https:\/\/doi.org\/10.1145\/358916.358975","DOI":"10.1145\/358916.358975"},{"key":"pdig.0001216.ref051","article-title":"Ways that researchers engage in \u201ctechnological reflexivity\u201d: a meta-synthesis","volume":"31","author":"TM Paulus","year":"2024","journal-title":"Qual Res Psychol"},{"key":"pdig.0001216.ref052","doi-asserted-by":"crossref","first-page":"181","DOI":"10.1177\/10497323251401503","article-title":"The AI-Reflexivity Checklist (ARC): a pre-analysis pause for LLM-assisted coding","volume":"36","author":"A Prahl","year":"2026","journal-title":"Qual Health Res"},{"issue":"2","key":"pdig.0001216.ref053","doi-asserted-by":"crossref","first-page":"182","DOI":"10.1016\/S0197-2456(02)00320-3","article-title":"Patient compliance with paper and electronic diaries","volume":"24","author":"AA Stone","year":"2003","journal-title":"Control Clin Trials"},{"key":"pdig.0001216.ref054","doi-asserted-by":"crossref","first-page":"1503411","DOI":"10.3389\/fpsyg.2024.1503411","article-title":"Do delayed responses introduce bias in ecological momentary assessment? Evidence from comparisons between self-reported and objective physical activity","volume":"15","author":"S Schneider","year":"2025","journal-title":"Front Psychol"},{"issue":"3","key":"pdig.0001216.ref055","doi-asserted-by":"crossref","first-page":"825","DOI":"10.1177\/10731911211067538","article-title":"Ecological momentary assessment: a meta-analysis on designs, compliance and samples across research fields","volume":"30","author":"C Wrzus","year":"2022","journal-title":"Assessment"},{"key":"pdig.0001216.ref056","doi-asserted-by":"crossref","DOI":"10.2196\/43826","article-title":"Evaluating declines in compliance with ecological momentary assessment in longitudinal health behavior research: analyses from a clinical trial","volume":"25","author":"S Tonkin","year":"2023","journal-title":"J Med Internet Res"},{"issue":"11","key":"pdig.0001216.ref057","doi-asserted-by":"crossref","first-page":"526","DOI":"10.3390\/jpm15110526","article-title":"Applying ecological momentary assessment (EMA) to understand overweight and obesity: a systematic review","volume":"15","author":"G Rapelli","year":"2025","journal-title":"J Pers Med"},{"key":"pdig.0001216.ref058","article-title":"Health-related digital ecological momentary assessment in children (aged 5\u201311 years): a systematic review","volume":"28","author":"S Charitos","year":"2026","journal-title":"JMIR"}],"container-title":["PLOS Digital Health"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pdig.0001216","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,27]],"date-time":"2026-05-27T17:33:20Z","timestamp":1779903200000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pdig.0001216"}},"subtitle":[],"editor":[{"given":"Sulaf","family":"Assi","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2026,5,27]]},"references-count":58,"journal-issue":{"issue":"5","published-online":{"date-parts":[[2026,5,27]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pdig.0001216","relation":{},"ISSN":["2767-3170"],"issn-type":[{"value":"2767-3170","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,5,27]]}}}