Abstract

Use of emotionally intelligent chatbots is increasing in mental health settings to provide support by recognizing and reacting to users’ emotions. This review has a closer look at 59 peer-reviewed studies from 2017 to 2024, with a focus on systems like Woebot and Wysa. It maps out how affective computing, psychological frameworks like cognitive behavioral therapy (CBT), and human-computer interaction theories shape these systems. While there is early evidence of benefits like reduced anxiety and better emotional self-awareness, many issues remain unresolved. These include weak long-term evidence, cultural bias in emotion recognition, and potential over-dependence on AI. We also highlight the risks of collecting and using emotional data without sufficient oversight. Based on this, we suggest future research should move toward multicultural, longer-term, and ethically grounded studies. The goal should be to create emotionally intelligent systems that support, not replace, genuine human connection, especially in vulnerable populations.

References

• N. Kallivalappil, K. D’souza, A. Deshmukh, C. Kadam, and N. Sharma, “Empath.ai: A context-aware chatbot for emotional detection and support,” in Proc. 14th Int. Conf. Comput. Commun. Netw. Technol. (ICCCNT), 2023, pp. 1–7. doi:10.1109/ICCCNT56998.2023.10306584.
• T. Spring, J. Casas, K. Daher, E. Mugellini, and O. A. Khaled, “Empathic response generation in chatbots,” CONVERSATIONS Workshop, Amsterdam, 2019. [Online]. Available: https://arxiv.org/abs/1911.12315
• S. Devaram, “Empathic Chatbot: Emotional Intelligence for Mental Health Well-being,” in IEEE ICAC3, Bournemouth University, UK, 2020. [Online]. Available: https://arxiv.org/abs/2012.09130
• S. B. Velagaleti, “Empathetic algorithms: The role of AI in understanding and enhancing human emotional intelligence,” J. Electr. Syst., vol. 20, no. 3s, pp. 2051–2060, 2024. doi:10.52783/jes.1806
• S. Zeb, N. FNU, N. Abbasi, and M. Fahad, “AI in Healthcare: Revolutionizing Diagnosis and Therapy,” Int. J. Multidiscip. Sci. Arts, vol. 3, no. 3, 2024. doi:10.47709/ijmdsa.v3i3.4546
• S. Tahir, S. A. Shah, and J. Abu-Khalaf, “Artificial Empathy Classification: A Survey,” arXiv preprint, arXiv:2310.00010, 2023. [Online]. Available: https://arxiv.org/abs/2310.00010
• S. Cao et al., “Pain recognition and pain empathy from a human-centered AI perspective,” iScience, vol. 27, no. 8, p. 110570, 2024. doi: 10.1016/j.isci.2024.110570
• M. Shvo and S. A. McIlraith, “Towards Empathetic Planning and Plan Recognition,” in Proc. AIES ’19, 2019, pp. 525–526. doi:10.1145/3306618.3314307
• G. Bilquise, S. Ibrahim, and K. Shaalan, “Emotionally intelligent chatbots: A systematic review,” Hum. Behav. Emerg. Technol., pp. 1–23, 2022. doi:10.1155/2022/9601630
• A. Ghandeharioun, D. McDuff, M. Czerwinski, and K. Rowan, “Towards understanding emotional intelligence for behavior change chatbots,” arXiv preprint, arXiv:1907.10664, 2019. doi:10.48550/arXiv.1907.10664
• M. Rostami and S. Navabinejad, “Artificial empathy: User experiences with emotionally intelligent chatbots,” AI & Tech. Behav. Soc. Sci., vol. 1, no. 3, pp. 19–27, 2023. doi:10.61838/kman.aitech.1.3.4
• P. Borele and D. A. Borikar, “An approach to sentiment analysis using artificial neural networks,” IOSR J. Comput. Eng., vol. 18, no. 2, pp. 64–69, 2016. doi:10.9790/0661-1802056469
• P. Chakriswaran et al., “Emotion AI-driven sentiment analysis,” Appl. Sci., vol. 9, no. 24, p. 5462, 2019. doi:10.3390/app9245462
• H. S. Yang et al., “AI chatbots in clinical laboratory medicine,” Clin. Chem., vol. 69, no. 11, pp. 1238–1246, 2023. doi:10.1093/clinchem/hvad106
• A. R. Mathew, A. Al Hajj, and A. Al Abri, “Human-computer interaction (HCI): An overview,” in IEEE Int. Conf. Comput. Sci. Autom. Eng., 2011, pp. 99–100. doi:10.1109/CSAE.2011.5953178
• B. Myers et al., “Strategic directions in human-computer interaction,” ACM Comput. Surv., vol. 28, no. 4, pp. 794–809, 1996. doi:10.1145/242223.246855
• R. J. Lee-Won, Y. K. Joo, and S. G. Park, “Media Equation,” Int. Encycl. Media Psychol., 2020. doi:10.1002/9781119011071.iemp0158
• C. Bartneck, C. Rosalia, R. Menges, and I. Deckers, “Robot abuse – A limitation of the media equation,” Eindhoven Univ. Technol., n.d. [Online]. Available: http://www.bartneck.de
• D. Johnson and J. Gardner, “The media equation and team formation,” Int. J. Hum.-Comput. Stud., vol. 65, no. 2, pp. 111–124, 2007. doi:10.1016/j.ijhcs.2006.08.007
• O. Gillath et al., “Attachment and trust in AI,” Comput. Hum. Behav., vol. 115, p. 106607, 2021. doi: 10.1016/j.chb.2020.106607
• T. Xie and I. Pentina, “Attachment theory for chatbot relationships: A case study of Replika,” in Proc. HICSS, 2022. doi:10.24251/HICSS.2022.258
• D. Petters and E. Waters, “AI, attachment theory, and secure base simulation,” AISB 2010 Convention, 2010.
• L. Kambeitz-Ilankovic et al., “Review of digital and face-to-face CBT for depression,” npj Digit. Med., vol. 5, p. 144, 2022. doi:10.1038/s41746-022-00677-8
• H. M. Jackson et al., “Skill enactment in digital CBT,” J. Med. Internet Res., vol. 25, p. e44673, 2023. doi:10.2196/44673
• G. R. Thew, A. Rozental, and H. D. Hadjistavropoulos, “Advances in digital CBT,” Cogn. Behav. Ther., vol. 15, p. e44, 2022. doi:10.1017/S1754470X22000423
• L. Lawlor-Savage and J. L. Prentice, “Digital CBT in Canada: Ethical considerations,” Can. Psychol., vol. 55, no. 4, pp. 231–239, 2014. doi:10.1037/a0037861
• M. Farzan et al., “AI-powered CBT chatbots: A review,” Iran. J. Psychiatry, 2024. doi:10.18502/ijps.v20i1.17395
• B. Maples et al., “GPT3-enabled chatbots and suicide prevention,” npj Ment. Health Res., vol. 3, p. 4, 2024. doi: 10.1038/s44184-023-00047-6
• E. Gabarron, D. Larbi, K. Denecke, and E. Årsand, “Chatbots in public health,” Stud. Health Technol. Inform., IOS Press, 2020.
• V. K. Voola et al., “AI chatbots in clinical trials,” Int. J. Res. Publ. Seminar, vol. 13, no. 5, pp. 323–337, 2022. doi:10.36676/jrps.v13.i5.1505
• L. T. Car et al., “Conversational agents in health care: Scoping review and conceptual analysis,” J. Med. Internet Res., vol. 22, no. 8, p. e17158, 2020. doi:10.2196/17158
• M. Laymouna et al., “Roles, users, benefits, and limitations of chatbots in health care: Rapid review (preprint),” 2024. doi: 10.2196/preprints.56930
• D. S. Parikh and H. Raval, “Limitations of existing chatbots: An analytical survey,” Int. J. Innov. Res. Sci. Eng. Technol., vol. 7, no. 2, 2020.
• V. S. Barletta et al., “Clinical-chatbot AHP evaluation based on ‘quality in use’ of ISO/IEC 25010,” Int. J. Med. Inform., vol. 170, p. 104951, 2023. doi:10.1016/j.ijmedinf.2022.104951
• H. S. Yang et al., “AI chatbots in clinical laboratory medicine: Foundations and trends,” Clin. Chem., vol. 69, no. 11, pp. 1238–1246, 2023. doi:10.1093/clinchem/hvad106
• E. Ortega-Ochoa et al., “The effectiveness of empathic chatbot feedback in online higher education,” Internet Things, vol. 25, p. 101101, 2024. doi:10.1016/j.iot.2024.101101
• M. Rostami and S. Navabinejad, “Artificial empathy: User experiences with emotionally intelligent chatbots,” AI Tech Behav. Soc. Sci., vol. 1, no. 3, pp. 19–27, 2023. doi:10.61838/kman.aitech.1.3.4
• R. Indellicato, “Artificial intelligence and social-emotional learning: What relationship?” J. Mod. Sci., vol. 60, no. 6, pp. 460–470, 2024. doi:10.13166/jms/196765
• S. S. Sethi and K. Jain, “AI technologies for social-emotional learning,” J. Res. Innov. Teach. Learn., vol. 17, no. 2, pp. 213–225, 2024. doi:10.1108/JRIT-03-2024-0073
• M. I. Gómez-León, “Development of empathy through socioemotional AI,” Papeles del Psicólogo, vol. 43, no. 3, p. 218, 2022. doi:10.23923/pap.psicol.2996
• K. Heljakka, P. Ihamäki, and A. I. Lamminen, “Empathic responses to robot dogs vs. real dogs in learning,” in Proc. CHI PLAY '20, pp. 262–266, 2020. doi:10.1145/3383668.3419900
• C. Akbulut et al., “All too human? Mapping and mitigating risks from anthropomorphic AI,” AIES Conf., vol. 7, pp. 13–26, 2024. doi:10.1609/aies.v7i1.31613
• C. Montemayor, J. Halpern, and A. Fairweather, “In principle, there are obstacles for empathic AI in healthcare,” AI & Society, vol. 37, no. 4, pp. 1353–1359, 2022. doi:10.1007/s00146-021-01230-z
• M. Rubin, H. Arnon, J. D. Huppert, and A. Perry, “Considering human empathy in AI-driven therapy (preprint),” 2024. doi:10.2196/preprints.56529
• R. Agrawal and N. Pandey, “Developing rapport with emotionally intelligent AI assistants,” Int. J. Res. Appl. Sci. Eng. Technol., vol. 12, no. 3, pp. 1473–1480, 2024. doi: 10.22214/ijraset.2024.59015
• A. McStay, “Emotional AI and privacy,” Big Data & Society, vol. 7, no. 1, p. 205395172090438, 2020. doi:10.1177/2053951720904386
• K. Roemmich, F. Schaub, and N. Andalibi, “Emotion AI at work,” in Proc. CHI Conf. Hum. Factors Comput. Syst., pp. 1–20, 2023. doi:10.1145/3544548.3580950
• E. Sedenberg and J. Chuang, “Smile for the camera: Privacy implications of emotion AI,” UC Berkeley School of Information, n.d. [Online]. Available: https://www.ischool.berkeley.edu/research/publications/smile-camera-privacy-and-policy-implications-emotion-ai
• L. Rhue, “Racial influence on automated perceptions of emotions,” SSRN Electron. J., 2018. doi:10.2139/ssrn.3281765
• M. Yoshie and D. A. Sauter, “Cultural norms in nonverbal emotion expression,” Emotion, vol. 20, no. 3, pp. 513–517, 2020. doi:10.1037/emo0000580
• M. Mattioli and F. Cabitza, “Ethics in automatic face emotion recognition,” Mach. Learn. Knowl. Extr., vol. 6, pp. 2201–2231, 2024. doi: 10.3390/make6040109
• M. Nagata and K. Okajima, “Observer culture and facial expression recognition,” PLoS ONE, vol. 19, no. 10, p. e0313029, 2024. doi:10.1371/journal.pone.0313029
• I. Dominguez-Catena, D. Paternain, and M. Galar, “Metrics for dataset demographic bias in facial expression recognition,” arXiv preprint, arXiv:2303.15889, 2024. [Online]. Available: https://arxiv.org/abs/2303.15889
• G. Benitez-Garcia, T. Nakamura, and M. Kaneko, “Facial expression recognition with Fourier descriptors,” J. Signal Inf. Process., vol. 8, no. 3, 2017. doi:10.4236/jsip.2017.83009
• R. Pusztahelyi and I. Stefán, “Social robots and data protection,” Acta Univ. Sapientiae, Legal Studies, vol. 11, no. 1, pp. 95–118, 2022. doi:10.47745/AUSLEG.2022.11.1.06
• E. Schwitzgebel, “AI systems must not mislead about sentience,” Patterns, vol. 4, no. 8, p. 100818, 2023. doi:10.1016/j.patter.2023.100818
• M. S. Farahani and G. Ghasemi, “Artificial intelligence and inequality,” Qeios, 2024. doi:10.32388/7HWUZ2
• A. Hagerty and I. Rubinov, “Global AI ethics: Review of social impacts,” arXiv preprint, arXiv:1907.07892, 2019. [Online]. Available: https://arxiv.org/abs/1907.07892.
• P. Choudhury, R. T. Allen, and M. G. Endres, “ML for pattern discovery in management research,” Strat. Manag. J., vol. 42, no. 1, pp. 30–57, 2021. doi:10.1002/smj.3215.