{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,30]],"date-time":"2026-09-30T06:55:36Z","timestamp":1790751336109,"version":"4.1.0"},"reference-count":41,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,9,30]],"date-time":"2026-09-30T00:00:00Z","timestamp":1790726400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Public Health"],"abstract":"<jats:sec>\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>Office workers accumulate most of their waking h in sedentary behavior, yet scalable personalized occupational-health advice remains limited, and the quality of large language model (LLM)-based tools in this domain has not been rigorously examined.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Objective<\/jats:title>\n                    <jats:p>This study evaluated whether a domain-specialized chatbot system for providing health advice on sedentary behavior, integrating retrieval augmentation, a curated corpus, and safety guardrails, performs better than a general-purpose LLM and static educational materials.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>A sequential explanatory mixed-methods design was used. In the blinded expert evaluation, nine raters independently rated 60 responses across five quality dimensions. In the user survey, 654 eligible Chinese office workers interacted with the specialized chatbot and completed six perception scales (two adapted from established technology-acceptance frameworks and four developed for this study) plus open-ended feedback.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>Inter-rater reliability was good for the composite score; in a case-level safety screen, no response from the specialized chatbot or the standard materials was flagged as potentially unsafe, whereas two Doubao responses were flagged by two or more raters. The specialized chatbot achieved the highest composite rating, followed by Doubao and standard materials. In a linear mixed-effects model and crossed random intercepts for rater and question, all Holm-adjusted pairwise contrasts were significant. Advantages of the specialized chatbot over Doubao were most pronounced on safety in symptom-management and special-population items. Among users, perceived ease of use was highest, whereas perceived safety and intention to use were rated comparatively lower. Frequent prior AI-chatbot use was associated with higher ratings on all six scales; after covariate adjustment the association persisted for five of the six scales but was attenuated and no longer significant for perceived safety.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>The specialized chatbot system received expert-rated accuracy and safety scores that did not differ significantly from standard educational materials, but exceeded standard materials on usefulness, comprehensibility, and completeness, and outperformed the general-purpose LLM on accuracy, safety, completeness, and the overall composite score. These findings concern response quality and immediate user perceptions, not behavioral or clinical outcomes. Nonetheless, users remained cautious about safety and intention to use after this brief exposure.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.3389\/fpubh.2026.1965655","type":"journal-article","created":{"date-parts":[[2026,9,30]],"date-time":"2026-09-30T06:01:38Z","timestamp":1790748098000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Evaluating AI chatbots for providing health advice on occupational sedentary behavior in the workplace"],"prefix":"10.3389","volume":"14","author":[{"given":"Jingwei","family":"Zhang","sequence":"first","affiliation":[{"name":"Jiangsu Vocational College of Finance and Economics","place":["Huai'an, Jiangsu, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2026,9,30]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","first-page":"629","DOI":"10.9734\/jsrr\/2025\/v31i113696","article-title":"Occupational sedentary behaviour and health risks among Nigerian office workers: implications for sitting-time reduction interventions","volume":"31","author":"Adeleye","year":"2025","journal-title":"J Sci Res Rep."},{"key":"B2","doi-asserted-by":"publisher","DOI":"10.2196\/59943","article-title":"Effectiveness of digital health interventions on sedentary behavior among patients with chronic diseases: systematic review and meta-analysis","author":"Zhang","year":"2025","journal-title":"JMIR Mhealth Uhealth"},{"key":"B3","doi-asserted-by":"publisher","DOI":"10.1145\/3240925.3240962","article-title":"Supporting action planning for sedentary behavior change by visualizing personal mobility patterns on smartphone","author":"Wang","year":"2018","journal-title":"Pervasive Computing Technologies for Healthcare."},{"key":"B4","doi-asserted-by":"publisher","first-page":"607","DOI":"10.1186\/s13063-022-06528-x","article-title":"Health effects of reduced occupational sedentary behaviour in type 2 diabetes using a mobile health intervention: a study protocol for a 12-month randomized controlled trial-the ROSEBUD study","volume":"23","author":"Syrj\u00e4l\u00e4","year":"2022","journal-title":"Trials."},{"key":"B5","doi-asserted-by":"publisher","first-page":"156","DOI":"10.62381\/P263421","article-title":"A study on the analysis of \u201csedentary behavior combined with late-night studying\u201d among college students and health interventions","volume":"3","author":"Liang","year":"2026","journal-title":"Philos Soc Sci."},{"key":"B6","doi-asserted-by":"publisher","first-page":"278","DOI":"10.4103\/jehp.jehp_1442_24","article-title":"Associations between cognitive function and vascular health in office-based sedentary workers: a six-month yoga intervention","volume":"14","author":"Shruthi","year":"2025","journal-title":"J Educ Health Promot."},{"key":"B7","doi-asserted-by":"publisher","first-page":"S111","DOI":"10.1097\/SAP.0000000000004640","article-title":"Development and assessment of a custom GPT-4o chatbot for postoperative counseling and frequently asked questions in breast surgery patients","volume":"96","author":"Claudy","year":"2026","journal-title":"Ann Plast Surg."},{"key":"B8","doi-asserted-by":"publisher","first-page":"31","DOI":"10.1186\/s12894-025-02033-w","article-title":"Readability and quality assessment of AI-powered chatbot responses to overactive bladder patient questions: a comparative study","volume":"26","author":"Deger","year":"2026","journal-title":"BMC Urol."},{"key":"B9","doi-asserted-by":"publisher","first-page":"389","DOI":"10.1370\/afm.250386","article-title":"CHART Collaborative. Reporting guideline for chatbot health advice studies: chatbot assessment reporting tool (CHART) statement","volume":"23","author":"Huo","year":"2025","journal-title":"Ann Fam Med."},{"key":"B10","doi-asserted-by":"publisher","first-page":"844","DOI":"10.1007\/s12539-025-00715-5","article-title":"CMedRAGBot: a Chinese medical chatbot based on graph RAG and large language models","volume":"17","author":"Zhang","year":"2025","journal-title":"Interdiscip Sci Comput Life Sci."},{"key":"B11","doi-asserted-by":"publisher","first-page":"1683322","DOI":"10.3389\/frai.2025.1683322","article-title":"AI for evidence-based treatment recommendation in oncology: a blinded evaluation of large language models and agentic workflows","volume":"8","author":"Zhai","year":"2025","journal-title":"Front Artif Intell."},{"key":"B12","doi-asserted-by":"publisher","first-page":"1","DOI":"10.32188\/ijiar.3.1_1","article-title":"Security design and evaluation of a citizen-oriented generative AI chatbot using RAG (retrieval-augmented generation)","volume":"3","author":"Kamata","year":"2026","journal-title":"Int J ICT Appl Res."},{"key":"B13","doi-asserted-by":"publisher","first-page":"1435329","DOI":"10.3389\/fpubh.2024.1435329","article-title":"Understanding older adults' acceptance of chatbots in healthcare delivery: an extended UTAUT model","volume":"12","author":"Yu","year":"2024","journal-title":"Front Public Health."},{"key":"B14","doi-asserted-by":"publisher","DOI":"10.2196\/46548","article-title":"Factors influencing the acceptability, acceptance, and adoption of conversational agents in health care: integrative review","author":"Wutz","year":"2023","journal-title":"J Med Internet Res."},{"key":"B15","doi-asserted-by":"publisher","first-page":"437","DOI":"10.12944\/CRNFSJ.6.2.18","article-title":"Perceived barriers of young adults for participation in physical activity","volume":"6","author":"Anjali","year":"2018","journal-title":"Curr Res Nutr Food Sci J."},{"key":"B16","doi-asserted-by":"publisher","first-page":"31","DOI":"10.1186\/s12905-025-04202-3","article-title":"From needs assessment to usability testing: evaluating the AinoAid chatbot for domestic violence support","volume":"26","author":"Vogt","year":"2025","journal-title":"BMC Womens Health."},{"key":"B17","doi-asserted-by":"publisher","DOI":"10.1093\/jamia\/ocy072","article-title":"Conversational agents in healthcare: a systematic review","author":"Laranjo","year":"2018","journal-title":"J Am Med Inform Assoc."},{"key":"B18","doi-asserted-by":"publisher","first-page":"e20346","DOI":"10.2196\/20346","article-title":"The effectiveness of artificial intelligence conversational agents in health care: systematic review","volume":"22","author":"Milne-Ives","year":"2020","journal-title":"J Med Internet Res."},{"key":"B19","doi-asserted-by":"publisher","first-page":"719","DOI":"10.1002\/jso.27966","article-title":"Assessment of artificial intelligence chatbot responses to common patient questions on bone sarcoma","volume":"131","author":"Khabaz","year":"2024","journal-title":"J Surg Oncol."},{"key":"B20","doi-asserted-by":"publisher","first-page":"107237","DOI":"10.1016\/j.nedt.2026.107237","article-title":"Dynamic changes and relationships among AI literacy, job crafting, and career growth in new nurses in the AI era: a multicenter three-wave longitudinal study","volume":"167","author":"Liu","year":"2026","journal-title":"Nurse Educ Today."},{"key":"B21","doi-asserted-by":"publisher","first-page":"100910","DOI":"10.1016\/j.landig.2025.100910","article-title":"How CHART (chatbot assessment reporting tool) can help to advance clinical artificial intelligence research through clearer task definition and robust validation","volume":"7","author":"Thirunavukarasu","year":"2025","journal-title":"Lancet Digit Health."},{"key":"B22","doi-asserted-by":"publisher","first-page":"znaf142","DOI":"10.1093\/bjs\/znaf142","article-title":"Reporting guideline for chatbot health advice studies: the chatbot assessment reporting tool (CHART) statement","volume":"112","author":"CHART","year":"2025","journal-title":"Br J Surg."},{"key":"B23","doi-asserted-by":"publisher","first-page":"110","DOI":"10.1186\/s12966-024-01661-z","article-title":"\u201cBalancing work and movement\u201d: barriers and enablers for being physically active at Indian workplaces\u2013findings from SMART STEP trial","volume":"21","author":"Chandrasekaran","year":"2024","journal-title":"Int J Behav Nutr Phys Act."},{"key":"B24","article-title":"WHO. Guidelines On Physical Activity And Sedentary Behaviour","year":"2020"},{"key":"B25","doi-asserted-by":"publisher","first-page":"20552076261481633","DOI":"10.1177\/20552076261481633","article-title":"Playing for better health: gamification in digital workplace health promotion\u2013a structured review of design elements, outcomes, and mechanisms from a self-determination theory perspective","volume":"12","author":"Hall","year":"2026","journal-title":"Digit Health."},{"key":"B26","doi-asserted-by":"publisher","first-page":"158","DOI":"10.3390\/ijerph17010158","article-title":"Temporal trends and recent correlates in sedentary behaviors among Chinese adults from 2002 to 2010\u20132012","volume":"17","author":"Ding","year":"2020","journal-title":"Int J Environ Res Public Health."},{"key":"B27","doi-asserted-by":"publisher","first-page":"1629149","DOI":"10.3389\/frai.2025.1629149","article-title":"Li F. Evaluation of the accuracy and repeatability of Deepseek V3, Doubao, and Kimi15 in answering knowledge-related queries about chronic non-bacterial osteitis","volume":"8","author":"Zhu","year":"2025","journal-title":"Front Artif Intell."},{"key":"B28","doi-asserted-by":"publisher","DOI":"10.2196\/70074","article-title":"Short-term effects of an mHealth intervention on healthy behaviors and cardiometabolic health in sedentary employees: quasi-experimental study","author":"Lin","year":"2026","journal-title":"JMIR Mhealth Uhealth"},{"key":"B29","doi-asserted-by":"publisher","first-page":"2055207619839883","DOI":"10.1177\/2055207619839883","article-title":"Mobile health interventions to promote physical activity and reduce sedentary behaviour in the workplace: a systematic review","volume":"5","author":"Buckingham","year":"2019","journal-title":"Digit Health."},{"key":"B30","doi-asserted-by":"publisher","first-page":"434","DOI":"10.1016\/j.pcd.2025.05.010","article-title":"Impact of a primary care-based mobile health intervention to \u201csit less and move more\u201d on HbA1c, blood pressure, and other clinical outcomes in office employees with type 2 diabetes: a randomized controlled trial","volume":"19","author":"Al\u00f2s","year":"2025","journal-title":"Prim Care Diabetes."},{"key":"B31","doi-asserted-by":"publisher","first-page":"106311","DOI":"10.1016\/j.cct.2021.106311","article-title":"The active workplace study: protocol for a randomized controlled trial with sedentary workers","volume":"103","author":"Wipfli","year":"2021","journal-title":"Contemp Clin Trials."},{"key":"B32","doi-asserted-by":"publisher","first-page":"207","DOI":"10.1038\/s41746-025-01578-2","article-title":"An umbrella review of efficacy of digital health interventions for workers","volume":"8","author":"Iwakura","year":"2025","journal-title":"npj Digit Med."},{"key":"B33","doi-asserted-by":"publisher","first-page":"141","DOI":"10.1007\/s10916-025-02284-y","article-title":"Diagnosis and triage performance of contemporary large language models on short clinical vignettes","volume":"49","author":"Xu","year":"2025","journal-title":"J Med Syst."},{"key":"B34","doi-asserted-by":"publisher","DOI":"10.1093\/fampra\/cmaf087","article-title":"Evaluating large language models for specialist referral triage in primary care: a quantitative study using otolaryngology scenarios","author":"Hack","year":"2025","journal-title":"Fam Pract."},{"key":"B35","doi-asserted-by":"publisher","first-page":"605","DOI":"10.1038\/s41746-025-02008-z","article-title":"When helpfulness backfires: LLMs and the risk of false medical information due to sycophantic behavior","volume":"8","author":"Chen","year":"2025","journal-title":"NPJ Digit Med."},{"key":"B36","doi-asserted-by":"publisher","first-page":"e55648","DOI":"10.2196\/55648","article-title":"Accuracy of a commercial large language model (ChatGPT) to perform disaster triage of simulated patients using the simple triage and rapid treatment (START) protocol: gage repeatability and reproducibility study","volume":"26","author":"Franc","year":"2024","journal-title":"J Med Internet Res."},{"key":"B37","doi-asserted-by":"publisher","DOI":"10.2196\/43592","article-title":"Designing a dyad-based digital health intervention to reduce sedentary time in Black breast cancer survivors and their first-degree relatives: human-centered design study","author":"Blazey","year":"2023","journal-title":"JMIR Form Res."},{"key":"B38","doi-asserted-by":"publisher","first-page":"2705006","DOI":"10.1080\/21645515.2026.2705006","article-title":"Motivators and barriers to influenza vaccination among healthcare workers","volume":"22","author":"Al-Hamdan","year":"2026","journal-title":"Hum Vaccin Immunother."},{"key":"B39","doi-asserted-by":"publisher","first-page":"1126","DOI":"10.1177\/08977151251401539","article-title":"Artificial intelligence chatbot responses to patient queries on traumatic brain injury: an expert assessment of reliability and accuracy","volume":"43","author":"Schuss","year":"2025","journal-title":"J Neurotrauma."},{"key":"B40","doi-asserted-by":"publisher","first-page":"102025","DOI":"10.1016\/j.ajpe.2026.102025","article-title":"Rest as strategy: the importance of psychological detachment from work for sustained career productivity","volume":"90","author":"Cain","year":"2026","journal-title":"Am J Pharm Educ."},{"key":"B41","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1108\/TQM-10-2024-0394","article-title":"AI chatbots for healthcare maintenance: transforming total productive maintenance in the Industry 5.0 era","author":"Mahfoud","year":"2025","journal-title":"TQM .J."}],"container-title":["Frontiers in Public Health"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fpubh.2026.1965655\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,30]],"date-time":"2026-09-30T06:01:40Z","timestamp":1790748100000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fpubh.2026.1965655\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9,30]]},"references-count":41,"alternative-id":["10.3389\/fpubh.2026.1965655"],"URL":"https:\/\/doi.org\/10.3389\/fpubh.2026.1965655","relation":{},"ISSN":["2296-2565"],"issn-type":[{"value":"2296-2565","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,9,30]]},"article-number":"1965655"}}