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 201–300 of 325
MyndFood: a conversational agent for enhancing the cooking and eating experience
Parra, M. O., Favela, J., & Castro, L. A. (2025) · Frontiers in Computer Science · doi:10.3389/fcomp.2025.1566940 · Cited by 3
Dolman, A. J., Kaliappan, S., Zhou, Y., Palleti, D., Marquard, J. L., Lee, S. I., Karkar, R., & Jimison, H. B. (2025) · Innovation in Aging · doi:10.1093/geroni/igaf106 · Cited by 5
Designing Around Stigma: Human-Centered LLMs for Menstrual Health
Shahnawaz, A., Shafique, A., Wang, D., & Mustafa, M. (2026) · CHI Conference on Human Factors in Computing Systems · doi:10.1145/3772318.3791318 · Cited by 5
“LLM-based systems can be personalized to match users’ conversational styles [46] and integrated with cultural cues and language norms to improve engagement in marginalized communities [3, 28, 49].”
Crossmodal Transformer on Multi-Physical Signals for Personalised Daily Mental Health Prediction
Song, M., Yang, Z., Triantafyllopoulos, A., Nakamura, T., Zhang, Y., Ren, Z. X., Takeuchi, H., Kishi, A., Ishizawa, T., Yoshiuchi, K., et al. (2023) · IEEE ... International Conference on Data Mining workshops · doi:10.1109/icdmw60847.2023.00167 · Cited by 4
“Secondly, existing methods are generally focused on single types of physiological signals, thereby neglecting the multi-modal nature of human physiology [11].”
MethodFiol, G. D., Orleans, B., Kuzmenko, T. V., Chipman, J., Greene, T., Martínez, A., Wirth, J., Meads, R., Kaphingst, K. A., Gibson, B., et al. (2024) · BMJ Open · doi:10.1136/bmjopen-2023-081455 · Cited by 4
“38 While scripted chatbots have been widely used in the COVID-19 pandemic, especially to evaluate patient’s eligibility for testing and vaccination, 39–44 research is needed to examine their benefits in addressing COVID-19 at-home testing.”
MethodLaymouna, M. A., Ma, Y., Lessard, D., Engler, K., Therrien, R., Schuster, T., Vicente, S., Achiche, S., Haj, M. N. E., Lemire, B., et al. (2024) · Healthcare · doi:10.3390/healthcare12161661 · Cited by 9
“Chatbots, also known as “conversational agents”, are computer programs designed to mimic human conversation through various platforms, including websites, texting apps, and computer software [22–33].”
BackgroundImproving Health Care Services via Personalized Medicine
Rhatassi, F. E. E., Ghali, B. E., & Daoudi, N. (2023) · Lecture notes in networks and systems · doi:10.1007/978-3-031-28387-1_37 · Cited by 3
Santini, S., Stara, V., Galassi, F., Merizzi, A., Schneider, C., Schwamm, S., Stolte, E., & Kropf, J. (2021) · doi:10.2196/preprints.30662 · Cited by 4
He, Y., Yang, L., Zhu, X., Wu, B., Zhang, S., Qian, C., & Tian, T. (2022) · doi:10.2196/preprints.40719 · Cited by 3
Mzwri, K., & Turcsányi-Szabó, M. (2025) · Research Square · doi:10.21203/rs.3.rs-6256444/v1 · Cited by 4
Sezgın, E., Jackson, D., Hussain, S.-A., Kocaballi, A. B., Richardson, C., Skeens, M. A., Fosler‐Lussier, E., Ewing, A. P., Donneyong, M. M., & Pai, A. L. H. (2026) · PLOS Digital Health · doi:10.1101/2025.06.16.25329054 · Cited by 3
“49”
Self-citationAvatar Appearance Beyond Pixels - User Ratings and Avatar Preferences Within Health Applications
Ashrafi, N., Graf, P., Marquardt, M., Vona, F., Schorlemmer, J., & Voigt‐Antons, J. (2025) · Lecture notes in computer science · doi:10.1007/978-3-031-93508-4_11 · Cited by 3
“As a result, there is a growing body of research dedicated to understanding the essential features, optimal design practices, and assessment metrics for evaluating the success rate of healthcare applications utilizing virtual avatars [15].”
Mapping the Research Landscape of Virtual Coaches: What Is to Come?
Korn, F., Karger, E., & Ahlemann, F. (2025) · IEEE Access · doi:10.1109/access.2025.3581440 · Cited by 2
“The rapid developments in AI, particularly when coupled with NLP, have enabled a new generation of VCs capable of simulating human-like conversations and offering real-time adaptation and personalized feedback [114], [115].”
Ahire, S., Guyre, M., Rey, B., Lee, M., & Candello, H. C. D. S. P. (2025) · ACM Conference on Conversational User Interfaces (CUI) · doi:10.1145/3719160.3728628 · Cited by 3
“Critical issues such as ensuring data privacy, maintaining user agency, and mitigating the psychological impacts of AI interactions in health and wellbeing applications must be care-fully navigated [1, 3, 10, 15, 28].”
Listening with the Eyes: Understanding User Gaze Influence in Counseling Dialogues with GC-Speaker
Lee, K., Yoo, S. Y., & Lee, J. (2025) · International Journal of Human-Computer Interaction · doi:10.1080/10447318.2025.2520930 · Cited by 2
“…et al., 2023; V € olkel et al., 2021), (2) maintaining brevity for efficient interaction (Anand et al., 2023; Hone & Graham, 2000), and (3) enhancing user engagement through dynamic tailoring of responses (Kocaballi et al., 2019; Litman & Pan, 2002; Pargellis et al., 2004; Thompson et al., 2004).”
Using Virtual Agents and LLMs to Generate Tailored Health Education Pamphlets
Fallah, M., Nouraei, F., & Bickmore, T. (2025) · ACM International Conference on Intelligent Virtual Agents (IVA) · doi:10.1145/3717511.3747088 · Cited by 3
“Compared to generic materials, tailored and personalized interventions have been associated with higher user engagement and satisfaction [30], better understanding health information [47], and greater success in promoting healthy behavior change [28].”
Increasing breastfeeding literacy: A preliminary study to develop an AI-based chatbot
Kantovitz, K. R., Mattoso, M. E., Meyer, M. D., de Araújo, M. A., Giovani, P. A., Martinez, V., Dubey, N., Nociti, F. H., & Motta, R. H. L. (2025) · International Journal of Nursing Sciences · doi:10.1016/j.ijnss.2025.10.013 · Cited by 2
“The current investigation sheds light on this field by evaluating a functional, accessible prototype with relevant content [39,40].”
Madera, F., Nicodemo, G., Guasco, S., Ciulli, T., & Cardinali, P. (2026) · European Psychologist · doi:10.1027/1016-9040/a000580 · Cited by 2
Personalizing Human-LLM Interactions through Mixed Profiling
Müller, E., Greiner, K., Wegener, A., Kuhlmeier, F. O., & Maedche, A. (2026) · CHI Conference Extended Abstracts on Human Factors in Computing Systems (CHI EA) · doi:10.1145/3772363.3799351 · Cited by 2
“As the field advances toward more personalized LLM-based interactions, accurately capturing a user’s psychological profile without disrupting conversational flow remains a critical challenge [13].”
Han, G. I., Lee, H. J., & Son, Y.-J. (2026) · Digital Health · doi:10.1177/20552076261450385 · Cited by 2
“7,8 In healthcare delivery, chatbots have been employed to improve access to timely information and reduce temporal and geographic barriers by providing personalized, on-demand support.”
Dialogue-Based User Needs Extraction for Effective Service Personalization
Nakata, T., Chen, S., Saiki, S., & Nakamura, M. (2023) · Lecture notes in computer science · doi:10.1007/978-3-031-35129-7_10 · Cited by 3
Ren, L., Yan, J., Zhu, Z., & Du, M. (2024) · Journal of Aging and Physical Activity · doi:10.1123/japa.2022-0224 · Cited by 2
Agiollo, A., Siebert, L. C., Murukannaiah, P. K., & Omicini, A. (2024) · Autonomous Agents and Multi-Agent Systems · doi:10.1007/s10458-024-09663-8 · Cited by 11
“…future of intelligent agent systems is likely to be deeply intertwined with LLMs. Intelligent agents exploiting NLP-enabled process for human-agent interaction as well as for inter-agent communication within complex Multi-Agent Systems (MASs) are going to become more and more popular [6, 7].”
Kim, S. J., Swanson, V. A., Collier, G. H., Rabinowitz, A. R., Zondervan, D. K., & Reinkensmeyer, D. J. (2024) · IEEE Transactions on Neural Systems and Rehabilitation Engineering · doi:10.1109/tnsre.2024.3428915 · Cited by 5
“Recently, chatbots have become increasingly common in healthcare to support users in developing healthy behavior habits, thanks to their ability to provide personalized and interactive content [39].”
BackgroundSCAN: A HealthCare Personalized ChatBot with Federated Learning Based GPT
Puppala, S., Hossain, I., Alam, M. J., & Talukder, S. K. (2024) · IEEE Annual International Computer Software and Applications Conference (COMPSAC) · doi:10.1109/compsac61105.2024.00309 · Cited by 3
Fiol, G. D., Kuzmenko, T. V., Orleans, B., Chipman, J., Greene, T., Meads, R., Kaphingst, K. A., Gibson, B., Kawamoto, K., King, A. J., et al. (2025) · Journal of Medical Internet Research · doi:10.2196/74145 · Cited by 4
“Chatbots have been shown to be effective across a wide variety of health domains, including asthma, diabetes, pain management, physical activity, mental health, and genetic testing [18-24].”
Hu, J., Yao, X., Huang, Z., Liang, D., Yang, D., Liu, D., Li, J., Zhang, Y., & Ma, X. (2026) · CHI Conference on Human Factors in Computing Systems · doi:10.1145/3772318.3792787 · Cited by 3
“Yet such inquiries remain sparse, overshadowed by the far larger body of reviews that fixate on domain-specific niches, such as elderly support [65, 78], customer service [17, 177, 183], and health care [26, 79, 85, 167].”
Smriti, D., Shin, J. Y., Mujib, M. I., Colosimo, M. M., Kao, T. A., Williams, J. R., & Huh, J. (2020) · International Conference on Pervasive Computing Technologies for Healthcare · doi:10.1145/3421937.3421963 · Cited by 2
Green, E. P., Pradheep, S., Heinzelman, J., Nyanchoka, A., Achieng, D., Goyal, S., Cusson, L., Kurz, A. S., & Bellows, B. (2021) · Translational Behavioral Medicine · doi:10.1093/tbm/ibab096 · Cited by 3
Take Back Control: User Privacy and Transparency Concerns in Personalized Conversational Agents
Hendrickx, I., van Waterschoot, J., Khan, A., ten Bosch, L., Catia Cucchiarini, A., & Strik, H. (2021) · University of Twente Research Information · Cited by 5
Alexa Depression and Anxiety Self-tests: A Preliminary Analysis of User Experience and TrustPreprint
Quiroz, J. C., Bongolan, T., & Ijaz, K. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2008.03892 · Cited by 2
“t challenges [15]. In our pilot, we observed similar trends where participants rarely used the Alexa Skill. Enhancing the engagement of conversational agents through storytelling [1], personalization [9], and affect [3] has been proposed in the past. However, further research is needed to understand the design implica…”
ResultSelf-citationChatbots: A Game Changer in mHealthPreprint
Chowdhury, M. N.-U.-R., Haque, A., & Soliman, H. (2023) · doi:10.36227/techrxiv.22548532.v2 · Cited by 2
Araujo, T., & Bol, N. (2025) · Computers in Human Behavior Artificial Humans · doi:10.1016/j.chbah.2025.100178 · Cited by 2
DECI: A Tutorial on Designing Effective Conversational Interfaces
Gadiraju, U., Abbas, T., & Allen, G. (2023) · ACM International Conference on Intelligent User Interfaces (IUI) · doi:10.1145/3581754.3584165 · Cited by 2
“Overall, the ease of use and potential for personalization make conversational interfaces an attractive option for many consumers [13, 24], increasing their popularity and widespread adoption.”
BackgroundFiol, G. D. (2023) · Elsevier eBooks · doi:10.1016/b978-0-323-91200-6.00023-1 · Cited by 2
Merkel, S., & Schorr, S. (2024) · JMIR AI · doi:10.2196/55673 · Cited by 2
“These devices can be used without any direct contact, are relatively inexpensive and easy to operate, and can be customized and personalized by installing new applications and features [28].”
DECI: The 3rd Tutorial on Designing Effective Conversational Interfaces
Gadiraju, U., & Yadav, K. (2025) · ACM International Conference on Intelligent User Interfaces (IUI) · doi:10.1145/3708557.3716162 · Cited by 1
“Overall, the ease of use and potential for personalization make conversational interfaces attractive for many consumers [19, 30], increasing their popularity and widespread adoption.”
Kadar, M. A., & Modak, R. (2021) · World Journal of Advanced Research and Reviews · doi:10.30574/wjarr.2021.10.3.0236 · Cited by 1
“Within healthcare, conversational AI can facilitate patient education, symptom monitoring, appointment scheduling, and medication reminders, potentially improving care access while reducing administrative burden [6, 7].”
Parents’ information needs and perceptions of chatbots regarding self medicating their children
Wei, X., Chen, X., Yue, L., & Liao, P. (2025) · Scientific Reports · doi:10.1038/s41598-025-15130-5 · Cited by 2
“Similar to the previous study 32 , our research revealed several design suggestions for information transmission, conversational interface and interaction frequency, and user experience.”
InfluentialExtended Reality in Health Care Simulation: Current State, Challenges, and Future Directions
Cieslowski, B. J., Anderson, M., Brown, K. M., Guido‐Sanz, F., Hallmark, B. F., Wells-Beede, E., Konzelmann, J., Belk, W. B., Smeltzer, S. L., Mallala, S. B., et al. (2025) · Nurse Educator · doi:10.1097/nne.0000000000001996 · Cited by 3
Lee, C., Joung, E., Koh, Y., Kim, E., Son, S., Kwon, S., & Lee, U. (2025) · Proceedings of the ACM on Human-Computer Interaction · doi:10.1145/3757533 · Cited by 3
“The personalization features in conversational agents for health care have been reported to enhance user satisfaction and engagement [61].”
Balaban, B.-M., Sacală, I. Ş., & Petrescu-Niţă, A.-C. (2025) · Future Internet · doi:10.3390/fi17070314 · Cited by 2
Kuwar, V., Kumari, P., Upreti, K., et al. (2025) · Elsevier eBooks · doi:10.1016/b978-0-443-41660-6.00018-1 · Cited by 1
Personalized transparency: A scoping review of approaches to personalized privacy disclosures
Xu, M., Guitton, C., Tamò‐Larrieux, A., & Lutz, C. (2026) · Computer law & security review · doi:10.1016/j.clsr.2026.106265 · Cited by 1
Maalouly, E., Rossi, A., & Rossi, S. (2026) · Frontiers in Robotics and AI · doi:10.3389/frobt.2026.1760008 · Cited by 3
“Kocaballi et al. (2019) proposed a framework to characterize personalization along three dimensions: 1.”
TigerGPT: A Theory-Driven AI Chatbot for Adaptive Campus Climate Surveys
Tang, J., Chen, S., & Shang, Y. (2025) · IEEE International Conference on Future Machine Learning and Data Science (FMLDS) · doi:10.1109/fmlds67896.2025.00110 · Cited by 1
“Its key features are presented below. a) Personalized Conversation : Personalization in chat-bots can significantly boost user engagement and satisfaction [21], [22].”
Conversational AI and Personal Growth: Insights from a Critical Integrative Review
Sharma, S., Vohra, P., & Vowels, L. M. (2026) · Behavioral Sciences · doi:10.3390/bs16050756 · Cited by 3
A Low-Code Approach for the Automatic Personalization of Conversational Agents
Conrardy, A. D., Capozucca, A., & Cabot, J. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-29372-5_4 · Cited by 2
“Text, speech, images/video, gestures, or haptics [22, 17] Table 1: Overview of personalization dimensions with embedded definitions and representative examples.”
InfluentialPersonalised AI Coaching Technology: A Systematic Mapping Review
Vitale, J., Cenacchi, F., Kraus, M., Orji, F. A., Richards, D., Orji, R., Conati, C., & Berkovsky, S. (2026) · ACM Transactions on Interactive Intelligent Systems · doi:10.1145/3820900 · Cited by 2
Self-citationAttitudes of nurses, physiotherapy assistants and masseurs towards low back pain treatment
Simoncsics, E., & Stauder, A. (2021) · Physiotherapy Practice and Research · doi:10.3233/ppr-200401 · Cited by 1
Sasseville, M., Barony, R., Yameogo, A. R., Bergeron-Drolet, L.-A., Bergeron, F., & Gagnon, M. (2022) · JMIR Research Protocols · doi:10.2196/40265 · Cited by 3
“Therefore, the development of conversational agents adapted to the needs of individuals, especially those in vulnerable situations, remains a major challenge for researchers [33].”
BackgroundOh, Y., Arias, K., Auster‐Gussman, L. A., & Graham, S. A. (2023) · Lecture notes in computer science · doi:10.1007/978-3-031-35748-0_7 · Cited by 2
Singh, A., Schooley, B. L., & Patel, N. (2023) · JMIR mhealth and uhealth · doi:10.2196/43105 · Cited by 1
“Although physicians have reported mixed views on the value of chatbots, some studies have found that providers acknowledge cost savings and benefits when the functionality of the chatbot plays a clear strategic role for an organization [39,40].”
BackgroundDECI: The 2nd Tutorial on Designing Effective Conversational Interfaces
Gadiraju, U., & Yadav, K. (2024) · ACM Conference on User Modeling, Adaptation and Personalization (UMAP) · doi:10.1145/3631700.3658531 · Cited by 1
“Overall, the ease of use and potential for personalization make conversational interfaces attractive for many consumers [16, 28], increasing their popularity and widespread adoption.”
BackgroundZhou, C., & Zhao, H. (2025) · International Journal of Human-Computer Interaction · doi:10.1080/10447318.2025.2508306 · Cited by 1
Making Warning Messages Personal: A Big 5 Personality Trait Persuasion Approach
Aneke, J., Ardito, C. A., & Desolda, G. (2021) · Lecture notes in computer science · doi:10.1007/978-3-030-85607-6_57 · Cited by 2
Uso de Chatbots Personalizados para Monitoração do Desaprendizado e Esquecimento de Idosos
Pinto, N., & García, A. C. B. (2021) · Simpósio Brasileiro de Sistemas Colaborativos (SBSC) · doi:10.5753/sbsc_estendido.2021.16034 · Cited by 1
Sasseville, M., Barony, R., Yameogo, A. R., Bergeron-Drolet, L.-A., Bergeron, F., & Gagnon, M. (2022) · doi:10.2196/preprints.40265 · Cited by 1
Loveys, K., Antoni, M. H., Donkin, L., Sagar, M. A., & Broadbent, E. (2022) · doi:10.2196/preprints.42390 · Cited by 1
A Systematic Review of Chatbot-Enabled Chronic Disease Management Interventions and mHealthPreprint
Islam, J., Hasan, M., & Hasan, M. M. (2023) · doi:10.36227/techrxiv.22815275 · Cited by 2
A Systematic Review of Chatbot-Enabled Chronic Disease Management Interventions and mHealthPreprint
Islam, J., Hasan, M., & Hasan, M. M. (2023) · doi:10.36227/techrxiv.22815275.v1 · Cited by 1
Consent GPT: Is It Ethical to Delegate Procedural Consent to Conversational AI?Preprint
Allen, J., Earp, B. D., Koplin, J. J., et al. (2023) · SSRN Electronic Journal · doi:10.2139/ssrn.4520613 · Cited by 1
Malik, U., Ahmad, L. I., Hassan, A., Shafique, I., Mohsin, E., Ali, A., Alizai, M. H., & Qazi, I. A. (2026) · CHI Conference on Human Factors in Computing Systems · doi:10.1145/3772318.3791761 · Cited by 2
“Prior work stresses explainability [32, 51, 67], personalization [43, 57], and multimodal interfaces [18] for cognitive efficiency, especially under high pressure [54, 59, 91].”
The Data-Dollars Tradeoff: Privacy Harms vs. Economic Risk in Personalized AI Adoption
Erlei, A., Abbas, T., Bizer, K., & Gadiraju, U. (2026) · CHI Conference on Human Factors in Computing Systems · doi:10.1145/3772318.3791427 · Cited by 5
“Personalization, for example, can improve user experience by providing tailored interactions, while recommendation systems rely on private signals to make calibrated predictions [58, 61, 65, 68].”
Berkovsky, S., & Coiera, E. W. (2021) · ACM SIGWEB Newsletter · doi:10.1145/3473044.3473048
“Typical personalised services support the wellbeing of their users by recommending recipes and meal plans, suggesting exercises and workouts, promoting physical activity and exergaming, assisting in health information access, providing personalised social support, and so on [Kocaballi et al. 2019].”
BackgroundSelf-citationGreen, E. P., Pradheep, S., Heinzelman, J., et al. (2020) · doi:10.31219/osf.io/9pazf
Personalization in digital interventions for behavior change (Preprint)Preprint
Tong, H. L., Quiroz, J. C., Kocaballi, A. B., Kennedy, G., Coiera, E. W., & Laranjo, L. (2020) · doi:10.2196/preprints.20562
Self-citationExploring the role of health apps in supporting young people with depression: a mixed methods study
Martinengo, L. (2021) · DR-NTU (Nanyang Technological University) · doi:10.32657/10356/157124
Weeks, R., Sangha, P., Cooper, L., Sedoc, J., White, S., Gretz, S., Toledo, A., Lahav, D., Hartner, A.-M., Martin, N., et al. (2022) · doi:10.2196/preprints.40533
Assessing Data Gathering Quality of Chatbot Based Symptom Checkers - a Clinical Vignettes StudyPreprint
Ben‐Shabat, N., Sharvit, G., Meimis, B., Joya, D. B., Sloma, A., Kiderman, D., Shabat, A., Tsur, A. M., Watad, ., & Amital, H. (2022) · SSRN Electronic Journal · doi:10.2139/ssrn.4128799
Dhinagaran, D. A. (2022) · DR-NTU (Nanyang Technological University) · doi:10.32657/10356/163179
Wang, W., Fang, S., Zhang, S., He, M., Zhu, X., Dong, Y., Ma, D., Zhao, Y., Meng, X., Gao, S., et al. (2023) · Research Square · doi:10.21203/rs.3.rs-2544870/v1
Chatbots: A Game Changer in mHealthPreprint
Chowdhury, M. N.-U.-R., Haque, A., & Soliman, H. (2023) · doi:10.36227/techrxiv.22548532
Kim, S., Swanson, V. A., Collier, G., et al. (2023) · doi:10.36227/techrxiv.24052923
A Systematic Review of Chatbot-Enabled Chronic Disease Management Interventions and mHealthPreprint
Islam, J., Hasan, M., & Hasan, M. M. (2023) · doi:10.36227/techrxiv.22815275.v2
Should Conversational Agents Care About Our Gender Identity?
Cocchi, A., Bosse, T., & van Pinxteren, M. M. E. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-54975-5_9 · Cited by 3
Kondaveeti, S., & Prabhala, P. (2024) · doi:10.36227/techrxiv.172469992.22196051/v1 · Cited by 1
Towards Digital Zen: A Systematic Review of Emerging Digital Interventions for Mental Wellness
Asadi, A. R., & Prabhakar, A. S. (2024) · Lecture notes in networks and systems · doi:10.1007/978-3-031-73125-9_7 · Cited by 1
Socially Competent Agents That Care
Wolfert, P., Neerincx, A., Thunberg, S., et al. (2024) · International Conference on Human-Agent Interaction (HAI) · doi:10.1145/3687272.3691360
“To achieve these outcomes, agents must be socially competent, e.g., by understanding and adapting to the needs of the user [2], and showing empathy [5].”
Analyzing and mitigating the threats & risks of AI voice bots
Dhaliwal, A. K. (2024) · AIP conference proceedings · doi:10.1063/5.0234448
Quantitative Review of Conversational Agents in E-Health Using NLP and AI
Carchiolo, V., & Malgeri, M. (2024) · Global Congress on Emerging Technologies (GCET) · doi:10.1109/gcet64327.2024.10934583 · Cited by 1
Challenges in Personalising AI: From Uniformity to UniquenessPreprint
Lukáč, M. (2025) · SocArXiv (OSF Preprints) · doi:10.31235/osf.io/hu4ev_v1 · Cited by 1
Unravelling the Power of Sentiment: How Emotions Shape Online Engagement in Public Health Discourse
Jaffali, S., & Khelifi, N. (2025) · BRAIN BROAD RESEARCH IN ARTIFICIAL INTELLIGENCE AND NEUROSCIENCE · doi:10.70594/brain/16.2/21
Mobile phones as assistive technology
Dobosz, K. (2025) · Technology and Disability · doi:10.1177/10554181251355421 · Cited by 2
“75,76 The power of AI is important for the blind and visually impaired to recognize images coming from a smartphone ’ s built-in camera.”
Ratnayake, A. R. M. C. D. (2025) · Lecture notes in computer science · doi:10.1007/978-3-032-02534-0_10
Hu, D., Chung, J., Díaz, D. V., Lee, S., Lee, S. W., & Lim, S. I. (2026) · International Journal of Human-Computer Studies · doi:10.1016/j.ijhcs.2026.103863
Scholz, S., Nass, E., & Winkler, C. (2025) · Springer eBooks · doi:10.1007/978-3-658-48573-3_39
Berrajaa, A., Berrajaa, I., & Rouky, N. (2025) · doi:10.3390/engproc2025112050
AyurMi: A Synergistic Approach to Mental Wellness through AI and Ayurvedic Mindfulness
Chauhan, B., Badnaware, T., Maharana, S., Patil, S., & Kadam, P. (2025) · International Conference on Computing Communication Control and automation · doi:10.1109/iccubea65967.2025.11284029 · Cited by 1
Mahmud, R., Berkovsky, S., Prasad, M., & Kocaballi, A. B. (2026) · SSRN Electronic Journal · doi:10.2139/ssrn.6067033
Self-citationMehta, T. (2026) · International Journal of Latest Technology in Engineering Management & Applied Science · doi:10.51583/ijltemas.2025.1412000140
Graf, L., Golz, V., Prehn, S., Masuch, M., & Gradl-Dietsch, G. (2026) · BMC Medical Education · doi:10.1186/s12909-026-08760-4
Joshi, R., Bengler, K. J., & Augustyniak, J. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-19687-3_8
Degachi, S., Niforatos, E., & Kortuem, G. (2026) · Behaviour and Information Technology · doi:10.1080/0144929x.2026.2638907 · Cited by 1
Saisie de prescriptions médicales en langage naturel sur terminaux mobiles
Kocabiyikoglu, A. C. (2022) · theses.fr (ABES) · doi:10.70675/998d4b74z9eb1z49bcz9763zfa1e8ebcbd43
Modelling a humanoid virtual leader assistant for a remote and isolated caregivers
Jackson, A. C. (2022) · theses.fr (ABES) · doi:10.70675/8634e096z6e3dz48c4z9cddzab3489fa64e0
AutismCarebot: Emotion-First, Source-Aware Conversational Support for Autistic Users
Srivastava, S., Zolyomi, A., & Si, D. (2026) · CHI Conference Extended Abstracts on Human Factors in Computing Systems (CHI EA) · doi:10.1145/3772363.3798986 · Cited by 1
“Health and mental health conversational agents are designed to support a person, but systematic reviews of personalization in health conversational agents highlight diverse implementations and limited evaluation of personalization’s impact [3].”
TrackWise: A Privacy-Preserving Client-Side Conversational Agent for Ambient Chronic Illness Support
Nasri, S. A. E. M., & Kavakli, M. (2026) · Lecture notes in networks and systems · doi:10.1007/978-3-032-16992-1_15
Guenier, A. W., & Mao, Y. (2026) · doi:10.2196/preprints.96062
AI in cancer education and screening: Improving patient awareness and quality of life
Sharma, D., Pal, D., & Sharma, L. (2026) · Elsevier eBooks · doi:10.1016/b978-0-443-45004-4.00001-3
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.
