The Personalization of Conversational Agents in Health Care: Systematic Review
Open accessPublished version of a preprint
The DOI matches its Crossref record; 64 of the 65 references it cites were found in a registry or an index; 8 of the 18 sources its claims cite were checked for support.
Abstract
BACKGROUND: The personalization of conversational agents with natural language user interfaces is seeing increasing use in health care applications, shaping the content, structure, or purpose of the dialogue between humans and conversational agents. OBJECTIVE: The goal of this systematic review was to understand the ways in which personalization has been used with conversational agents in health care and characterize the methods of its implementation. METHODS: We searched on PubMed, Embase, CINAHL, PsycInfo, and ACM Digital Library using a predefined search strategy. The studies were included if they: (1) were primary research studies that focused on consumers, caregivers, or health care professionals; (2) involved a conversational agent with an unconstrained natural language interface; (3) tested the system with human subjects; and (4) implemented personalization features. RESULTS: The search found 1958 publications. After abstract and full-text screening, 13 studies were included in the review. Common examples of personalized content included feedback, daily health reports, alerts, warnings, and recommendations. The personalization features were implemented without a theoretical framework of customization and with limited evaluation of its impact. While conversational agents with personalization features were reported to improve user satisfaction, user engagement and dialogue quality, the role of personalization in improving health outcomes was not assessed directly. CONCLUSIONS: Most of the studies in our review implemented the personalization features without theoretical or evidence-based support for them and did not leverage the recent developments in other domains of personalization. Future research could incorporate personalization as a distinct design factor with a more careful consideration of its impact on health outcomes and its implications on patient safety, privacy, and decision-making.
Overview
CoChat Summary
## TL;DR
This systematic review found only 13 health care conversational-agent studies with personalization features, and most personalized content rather than conversational style. The paper concludes that personalization was rarely theory-based or directly evaluated for health outcomes.
## Key findings
- The search identified 1958 publications in total; after screening, 13 studies were included.
- Personalization was most often used for content delivery: feedback, daily health reports, alerts, warnings, recommendations, reminders, multimedia, and personalized questions.
- Across the 13 studies, 8 supported patients and 5 supported both patients and clinicians; all used individuated personalization, and 1 study also used categorical personalization for novice vs expert users.
- Only 2 studies directly assessed personalization itself; one reported that 85% (29/34) found tailored feedback helpful, and another rated customized feedback 0.3 on a –2 to +2 Likert scale as the most successful feature.
## Methods
- Systematic review of health care conversational agents with unconstrained natural language input and personalization features.
- Searched PubMed, Embase, CINAHL, PsycInfo, and ACM Digital Library in March 2019, with no publication-year or language restriction.
- Included primary studies on consumers, caregivers, or health care professionals that tested a conversational agent with human users and implemented personalization; screening/data extraction were done independently by two researchers, with Cohen kappa used for agreement.
## Limitations
- The authors state the results are limited by how much the included studies reported their personalization features.
- The review focused only on CAs with unconstrained natural language input, so the findings may not extend to constrained systems; this is stated in the paper.
- Evident from the text: outcomes in the included studies were often attributable to the overall system rather than personalization alone, making it hard to isolate personalization effects.
Model-written summary. Check it against the paper before relying on it.
Integrity signals
Registry
Cites
Statistics
Figures
Verification
Claims the paper makes
5 Valid · 0 Not valid · 6 Not checked · 32 Own results and interpretations
The cited sources support only part of this claim — read each source’s verdict below.
In the paper
“The effects of personalization have been evaluated in various ways by measuring aspects like efficiency in terms of the number and duration of interactions [11,20], user satisfaction, relevance, and understandability [20], information quality presented [21], and appropriateness of system responses [10].”
§ The Personalization of Conversational Agents in Health Care: Systematic Review > Introduction > Personalization in Conversational Agents
What the sources say
- Partly supportedcites [11] sourceExperimental — accuracy not yet measured
Thompson et al. (2004) do evaluate personalization by measuring efficiency — 'the average number of interactions needed to find a restaurant accepted by the user' and 'the time taken for each conversation' (4.1 Experimental Variables, p. 18) — and user satisfaction, via rejection rate, hit rate (the percentage of conversations in which the first item presented was acceptable, i.e. a relevance-style measure) and a post-study questionnaire (4.1, p. 18; Appendix A, p. 29). However, our copy contains no measure of 'understandability' or of 'information quality presented'; appropriateness appears only as a general goal of personalization ('to increase the quality and appropriateness of both the interaction and the result(s)', 2.1 Personalization, p. 3), not as an evaluated dimension. So the list of six evaluation aspects exceeds what this single source reports. (LLM, conf=0.78)
- Supportedcites [20] source
Section 6 (Evaluation II—User Interaction Study) says the paper measured efficiency by dialog duration and also assessed user satisfaction. The User Satisfaction Ratings and Results sections report measures of relevance and understandability. Information quality and response appropriateness are attached to other citations in the citing sentence, not to this paper. (LLM, conf=0.92)
- Supportedcites [21] source
In §5.1 (Experimental design for tailoring and mode experiment) our copy defines and elicits a five-point Likert judgement of the informativeness/'information quality' of tailored system utterances, recorded as the measure InformationQuality, and §5.2 reports the tailoring result on that measure (paired t-test, t(383)=1.76, P<.05). The citation [21] in the printed sentence is attached specifically to 'information quality presented', which is exactly this paper's evaluation variable; the other listed aspects (efficiency, satisfaction, appropriateness) are credited to different citations, and §6 indeed notes task completion, time and user satisfaction as future work rather than measures here, so nothing attributed to this source is unsupported. (LLM, conf=0.90)
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Partly supported
Every source the paper cites for this claim was checked and supports it.
In the paper
“Learning from a history of previous conversations plays a key role in ensuring the continuity of health communications that take place over multiple interactions over time [31].”
§ The Personalization of Conversational Agents in Health Care: Systematic Review > Introduction > Personalization in Health Care and Medicine
What the sources say
- Supportedcites [31] source
Section 3.3, “Continuity over multiple interactions,” says that health communication applications require repeated interactions over time and must retain information between sessions so later dialog can be tailored to earlier conversations. This supports the claim’s paraphrase about using conversation history to maintain continuity. (LLM, conf=0.93)
plainstates a cause- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Supported
Every source the paper cites for this claim was checked and supports it.
In the paper
“Using CAs with unconstrained natural language input can be risky [66].”
§ The Personalization of Conversational Agents in Health Care: Systematic Review > Discussion > Principal Results
What the sources say
- Supportedcites [66] source
The Discussion’s Principal Findings say that patients and consumers should not rely on conversational assistants using unconstrained natural language input for actionable medical advice, because responses could lead to harm. The claim accurately conveys that risk, though the paper examines medical-information use specifically. (LLM, conf=0.93)
plainstates a possible cause- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Supported
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“The use of CAs with unconstrained language input in health care is still limited, but there has been a notable increase in the number of studies in recent years.”
§ The Personalization of Conversational Agents in Health Care: Systematic Review > Discussion > Principal Results
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“The personalization features were implemented without a theoretical framework of customization and with limited evaluation of its impact.”
- Also stated in: § Conclusions · plain
“While the CAs with personalization features were reported to improve user satisfaction, user engagement, and dialogue quality, little evaluation was performed to measure the extent of personalization and its role in improving health outcomes.”
§ The Personalization of Conversational Agents in Health Care: Systematic Review > Abstract > Results
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Also stated in: § Conclusions · plain
26 more claims
Create a free account to see all 43 claims and to verify the 1 reference still open.
- It may state two separate claims as one. 6
- Probably not a substantial claim. 6
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
The source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“Existing reviews on conversational agents focus on a certain subtype of agents such as virtual coaches [31-33] or embodied conversational agents (ECAs) [34] or on specific functionalities of these agents such as behavior change [35] or mental health applications [36,37].”
From Conversational Agents in Health Care: Scoping Review and Conceptual Analysis (2020) · cites this paper as [33]
Experimental — accuracy not yet measuredThe source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“In mental health CAs, the use of user profiles or user models to support personalized and adaptive features and the assessment of personalization is still in its infancy [79].”
From Conversational Agent Interventions for Mental Health Problems: Systematic Review and Meta-analysis of Randomized Controlled Trials (2023) · cites this paper as [79]
Experimental — accuracy not yet measuredThe cited source says what the claim attributes to it.
In the citing paper
“Other recent reviews focused on conversational agents for either a specific health condition such as mental health [44], the general application of chatbots in health care [1], or specific features thereof such as personalization [45] or technical architectures [11].”
From Artificial Intelligence-Based Conversational Agents for Chronic Conditions: Systematic Literature Review (2020) · cites this paper as [45]
The cited source says what the claim attributes to it.
In the citing paper
“Despite the large body of research concerning the application of conversational agents in health care, most reviews have limited their focus to a particular health area, agent type, or function [10,19-22].”
From The Effectiveness of Artificial Intelligence Conversational Agents in Health Care: Systematic Review (2020) · cites this paper as [10]
The cited source says what the claim attributes to it.
In the citing paper
“Personalization of conversational agents has documented benefits60, but there is a growing concern about the harms posed by the anthropomorphization of AI.”
From A psychometric framework for evaluating and shaping personality traits in large language models (2025) · cites this paper as [60]
4 more claims about this paper
Create a free account to see every claim other papers make about this one.
Citations
Cites
The theory of planned behavior
Ajzen, I. (1991) · Organizational Behavior and Human Decision Processes · doi:10.1016/0749-5978(91)90020-t · Cited by 90,587 · cited 1×
“Moreover, other theories not specific to personalization may prove useful for personalization purposes, such as the Theory of Planned Behavior [71].”
BackgroundThe PHQ-9: Validity of a brief depression severity measure
Kroenke, K., Spitzer, R. L., & Williams, J. B. W. (2001) · Journal of General Internal Medicine · doi:10.1046/j.1525-1497.2001.016009606.x · Cited by 44,910 · cited 1×
“03) and significant differences in the posi• Questionnaires to measure depression (PHQ-9a) [48], anxiety (GAD-7b) [49], and affect • To improve depression and anxiety symptoms • To provide more engaging and convenient user experitive and negative affects (P=.”
BackgroundDevelopment and validation of brief measures of positive and negative affect: The PANAS scales.
Watson, D., Clark, L. A., & Tellegen, A. (1988) · Journal of Personality and Social Psychology · doi:10.1037/0022-3514.54.6.1063 · Cited by 32,433
A Brief Measure for Assessing Generalized Anxiety Disorder: The GAD-7
Spitzer, R. L., Kroenke, K., Williams, J. B. W., & Löwe, B. (2006) · Archives of Internal Medicine · doi:10.1001/archinte.166.10.1092 · Cited by 31,765 · cited 1×
“03) and significant differences in the posi• Questionnaires to measure depression (PHQ-9a) [48], anxiety (GAD-7b) [49], and affect • To improve depression and anxiety symptoms • To provide more engaging and convenient user experitive and negative affects (P=.”
BackgroundFitzpatrick, K. K., Darcy, A., & Vierhile, M. (2017) · JMIR Mental Health · doi:10.2196/mental.7785 · Cited by 2,730 · cited 7×
“Information needed for personalization was provided explicitly by the users in seven studies [35,37-40, 44, 45], and obtained implicitly by the system in one study [36]”
BackgroundMethodInfluentialReferring as a collaborative process
Clark, H. H., & Wilkes-Gibbs, D. (1986) · Cognition · doi:10.1016/0010-0277(86)90010-7 · Cited by 2,401 · cited 1×
“Personalized and adaptive system behavior in conversational systems can improve user comprehension [16], user satisfaction [17], task efficiency [18], and the likelihood of behavior change [19].”
BackgroundDoes tailoring matter? Meta-analytic review of tailored print health behavior change interventions
Noar, S. M., Benac, C. N., & Harris, M. S. (2007) · Psychological Bulletin · doi:10.1037/0033-2909.133.4.673 · Cited by 2,136 · cited 1×
“Studies of personalization in health care and medicine have been increasing in number since the early 2000s [22], with growing evidence showing their effectiveness [23-26].”
BackgroundMeasuring mindfulness—The Freiburg Mindfulness Inventory (FMI)
Walach, H., Buchheld, N., Buttenmüller, V., Kleinknecht, N., & Schmidt, S. (2006) · Personality and Individual Differences · doi:10.1016/j.paid.2005.11.025 · Cited by 1,475 · cited 1×
“07; sm) • Questionnaires to measure health awareness [51], mindfulness (FMIg) [52], and reflection • To trigger deeper reflection, which would increase motivation, empowerment, and adoption of new behavior • Prolonged use of CA (additional two weeks) by half of the participants (16/33) with an avg (RQh) [53] of 98.”
BackgroundConversational agents in healthcare: a systematic review
Laranjo, L., Dunn, A. G., Tong, H. L., Kocaballi, A. B., Chen, J., Bashir, R., Surian, D., Gallego, B., Magrabi, F., Lau, A. Y. S., et al. (2018) · Journal of the American Medical Informatics Association · doi:10.1093/jamia/ocy072 · Cited by 1,388 · cited 1×
“A recent systematic review in this area examined technical performance, user experience, and health-related outcomes and found that most studies had not employed standardized evaluation methods or had failed to address aspects of patient safety [2].”
BackgroundSelf-citationThe filter bubble: how the new personalized web is changing what we read and how we think
(2012) · Choice Reviews Online · doi:10.5860/choice.50-0926 · Cited by 1,319 · cited 1×
“For example, a recent research paper drew attention to the limitations of implicit and explicit personalization [61]: while implicit personalization with its often-imperceptible user models and hidden assumptions can result in biased decision-making [62], over-reliance on system suggestions [63], and filter bubbles [6…”
Background
Research works printed but not linked: 8
- Cambridge dictionaries online20152019-09-16Cambridge University Presshttp://dictionary.cambridge.org
- Coiera, E, 2012, Yearb Med Inform, 7, 4
- Radziwill, NM, 2017, arXiv preprint, 1
- 10.2196/jmir.8.4.e30 · DOI · Paper page
- Azzini, I, 2003, Stud Health Technol Inform, 95, 146
- Chu-CarrollJNickersonJSEvaluating automatic dialogue strategy adaptation for a spoken dialogue system2000North American Chapter of the Association for Computational Linguistics ConferenceApril 29 - May 04, 2000Seattle, WashingtonAssociation for Computational Linguistics202209
- Carr, N, 2015, The glass cage: Where automation is taking us
- 10.1007/s10916-019-1237-1 · DOI · Paper page
Cited by
Items 301–325 of 325
Evaluating Chatbots as Nursing Assistants in Palliative Care: A Narrative Review
Dehnayebi, M. J., Etedali, M., Safarabadi, M., Parnikh, H., & Talebi, H. M. (2026) · Indian Journal of Palliative Care · doi:10.25259/ijpc_144_2025 · Cited by 2
“[33] A 2020 Journal of Medical Internet Research (JMIR) review reported mixed evidence on usability and effectiveness across 31 conversational agents, stressing the need for standardised outcome measures and health-economic evaluations.”
Relational Mediators: LLM Chatbots as Boundary Objects in Psychotherapy CSCW033
Quan, J., Li, Z., Zhu, T. Q., Li, Y., Wang, B., Pratt, W., & Gao, N. (2026) · Proceedings of the ACM on Human-Computer Interaction · doi:10.1145/3788069 · Cited by 3
“• Personalization : Embodies the plasticity principle by allowing the system to adapt its mediating approach to different cultural contexts and communication styles [27].”
Designing AI-Based Entrepreneurial Coaching Systems
Liebschner, J., Heinz, D., & Satzger, G. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-28313-9_2
Akoglu, B., & Şimşek, A. (2026) · Journal of Nursing Management · doi:10.1155/jonm/7878494
Tojib, D., Abdi, E., & Tian, L. (2026) · International Journal of Social Robotics · doi:10.1007/s12369-026-01406-x
“Similarly, games designed for behavioural change are more effective if they are tailored to the player’s person - ality type [ 42], and personalisation features improved user engagement and interaction quality [ 33].”
Do Not Think Ahead of Me: High‐Personalization Chatbots Can Backfire During the Goal Formation Stage
Chen, X., Huang, M., & Xie, X. (2026) · Psychology and Marketing · doi:10.1002/mar.70189
Kim, Y., Hong, J., & Lee, S. (2026) · International Journal of Human-Computer Interaction · doi:10.1080/10447318.2026.2678531 · Cited by 1
Optimizing Mental-Health Support via Context-Sensitive Conversational AI
Zhang, Y., & Ali, W. (2025) · doi:10.1109/ccat68690.2025.00036
“The user’s subsequent answer now informed by reflection feeds into Nuna’s existing pipeline [5].”
InfluentialAUTOMED: A Finite Automata-Based Framework for Health Misinformation Detection in Medical Chatbots
Postiglione, A., & Nota, G. (2026) · Lecture notes on data engineering and communications technologies · doi:10.1007/978-3-032-23347-9_30
Patient-Engaged AI: The Nursing Path to Health Equity
Milo, R. B., Etland, C., Martínez, N., Scott, S., Leon, C. D., Calero, P., Nibbelink, C. W., Georges, J. M., & Connelly, C. D. (2026) · SAGE Open Nursing · doi:10.1177/23779608261466379
“Limitations include reliance on evidence primarily from Western or developed nations, an overrepresentation of systematic reviews on CAs, heterogeneous study designs, and a disproportionate focus on the most populous groups across racial, ethnic, and social perspectives.”
InfluentialAssessing Mental Health Therapeutic Capacity in AI Agents
Maruotti, P., Rampazzo, M., Muñoz, S., Dragoni, M., & Bellan, P. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-30710-1_46
Abesadze, N., Fernandes, A., & Rubin, E. (2026) · Cureus · doi:10.7759/cureus.112306
“Conversational AI has also shown promise in psychoeducation, digital mental health interventions, and improving access to supportive health information, particularly when used with appropriate safeguards and clinical oversight [4,5].”
Zhou, H., Skalski-Fouts, Z., Nguyen, L., Rivera, C., Spring, B., Miao, H., & Zhang, X. (2026) · Smart Health · doi:10.1016/j.smhl.2026.100694
Leite, M. V., Abe, J. M., dos Santos, J. G. B., Thomas, L. C. D. S., & Souza, M. L. H. (2026) · Advances in sustainability science and technology · doi:10.1007/978-3-032-25267-8_12
Mahmud, R., Berkovsky, S., Prasad, M., & Kocaballi, A. B. (2026) · ACM Transactions on Recommender Systems · doi:10.1145/3838803 · Cited by 1
“2 These findings echo broader work in conversational systems, where users frequently prefer to retain initiative in information-rich interactions [69, 70, 71].”
Self-citationConversational Pharmacovigilance That Preserves the Patient’s Narrative
Bennett, O., Collins, H., Foster, J., & Wright, E. (2026) · Archives of Pharmacy Practice · doi:10.51847/hsmlawfbcn
Kandasamy, G., Orayj, K. M., Asiri, R., Alshahrani, A. M., Alharbi, G., Abutaily, S. A., Suhaym, A. Y. A., & Alyahya, A. A. (2026) · Frontiers in Public Health · doi:10.3389/fpubh.2026.1862006
Siefert, C. J., Dauphin, B., Slavin‐Mulford, J. M., Mukkamala, S. D. K., Tatipally, V. A. R., Alsaid, A., & Chehade, A. (2026) · Frontiers in Digital Health · doi:10.3389/fdgth.2026.1762253
Aboulqassim, N. S. S., shennib, A. K., alkremy, M. S., fathallah, L., alhamar, E. M., & almajry, M. A. (2026) · Derna Academy Journal for Applied Sciences · doi:10.71147/bgkxz309
Ong, R. H. S., Oh, H. C., Choo, B. P., Tan, L. Z. A., Gunn, M. H. W., Ng, J. W., Teng, A. C. C., Ong, S. Y. B., Ng, A. H. K., Soo, W. Y. L., et al. (2026) · Journal of Medical Internet Research · doi:10.2196/91058
Zhou, C., Wu, H., Li, G., & CHEN, Y. (2026) · Frontiers in Psychology · doi:10.3389/fpsyg.2026.1915597
Hassan, R., & Fathy, D. (2026) · Journal of Health Informatics and Digital Systems · doi:10.68159/a002740697
Gu, C., Sun, Y., Chen, Z., Wang, Z., Li, Y., Chen, K., Lu, F., Chen, Y., & Zhen, Y. (2026) · Proceedings of the ACM on Interactive Mobile Wearable and Ubiquitous Technologies · doi:10.1145/3832031 · Cited by 1
“Inspired by chatbots, researchers have developed conversational agents (CAs) to administer assessments via text or voice [38].”
Munz, L., Kirschbaum, A., Kania, C. J., Fellerhoff, T., & Richert, A. (2026) · Companion Publication of the 28th International Conference on Multimodal Interaction · doi:10.1145/3776591.3836731 · Cited by 1
“Reviews report weak theoretical grounding, limited direct evaluation of personalization effects, uneven implementation of adaptive dialogue, and limited integration of user characteristics and medical records [30, 39, 56].”
Rutan, R., Bravo, M. Á., Monteverde, C., Lafler, R. P., Biggs, T. W., Sales, F. D., Solorio, A., Toji-Ruiz, B., & Shen, S. S. P. (2026) · Climate Services · doi:10.1016/j.cliser.2026.100736 · Cited by 1
Metadata
- Authors
- Kocaballi, A. B., Berkovsky, S., Quiroz, J. C., Laranjo, L., Tong, H. L., Rezazadegan, D., Briatore, A., & Coiera, E.
- Affiliations
- Macquarie University (AU)
- Ministerio de Salud (AR)
- Corresponding author
- Kocaballi, Ahmet Baki
- ORCID
- Venue
- Journal of Medical Internet Research
- Publisher
- JMIR Publications Inc.
- Published
- 2019-11-07
- Volume
- 21
- Issue
- 11
- Pages
- e15360
- ISSN
- 1438-8871 (ISSN-L)
- PMC
- PMC6873147
- OpenAlex
- W2972203331
- Semantic Scholar
- c99dffde110ac8a193caa027af1172372a92e896
- Cited by
- 332
- References
- 65
- Citations by year
- 2026: 57 · 2025: 64 · 2024: 47 · 2023: 56 · 2022: 38 · 2021: 48 · 2020: 21 · 2019: 1
- FWCI
- 1.30
- Type
- journal article
- Language
- en
- Open access
- gold
- doi.org
- Licence
- cc-by
- Locations
- Journal of Medical Internet Research (publishedVersion, cc-by)
- PubMed Central (publishedVersion, cc-by)
- PubMed (publishedVersion)
- DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
- Swinburne figshare (Swinburne University of Technology) (submittedVersion, other-oa)
- Greater South Information System
- Funders
- Directorate for Computer and Information Science and Engineering
- Medical Research Council
- National Health and Medical Research Council (1134919)
- Topics
- Health Sciences › Medicine › Health Informatics › Artificial Intelligence in Healthcare and Education
- Health Sciences › Health Professions › General Health Professions › Mobile Health and mHealth Applications
- Physical Sciences › Computer Science › Artificial Intelligence › Speech and dialogue systems
- Keywords
- chatbots, personalization, health care, natural language interfaces, personalized feedback, user satisfaction, user engagement, dialogue quality, patient safety, privacy, decision support
- MeSH terms
- Delivery of Health Care, Humans, Precision Medicine
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
The claim verdicts this report counts are experimental: their accuracy is not yet measured.
A language model drew the claims from the paper on 2026-10-10, under version 3 of the claim definition (model deepseek-v4.1-flash, prompt extract-v3).
A second model labelled each claim on 2026-10-10 (model jev-1.13-20260917, definition revision gold-guideline-v0.2).
Cited sources are checked with a language model’s help (qwen3.8-omni-flash and gpt-6-sol).
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.
