Conversational Agents for Mental Health and Wellbeing

Abstract

Recent advances in spoken language technology, artificial intelligence, and conversational interface design, coupled with the emergence of smart devices, have increased the possibilities of using conversational interfaces for a growing range of application domains. These interfaces are currently applied in the healthcare domain in a range of innovative tasks that allow to provide a more natural an user-friendly human-machine communication, promote patient participation in their own care, and help and support medical professionals. This chapter provides a detailed description of the great potential for the use of conversational interfaces for the specific area of mental health by means of the description of their most valuable applications in this domain and the open challenges for future research.

Reducing social diabetes distress with a conversational agent support system: a three-week technology feasibility evaluation

“…Furthermore, our finding adds social diabetes distress to the long list of problems that a conversational agent can potentially address (e.g. ( 24 , 25 )). Investigating a potential reason underlying the positive effects of a conversational agent as an intervention, we hypothesised that the attitude of the participant towards the intervention (either the conversational agent or the self-help text) might have a mediation effect on diabetes distress difference ( H2 ).…”

“…Conversational agents have shown to be effective in the mental health domain, for example, by delivering cognitive behaviour therapy to people with symptoms of depression and anxiety ( 22 ) or by using elements of motivational interviewing and social cognitive therapy to promote exercising and a healthier diet to users ( 23 ). Many other examples of conversational agents in health exist, for example, conversational agents used for applying therapy, self-management, intervention and counselling successfully (see for an overview ( 24 , 25 )). Recently, mobile app-based interactive conversational agents to support people with type-2 diabetes have been discussed, showing that the self-management education such systems offer can be accepted by the PWD ( 26 ) and that such systems can be effective in improving the reported health-related quality of life of the PWD ( 27 ).…”

Integrating Conversational Agents and Knowledge Graphs Within the Scholarly Domain

“…Within the health domain, there is great attention towards recent discoveries within the AI technologies with the goal to automatize services in health centers such as nursing homes and hospitals [2]. The work described by Callejas and Griol [12] illustrates some of the applications of conversational interfaces concerning the mental health sphere. Furthermore, the survey published by Montenegro et al [13] investigates approximately 4,145 articles related to conversational agents in health published from 2009 to 2019.…”

“…These KGs typically represent the relevant actors (such as institutions and researchers), scientific reports (such as patents, research articles), entities (such as concepts, technologies, tasks to solve), as well as additional information (such as funded projects, acknowledgements) in a structured organization. Nowadays, in the literature, we can find many large-scale KGs within the scholarly domain such as OpenCitations [17], Scopus 8 , Semantic Scholar 9 , Aminer [18], CORE 10 , ORKG 11 , OpenAlex 12 , and others. Given the amount of data and analytics that can be inferred and analyzed out of such a large amount of information represented by scholarly data, conversational agents could be leveraged to interact with the users and provide the information that is being analyzed.…”