An overview of the features of chatbots in mental health: A scoping review

By Alaa A. Abd-alrazaq, Mohannad Alajlani, Ali Abdallah Alalwan, Bridgette M. Bewick, Peter H Gardner, Mowafa Said Househ. Int. J. Medical Informatics, 2019

475 citations recorded by the source corpus.

BACKGROUND Chatbots are systems that are able to converse and interact with human users using spoken, written, and visual languages. Chatbots have the potential to be useful tools for individuals with mental disorders, especially those who are reluctant to seek mental health advice due to stigmatization. While numerous studies have been conducted about using chatbots for mental health, there is a need to systematically bring this evidence together in order to inform mental health providers and potential users about the main features of chatbots and their potential uses, and to inform future research about the main gaps of the previous literature. OBJECTIVE We aimed to provide an overview of the features of chatbots used by individuals for their mental health as reported in the empirical literature. METHODS Seven bibliographic databases (Medline, Embase, PsycINFO, Cochrane Central Register of Controlled Trials, IEEE Xplore, ACM Digital Library, and Google Scholar) were used in our search. In addition, backward and forward reference list checking of the included studies and relevant reviews was conducted. Study selection and data extraction were carried out by two reviewers independently. Extracted data were synthesised using a narrative approach. Chatbots were classified according to their purposes, platforms, response generation, dialogue initiative, input and output modalities, embodiment, and targeted disorders. RESULTS Of 1039 citations retrieved, 53 unique studies were included in this review. The included studies assessed 41 different chatbots. Common uses of chatbots were: therapy (n = 17), training (n = 12), and screening (n = 10). Chatbots in most studies were rule-based (n = 49) and implemented in stand-alone software (n = 37). In 46 studies, chatbots controlled and led the conversations. While the most frequently used input modality was written language only (n = 26), the most frequently used output modality was a combination of written, spoken and visual languages (n = 28). In the majority of studies, chatbots included virtual representations (n = 44). The most common focus of chatbots was depression (n = 16) or autism (n = 10). CONCLUSION Research regarding chatbots in mental health is nascent. There are numerous chatbots that are used for various mental disorders and purposes. Healthcare providers should compare chatbots found in this review to help guide potential users to the most appropriate chatbot to support their mental health needs. More reviews are needed to summarise the evidence regarding the effectiveness and acceptability of chatbots in mental health.

Subfields: Applied Psychology, Artificial Intelligence, Social Psychology

View Paper: https://www.semanticscholar.org/paper/ee757d582438057b79e60bf410bc459279398d73

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Applied Psychology

In Artificial Intelligence

In Social Psychology

Citations in the corpus

Large language models could change the future of behavioral healthcare: a proposal for responsible development and evaluation (2024, background): “Forexample,mentalhealthchatbotsWoebot andTessa,whichtargetdepressionandeatingpathologyrespectively 10,11 ,are rule-based and do not use LLMs (i.e., the application ’ s content is human-generated, and the chatbot ’ s responds based on prede ﬁ ned rules or decision trees 12 ).”
Artificially intelligent chatbots in digital mental health interventions: a review (2021, methodology): “Chatbots employing principles of cognitive behavioral therapy (CBT) are the most common and well-studied; one meta-analysis found that 10 out of 17 chatbots primarily used CBT [86].”
An Overview of Chatbot-Based Mobile Mental Health Apps: Insights From App Description and User Reviews (2022, unknown): “Recent research on MH apps in general points out that patient safety is rarely examined, health outcomes are evaluated on a small scale, and no standard evaluation methods are present [14], and these findings also apply to MH chatbot apps.”
Systematic review and meta-analysis of AI-based conversational agents for promoting mental health and well-being (2023, background): “The detailed results of subgroup analysis are presented in Supplementary Table 6.”
On the Safety of Conversational Models: Taxonomy, Dataset, and Benchmark (2021, background): “For example, conversational models are expected to understand the user’s psychological state, so as to avoid giving replies that might aggravate depression or even induce suicides (Vaidyam et al., 2019; Abd-Alrazaq et al., 2019).”
AI in mental health. (2020, background): “User satisfaction with chatbots is good and preliminary evidence for efﬁcacy is reasonably favourable [38,39].”