Embodied Conversational Agents for the Detection and Prevention of Suicidal Behaviour: Current Applications and Open Challenges
The DOI matches its Crossref record; 53 of the 55 references it cites were found in a registry or an index.
Abstract
Embodied conversational agents (ECAs) are advanced computational interactive interfaces designed with the aim to engage users in the continuous and long-term use of a background application. The advantages and benefits of these agents have been exploited in several e-health systems. One of the medical domains where ECAs are recently applied is to support the detection of symptoms, prevention and treatment of mental health disorders. As ECAs based applications are increasingly used in clinical psychology, and due that one fatal consequence of mental health problems is the commitment of suicide, it is necessary to analyse how current ECAs in this clinical domain support the early detection and prevention of risk situations associated with suicidality. The present work provides and overview of the main features implemented in the ECAs to detect and prevent suicidal behaviours through two scenarios: ECAs acting as virtual counsellors to offer immediate help to individuals in risk; and ECAs acting as virtual patients for learning/training in the identification of suicide behaviours. A literature review was performed to identify relevant studies in this domain during the last decade, describing the main characteristics of the implemented ECAs and how they have been evaluated. A total of six studies were included in the review fulfilling the defined search criteria. Most of the experimental studies indicate promising results, though these types of ECAs are not yet commonly used in routine practice. The identification of some open challenges for the further development of ECAs within this domain is also discussed.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
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?
In the citing paper
“and talking to young people about suicide, sex, and drug use (9, 10).”
From Key Considerations for Incorporating Conversational AI in Psychotherapy (2019) · cites this paper as [10]
Citations
Cites
The 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
SUS: A 'Quick and Dirty' Usability Scale
(1996) · Usability Evaluation In Industry · doi:10.1201/9781498710411-35 · Cited by 8,989
Intelligent agents: theory and practice
Wooldridge, M., & Jennings, N. R. (1995) · The Knowledge Engineering Review · doi:10.1017/s0269888900008122 · Cited by 6,810 · cited 1×
“The main features of an intelligent agent include autonomy: the agent operates without the intervention of others (software or human) agents; reactivity: the agent responds in a timely fashion to the changes that occurs in its environment; proactivity: the agent does not only respond to the changes in the environment,…”
BackgroundUsability Evaluation In Industry
(1996) · CRC Press eBooks · doi:10.1201/9781498710411 · Cited by 4,354
Appraisal processes in emotion: Theory, methods, research.
Scherer, K. R., Schorr, A., & Johnstone, T. (2001) · Cited by 2,418
Appraisal Processes in Emotion: Theory, Methods, Research
(2001) · doi:10.1093/oso/9780195130072.001.0001 · Cited by 2,384
Cognitive Load Theory and Complex Learning: Recent Developments and Future Directions
van Merriënboer, J. J. G., & Sweller, J. (2005) · Educational Psychology Review · doi:10.1007/s10648-005-3951-0 · Cited by 2,206 · cited 1×
“The underlying model implemented in the Kognito ECAs is based on instructional design strategies to increase encoding capabilities in working memory which result in deeper and more meaningful learning [37]; and the conversa t iona l component implements d if ferent communication strategies taken from social/cognitive…”
MethodMotivational interviewing with problem drinkers
Miller, W. R. (1983) · Behavioural Psychotherapy · doi:10.1017/s0141347300006583 · Cited by 1,390 · cited 1×
“The underlying model implemented in the Kognito ECAs is based on instructional design strategies to increase encoding capabilities in working memory which result in deeper and more meaningful learning [37]; and the conversa t iona l component implements d if ferent communication strategies taken from social/cognitive…”
MethodStudies in Health Technology and Informatics
Aphinyanaphongs, Y., & Aliferis, C. (2007) · Cited by 1,247
A review of depression and suicide risk assessment using speech analysis
Cummins, N., Scherer, S., Krajewski, J., Schnieder, S., Epps, J., & Quatieri, T. F. (2015) · Speech Communication · doi:10.1016/j.specom.2015.03.004 · Cited by 1,003 · cited 1×
“Nevertheless, further developments of ECAs should detect risk situations and provide advice based not only in the self-reports of the user, but implementing a multi-modal interaction where facial expressions and voice characteristics of the user can be analysed to detect distress indicators [47] and patterns associate…”
BackgroundIt's only a computer: virtual humans increase willingness to disclose
Lucas, G. M., Gratch, J., King, A., & Morency, L.-P. (2014) · Computers in Human Behavior · doi:10.1016/j.chb.2014.04.043 · Cited by 977 · cited 1×
“When the appearance and behaviourof theECAaredesignedsuitably, theECAcanestablish good levels of trust and a social bond with the user facilitating the disclosure of relevant health-related information [20].”
BackgroundFaçade: An Experiment in Building a Fully-Realized Interactive Drama
Mateas, M., & Stern, A. (2003) · Cited by 583
Serious Games and Gamification for Mental Health: Current Status and Promising Directions
Fleming, T. M., Bavin, L., Stasiak, K., Hermansson-Webb, E., Merry, S. N., Cheek, C., Lucassen, M., Lau, H. M., Pollmuller, B., & Hetrick, S. (2017) · Frontiers in Psychiatry · doi:10.3389/fpsyt.2016.00215 · Cited by 582 · cited 1×
“There are currently some serious games aimed to support people suffering from mental health problems such as depression [9], and a mini-game to”
Background(2014) · doi:10.5555/2615731.2617415 · Cited by 553
Establishing the computer-patient working alliance in automated health behavior change interventions
Bickmore, T., Gruber, A., & Picard, R. (2005) · Patient Education and Counseling · doi:10.1016/j.pec.2004.09.008 · Cited by 494
Detecting suicidality on Twitter
O'Dea, B., Wan, S., Batterham, P. J., Calear, A. L., Paris, C., & Christensen, H. (2015) · Internet Interventions · doi:10.1016/j.invent.2015.03.005 · Cited by 439
Embodied conversational agents in clinical psychology: a scoping review
Provoost, S., Lau, H. M., Ruwaard, J., & Riper, H. (2017) · Journal of Medical Internet Research · doi:10.2196/jmir.6553 · Cited by 433 · cited 3×
“mental and behavioural related problems [26].”
MethodInfluentialRobinson, J., Cox, G., Malone, A., Williamson, M., Baldwin, G., Fletcher, K., & O’Brien, M. (2013) · Crisis · doi:10.1027/0227-5910/a000168 · Cited by 286 · cited 1×
“Big efforts have been dedicated and several health interventions have been tested in different settings, such as schools [2] and workplaces [3], or addressed to specific populations [4, 5] to effectively detect and prevent suicidal behaviours.”
BackgroundBickmore, T. W., Utami, D., Matsuyama, R., & Paasche-Orlow, M. K. (2016) · Journal of Medical Internet Research · doi:10.2196/jmir.5239 · Cited by 153
Playing with virtual peers: bootstrapping contingent discourse in children with autism
Tartaro, A., & Cassell, J. (2008) · International Conference of Learning Sciences · Cited by 141
Validity of Suicidality Items From the Youth Risk Behavior Survey in a High School Sample
May, A., & Klonsky, E. D. (2011) · Assessment · doi:10.1177/1073191110374285 · Cited by 139
Burton, C., Szentagotai Tatar, A., McKinstry, B., Matheson, C., Matu, S., Moldovan, R., Macnab, M., Farrow, E., David, D., Pagliari, C., et al. (2016) · Journal of Telemedicine and Telecare · doi:10.1177/1357633x15609793 · Cited by 125
A Systematic Literature Review of Agents Applied in Healthcare
Isern, D., & Moreno, A. (2015) · Journal of Medical Systems · doi:10.1007/s10916-015-0376-2 · Cited by 123 · cited 1×
“Agent-based applications have been extensively used in the healthcare domain to the development of data-management systems, implementation of secure platforms, clinical decision support systems, care platforms or the implementation of patient monitoring systems among some others [12].”
BackgroundTeaching Negotiation Skills through Practice and Reflection with Virtual Humans
Core, M., Traum, D., Lane, H. C., Swartout, W., Gratch, J., van Lent, M., & Marsella, S. (2006) · SIMULATION · doi:10.1177/0037549706075542 · Cited by 113 · cited 1×
“Although the first applications of this technology were developed mainly for teaching/training purposes [13,14]or in thegameindustry (asnon-playercharacters) [15, 16], the use of the ECAs within the health context has grown in the last years [17–19].”
MethodRelational Agents in Clinical Psychiatry
Bickmore, T., & Gruber, A. (2010) · Harvard Review of Psychiatry · doi:10.3109/10673221003707538 · Cited by 112
Robinson, J., Hetrick, S., Cox, G., Bendall, S., Yuen, H. P., Yung, A., & Pirkis, J. (2016) · Early Intervention in Psychiatry · doi:10.1111/eip.12137 · Cited by 108 · cited 1×
“These technologies include the development of internetbased and mobile applications for suicide prevention [6], and although the effectiveness of these tools is still under analysis, some of them have reported promising results in the reduction of suicidal ideation [7].”
BackgroundWorkplace suicide prevention: a systematic review of published and unpublished activities
Milner, A., Page, K., Spencer-Thomas, S., & LaMontagne, A. D. (2014) · Health Promotion International · doi:10.1093/heapro/dau085 · Cited by 100 · cited 1×
“Big efforts have been dedicated and several health interventions have been tested in different settings, such as schools [2] and workplaces [3], or addressed to specific populations [4, 5] to effectively detect and prevent suicidal behaviours.”
BackgroundUsing Linguistic Features to Estimate Suicide Probability of Chinese Microblog Users
Zhang, L., Huang, X., Liu, T., Li, A., Chen, Z., & Zhu, T. (2015) · Lecture notes in computer science · doi:10.1007/978-3-319-15554-8_45 · Cited by 99
Web-Based and Mobile Suicide Prevention Interventions for Young People: A Systematic Review.
Perry, Y., Werner‐Seidler, A., Calear, A. L., & Christensen, H. M. (2016) · PubMed Central · Cited by 86
Investigating the speech characteristics of suicidal adolescents
Scherer, S. J., Pestian, J. P., & Morency, L. (2013) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp.2013.6637740 · Cited by 78 · cited 1×
“Nevertheless, further developments of ECAs should detect risk situations and provide advice based not only in the self-reports of the user, but implementing a multi-modal interaction where facial expressions and voice characteristics of the user can be analysed to detect distress indicators [47] and patterns associate…”
BackgroundFoster, A. E., Chaudhary, N., Murphy, J. P., Lok, B. C. L., Waller, J. L., & Buckley, P. F. (2014) · Academic Psychiatry · doi:10.1007/s40596-014-0185-9 · Cited by 72 · cited 2×
“Also, the results indicating that the participants prefer a video session over the ECA as educational tool reported in [36] could be caused by the fact that the ECAwas represented through a static image.”
BackgroundA Systematic Review of Suicide Prevention Programs for Military or Veterans
Bagley, S. C., Munjas, B., & Shekelle, P. (2010) · Suicide and Life-Threatening Behavior · doi:10.1521/suli.2010.40.3.257 · Cited by 72 · cited 1×
“Big efforts have been dedicated and several health interventions have been tested in different settings, such as schools [2] and workplaces [3], or addressed to specific populations [4, 5] to effectively detect and prevent suicidal behaviours.”
BackgroundAn Intelligent Virtual Human System for Providing Healthcare Information and Support
Rizzo Albert, A., Belinda, L., Buckwalter John, G., Eric, F., Julia, K., Kenji, S., Josh, W., Rothbaum Barbara, O., JoAnn, D., Greg, R., et al. (2011) · Studies in Health Technology and Informatics · doi:10.3233/978-1-60750-706-2-503 · Cited by 67
Therapy in virtual environments--clinical and ethical issues
Yellowlees, P. M., Holloway, K. M., & Parish, M. B. (2012) · Telemedicine and e-Health · doi:10.1089/tmj.2011.0195 · Cited by 63 · cited 1×
“The reason behind the lack of such mechanism could rely on similar concerns to those associated with online counselling: the legal and risk management obligations of a clinician who may not be able to identify or locate their online client in the real world [48], or the impossibility to immediately contact him/her to…”
BackgroundLuxton, D. D., June, J. D., & Chalker, S. A. (2015) · Current Treatment Options in Psychiatry · doi:10.1007/s40501-015-0057-2 · Cited by 51
Bartgis (2016) · American Indian and Alaska Native Mental Health Research · doi:10.5820/aian.2302.2016.1 · Cited by 48 · cited 1×
“In [40], the Kognito simulation platform was adapted to train members of the American Indian and Alaska Native (AI/AN) communities in the identification of symptoms of psychological distress including depression and suicidal ideation in the youth population.”
MethodWitt, K., Milner, A. J., Allisey, A., Davenport, L. J., & LaMontagne, A. D. (2017) · American Journal of Industrial Medicine · doi:10.1002/ajim.22676 · Cited by 46 · cited 1×
“Big efforts have been dedicated and several health interventions have been tested in different settings, such as schools [2] and workplaces [3], or addressed to specific populations [4, 5] to effectively detect and prevent suicidal behaviours.”
BackgroundHarnessing the power of conversations with virtual humans to change health behaviors
Albright, G., Adam, C., Serri, D., Bleeker, S., & Goldman, R. (2016) · mHealth · doi:10.21037/mhealth.2016.11.02 · Cited by 44
IDEAS4Games: Building Expressive Virtual Characters for Computer Games
Gebhard, P., Schröder, M., Charfuelàn, M., Endres, C., Kipp, M., Pammi, S., Rumpler, M., & Türk, O. (2008) · Lecture notes in computer science · doi:10.1007/978-3-540-85483-8_43 · Cited by 39 · cited 1×
“Although the first applications of this technology were developed mainly for teaching/training purposes [13,14]or in thegameindustry (asnon-playercharacters) [15, 16], the use of the ECAs within the health context has grown in the last years [17–19].”
MethodUsability and acceptability assessment of an empathic virtual agent to prevent major depression
Bresó, A., Martínez‐Miranda, J., Botella, C., Baños, R. M., & García‐Gómez, J. M. (2016) · Expert Systems · doi:10.1111/exsy.12151 · Cited by 36 · cited 2×
“The study presented in [33] describes the development of an interactive system containing an empathic ECA (see Fig.”
BackgroundSelf-citationSilverman, B. G., Holmes, J. H., Kimmel, S., Branas, C. C., Ivins, D., Weaver, R., & Chen, Y. (2001) · Health Care Management Science · doi:10.1023/a:1011448916375 · Cited by 29 · cited 1×
“This is indicative that although the use of ECAs with health purposes in general [41, 42], and particularly to support the treatment and prevention of mental and behavioural disorders”
Towards the Development of A Virtual Counselor to Tackle Students' Exam Stress
Kavakli, M., Li, M., & Rudra, T. (2012) · Journal of Integrated Design and Process Science · doi:10.3233/jid-2012-0004 · Cited by 29
A Virtual Therapist That Responds Empathically to Your Answers
Pontier, M. A., & Siddiqui, G. F. (2008) · Lecture notes in computer science · doi:10.1007/978-3-540-85483-8_42 · Cited by 28
Acceptability of Embodied Conversational Agent in a Health Care Context
Micoulaud‐Franchi, J., Sagaspe, P., de Sevin, É., Bioulac, S., Sauteraud, A., & Philip, P. (2016) · Lecture notes in computer science · doi:10.1007/978-3-319-47665-0_45 · Cited by 28
Zhang, Z., Bickmore, T., Mainello, K., Mueller, M., Foley, M., Jenkins, L., & Edwards, R. A. (2014) · Lecture notes in computer science · doi:10.1007/978-3-319-09767-1_61 · Cited by 23
Perry, Y., Calear, A. L., Mackinnon, A., Batterham, P. J., Licinio, J., King, C., Thomsen, N., Scott, J., Donker, T., Merry, S., et al. (2015) · Trials · doi:10.1186/s13063-015-0929-1 · Cited by 21 · cited 1×
“2a) who acts as a virtual guide, based on Cognitive Behavioural Therapy (CBT) principles addressed to adolescent students (16–18 years old) of high school in the prevention of depression [28].”
MethodBresó, A., Martínez-Miranda, J., Fuster‐García, E., & Garcia-Gomez, J. M. (2015) · International Journal of Human-Computer Studies · doi:10.1016/j.ijhcs.2015.11.003 · Cited by 20 · cited 1×
“The ECA implements a model of therapeutic empathy to generate adequate emotional responses [31], and makes use of a mechanism based on inference rules to offer personalised and varied contents during the interactive sessions [32].”
MethodSelf-citationEze, G. U., & Okojie, O. H. (2016) · PubMed · doi:10.3978/j.issn.2306-9740.2016.01.01 · Cited by 17
Modelling Two Emotion Regulation Strategies as Key Features of Therapeutic Empathy
Martínez-Miranda, J., Bresó, A., & Garcia-Gomez, J. M. (2014) · Lecture notes in computer science · doi:10.1007/978-3-319-12973-0_7 · Cited by 16 · cited 2×
“The ECA implements a model of therapeutic empathy to generate adequate emotional responses [31], and makes use of a mechanism based on inference rules to offer personalised and varied contents during the interactive sessions [32].”
BackgroundMethodSelf-citationThe intermediary agent's brain: supporting learning to collaborate at the inter-personal level
Martínez-Miranda, J., Jung, B., Payr, S., & Petta, P. (2008) · Adaptive Agents and Multi-Agents Systems · doi:10.5555/1402821.1402850 · Cited by 8
Self-citationEcounsellor : an avatar for student exam stress management
Li, M., Kavakli, M., & Rudra, T. (2012) · International Conference on Information Management · Cited by 5
Modelling Personality-Based Individual Differences in the Use of Emotion Regulation Strategies
Martínez-Miranda, J., & Alvarado, M. (2017) · Lecture notes in computer science · doi:10.1007/978-3-319-57351-9_41 · Cited by 4
Self-citationUsability Assessment of a Suicide Intervention-Prevention Mini-Game
Savage, J. (2015) · Communications in computer and information science · doi:10.1007/978-3-319-21383-5_119 · Cited by 2 · cited 1×
“improve in the users the knowledge concerning suicide prevention-intervention [10].”
Background
Research works printed but not linked: 2
- Lisetti C (2008) Embodied conversational agents for psychotherapy. Proceedings of CHI 2008 conference workshop on technology in mental health 1–12
- Ring L, Bickmore T W, Pedrelli P (2016) An Affectively Aware Virtual Therapist for Depression Counseling. Proceedings ACM SIGCHI Conference on Human Factors in Computing Systems. http://relationalagents.com/publications/CHI2016-MentalHealth.pdf Accessed 29 May 2017
Cited by
Bendig, E., Erb, B., Schulze-Thuesing, L., & Baumeister, H. (2022) · Verhaltenstherapie · doi:10.1159/000501812 · Cited by 214
“They could be used preventively in the future, for example for suicide prevention [Martínez-Miranda, 2017].”
MethodAI Chatbots in Digital Mental Health
Balcombe, L. (2023) · Informatics · doi:10.3390/informatics10040082 · Cited by 174
Key Considerations for Incorporating Conversational AI in Psychotherapy
Miner, A. S., Shah, N., Bullock, K. D., Arnow, B. A., Bailenson, J., & Hancock, J. (2019) · Frontiers in Psychiatry · doi:10.3389/fpsyt.2019.00746 · Cited by 166
“Additionally, conversational AI is providing clinicians with feedback on their psychotherapy (8) and talking to young people about suicide, sex, and drug use (9, 10).”
BackgroundSuganuma, S., Sakamoto, D., & Shimoyama, H. (2018) · JMIR Mental Health · doi:10.2196/10454 · Cited by 112
“Furthermore, there were other applications related to detecting and preventing suicidal behavior [18], changing of stigmatizing attitudes [19], and mental health interview [20].”
BackgroundFonseka, T. M., Bhat, V., & Kennedy, S. H. (2019) · Australian & New Zealand Journal of Psychiatry · doi:10.1177/0004867419864428 · Cited by 126
“Within direct patient care, conversational agents can be programmed to complete several tasks, which include collecting information on the patient’s clinical state, providing psychoeducation, making recommendations for supports and delivering patient-tailored psychotherapies (Martinez-Miranda, 2017).”
BackgroundInfluential
Metadata
- Authors
- Martínez-Miranda, J.
- Venue
- Journal of Medical Systems
- Published
- 2017-07-28
- Volume
- 41
- Issue
- 9
- Pages
- 135-135
- ISSN
- 0148-5598 (ISSN-L)
- 1573-689X
- OpenAlex
- W2740594804
- Cited by
- 51
- References
- 55
- Citations by year
- 2026: 2 · 2025: 8 · 2024: 4 · 2023: 8 · 2022: 3 · 2021: 4 · 2020: 4 · 2019: 16 · 2018: 2
- FWCI
- 6.87
- Type
- journal article
- Language
- en
- Open access
- closed
- Locations
- Journal of Medical Systems (publishedVersion)
- PubMed (publishedVersion)
- Funders
- CONACyT (FOSISS-2016-1-273163)
- Topics
- Social Sciences › Psychology › Applied Psychology › Digital Mental Health Interventions
- Social Sciences › Psychology › Social Psychology › Social Robot Interaction and HRI
- Social Sciences › Psychology › Clinical Psychology › Suicide and Self-Harm Studies
- Keywords
- embodied conversational agents, suicide prevention, virtual patients, mental illness, e-health, clinical psychology, suicide risk identification
- MeSH terms
- Mental Disorders, Communication, Humans, Early Diagnosis, Suicidal Ideation
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.
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.