Chatbots and mental health: A scoping review of reviews

The majority of individuals presenting with mental disorders do not receive mental health services. The use of chatbots for mental health is now frequently discussed as a means to increase access to mental health resources. For this scoping review of reviews on chatbots for mental health, we performed a systematic search of the literature on Scopus, Web of Science, Pubmed and Dimensions.ai and identified 14 relevant reviews published in scientific journals which identified publications following a systematic search on two or more databases. Three additional relevant reviews were included following forward and backward reference examination. The 17 included reviews are: eight systematic reviews (three with meta-analysis), seven scoping reviews and two unlabeled reviews. We have summarized the scope of the reviews as well as their findings. Most reviews included at least one study with 15 participants or less. Few reviews report an important proportion of RCTs and some original publications most of the time report on piloting studies. Overall, the reviews examined the opinions of users of chatbots (generally good user’s perceptions although some find deterrents), the features of chatbots, the outcomes and measures in studies relying on chatbots, the effectiveness of chatbots (particularly the meta-analyses) for the alleviation of mental disorder symptomatology (three meta-analyses find effectiveness for depression, whereas other clinical targets might need further research) as well as their potential for the assessment of mental health. The use of machine learning and natural language processing frameworks (Dialogflow, RASA) seems to drive an increasing number of studies of chatbots for mental health. Overall, we conclude that there is potential for the use of chatbots for mental health, but that progress is necessary in following areas affecting interaction dynamics: reduction of the frequent lack of empathy and repetitiveness, inclusion of user assessment within the chatbot system, inclusion of a memory of past interactions. Large language models might be capable of reducing part of these issues and playing an increasingly important role in the field. Whether data privacy can be guaranteed to users is also an important question, which seems to be overlooked in the field.