Survey on psychotherapy chatbots
The DOI matches its Crossref record; 18 of the 18 references it cites were found in a registry or an index.
Abstract
This survey aims to investigate, analyze, and compare the state‐of‐the‐art chatbots' feasibility and defects for psychotherapy. The survey points out a series of tasks necessary for future psychotherapy chatbots. We searched about 1200 related literature in public databases and selected five typical and state‐of‐the‐art psychotherapy chatbots. Most of the state‐of‐the‐art psychotherapy chatbots use retrieval‐based methods to generate dialogs. Some psychotherapy chatbots incorporate psychological theories, such as cognitive behavior therapy, to solve unique psychological problems. The assessments show that chatbots can preliminarily recognize specific kinds of negative emotions and give relatively appropriate responses. The randomized controlled trials prove that psychotherapy chatbots are useful for some people with a mental health condition. Compared with real psychologists, psychotherapy chatbots have some advantages, such as accessibility without the limitation on time or location. However, some critical technical obstacles limit the usage of psychotherapy chatbots. The limitations require a series of necessary tasks for more effective and safer psychotherapy chatbots, such as collecting standard, valid, real, and rich corpora. In conclusion, current psychotherapy chatbots can hardly replace human psychologists in the short term, but they can improve human psychologists' effectiveness and efficiency as an auxiliary tool.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Hochreiter, S., & Schmidhuber, J. (1997) · Neural Computation · doi:10.1162/neco.1997.9.8.1735 · Cited by 102,318
LeCun, Y., Bengio, Y., & Hinton, G. (2015) · Nature · doi:10.1038/nature14539 · Cited by 84,126
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
ELIZA—a computer program for the study of natural language communication between man and machine
Weizenbaum, J. (1966) · Communications of the ACM · doi:10.1145/365153.365168 · Cited by 4,452
Emotion knowledge: further exploration of a prototype approach
Shaver, P., Schwartz, J., Kirson, D., & O'Connor, C. (1987) · Journal of Personality and Social Psychology · doi:10.1037/0022-3514.52.6.1061 · Cited by 3,072
Fitzpatrick, K. K., Darcy, A., & Vierhile, M. (2017) · JMIR Mental Health · doi:10.2196/mental.7785 · Cited by 2,730
Livingston, J. D., & Boyd, J. E. (2010) · Social Science & Medicine · doi:10.1016/j.socscimed.2010.09.030 · Cited by 1,677
Detecting and monitoring depression with a two-item questionnaire (PHQ-2)
Löwe, B., Kroenke, K., & Gräfe, K. (2005) · Journal of Psychosomatic Research · doi:10.1016/j.jpsychores.2004.09.006 · Cited by 1,473
The efficacy of psychodynamic psychotherapy
Shedler, J. (2010) · American Psychologist · doi:10.1037/a0018378 · Cited by 1,452
Inkster, B., Sarda, S., & Subramanian, V. (2018) · doi:10.2196/preprints.12106 · Cited by 1,063
Research works printed but not linked: 56
- CuiL HuangS WeiF TanC DuanC ZhouM.Superagent: A customer service chatbot for e‐commerce websites. Paper presented at: Proceedings of Association for Computational Linguistics Association for Computational Linguistics; 2017; Vancouver Canada:97‐102. · DOI · Paper page
- YanZ DuanN BaoJ ChenP ZhouM LiZ Zhou J.Docchat: An information retrieval approach for chatbot engines using unstructured documents. Paper presented at: Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers); 2016; Berlin Germany: Association for Computational Linguistics:516‐525. · DOI · Paper page
- Dai Y, 2018, Survey of Intelligent Chatbot Technology, Comput Sci Appl, 8, 918
- Nuruzzaman M. &Hussain O. K.A survey on chatbot implementation in customer service industry through deep neural networks. Paper presented at: 2018 IEEE 15th ICEBE; 2018; Xian China: IEEE:54‐61. · DOI · Paper page
- 10.1016/j.jbusres.2018.10.004 · DOI · Paper page
- ZhouH HuangM ZhangT ZhuX LiuB.Emotional chatting machine: Emotional conversation generation with internal and external memory. Paper presented at: Thirty‐Second AAAI Conference on Artificial Intelligence; 2018; New OL: AAAI Press:730‐738. · DOI · Paper page
- Lokman AS, 2018, Proceedings of the Future Technologies Conference
- 10.18653/v1/P17-2079 · DOI · Paper page
- 10.1016/S0140-6736(18)32279-7 · DOI · Paper page
- 10.1037/12050-000 · DOI
- 10.1037/10110-007 · DOI
- Miller WR, 2012, Motivational Interviewing: Helping People Change
- Raskin NJ, 2005, Current Psychotherapies
- 10.1097/00004583-200206000-00005 · DOI
- 10.1016/S0747-5632(01)00004-8 · DOI
- 10.1109/CoDIT.2016.7593646 · DOI
- 10.1109/ICACCI.2016.7732476 · DOI · Paper page
- 10.1109/ICASSP.2011.5947611 · DOI · Paper page
- 10.1016/j.eswa.2016.10.065 · DOI · Paper page
- YinJ ChenZ ZhouK YuC.A deep learning based chatbot for campus psychological therapy; 2019. arXiv preprint arXiv:1910.06707. · arXiv
- Parrott WG, 2001, Emotions in Social Psychology: Essential Readings
- Balahur A, 2011, Proceedings of the 2nd workshop on computational approaches to subjectivity and sentiment analysis, 53
- Liu Y, 2013, Proceedings of the 51st Annual Meeting of the Association for Computational Linguistics: System Demonstrations, 67
- LiJ GalleyM BrockettC GaoJ DolanB.A diversity‐promoting objective function for neural conversation models; 2015. arXiv preprint arXiv:1510.03055. · arXiv
- Adiwardana D. Luong M. T. So D. R. Hall J. Fiedel N. Thoppilan R. … &Le Q. V.Towards a human‐like open‐domain chatbot; 2020. arXiv preprint arXiv:2001.09977. · arXiv
- 10.1016/j.jsat.2016.01.006 · DOI · Paper page
- 10.1016/j.future.2020.02.042 · DOI
- Cambria E, 2009, AffectiveSpace: Blending common sense and affective knowledge to perform emotive reasoning, WOMSA at CAEPIA, Seville, 32
- 10.1145/604045.604067 · DOI · Paper page
- 10.1007/11527886_9 · DOI
- Tripathi S, 2017, Twenty‐Ninth IAAI Conference, 4746
- 10.30773/pi.2018.12.21.2 · DOI · Paper page
- RamA PrasadR KhatriC VenkateshA GabrielR LiuQ KingE.Conversational ai: The science behind the alexa prize; 2018. arXiv preprint arXiv:1801.03604. · arXiv
- 10.3115/1556328.1556341 · DOI · Paper page
- 10.1037/0022-3514.54.6.1063 · DOI · Paper page
- 10.1192/bjpo.bp.115.001685 · DOI · Paper page
- 10.2196/12106 · doi:10.2196/12106 · Paper page
- 10.1001/archinte.166.10.1092 · DOI · Paper page
- 10.1142/7567 · doi:10.1142/7567
- Zhuge H, 2019, Cyber‐Physical‐Social Intelligence: On Human‐Machine‐Nature Symbiosis
- 10.1007/978-981-13-7311-4_5 · doi:10.1007/978-981-13-7311-4_5
- 10.1016/0022-0965(79)90044-4 · DOI · Paper page
- 10.1016/0010-0285(73)90023-6 · DOI · Paper page
- 10.1002/cpe.870 · DOI
- 10.1016/j.artint.2010.09.009 · DOI · Paper page
- 10.1007/978-0-387-72772-1 · doi:10.1007/978-0-387-72772-1
- 10.1109/TSC.2011.12 · DOI
- 10.1145/1391949.1391954 · DOI
- 10.1016/j.artint.2009.11.014 · DOI
- 10.1007/978-981-13-7311-4_3 · DOI
- Zhuge H, 2016, Multi‐Dimensional Summarization in Cyber‐Physical Society
- 10.1007/978-981-13-7311-4_9 · doi:10.1007/978-981-13-7311-4_9
- 10.1007/978-981-13-7311-4_10 · doi:10.1007/978-981-13-7311-4_10
- 10.1109/TKDE.2008.141 · DOI · Paper page
- 10.1002/cpe.1097 · DOI
- 10.1145/2974804.2974820 · DOI · Paper page
Cited by
Chatbots: Security, privacy, data protection, and social aspects
Hasal, M., Nowaková, J., Ahmed Saghair, K., Abdulla, H., Snášel, V., & Ogiela, L. (2021) · Concurrency and Computation: Practice and Experience · doi:10.1002/cpe.6426 · Cited by 249
He, Y., Yang, L., Qian, C., Li, T., Su, Z., Zhang, Q., & Hou, X. (2023) · Journal of Medical Internet Research · doi:10.2196/43862 · Cited by 213
“…studies found that users establish therapeutic bonds with chatbots [21-24]; and other studies revealed some hazards associated with CAIs, including misunderstanding that may result in inefficient or even harmful interventions, a lack of crisis warning systems, and a lack of privacy protection [25].”
He, Y., Yang, L., Zhu, X., Wu, B., Zhang, S., Qian, C., & Tian, T. (2022) · Journal of Medical Internet Research · doi:10.2196/40719 · Cited by 178
“However, studies have shown that mental health chatbots have some risks as well, such as “misunderstanding,” which may lead to ineffective or even harmful interventions, lack of crisis warning mechanisms, and lack of privacy protection [21].”
Developing a natural language-based AI-chatbot for social work training: an illustrative case study
Chan, C., & Li, F. (2023) · China Journal of Social Work · doi:10.1080/17525098.2023.2176901 · Cited by 27
Sun, X. (2023) · 28th International Conference on Intelligent User Interfaces · doi:10.1145/3581754.3584115 · Cited by 3
He, Y., Yang, L., Zhu, X., Wu, B., Zhang, S., Qian, C., & Tian, T. (2022) · doi:10.2196/preprints.40719 · Cited by 3
Liu, I., Chen, W., Ge, Q., Song, D., & Ni, S. (2022) · Proceedings of the Tenth International Symposium of Chinese CHI · doi:10.1145/3565698.3565787 · Cited by 3
“[17], [31].”
Background
Metadata
- Authors
- Xu, B., & Zhuang, Z.
- Venue
- Concurrency and Computation: Practice and Experience
- Publisher
- Wiley
- Published
- 2020-12-28
- Volume
- 34
- Issue
- 7
- ISSN
- 1532-0626 (ISSN-L)
- 1532-0634
- OpenAlex
- W3115692466
- Cited by
- 47
- References
- 18
- FWCI
- 4.11
- Type
- journal article
- Language
- en
- Open access
- closed
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.