Unleashing the Potential of Chatbots in Mental Health: Bibliometric Analysis

QING HAN Chenyang Zhao ^*

• Zhejiang Chinese Medical University, Hangzhou, China

Background: Chatbots have begun to flourish in the digital mental health space. They can make mental health services and support more accessible for many individuals. Objective: This study aims to provide a comprehensive bibliometric analysis and discussion on utilization of chatbots in mental health, and offer valuable insights into understanding the scientific patterns at the intersection of chatbots and mental health on a global scale. Methods: The bibliometric software Biblioshiny and VOSviewer are used to analyze 261 journal articles in Web of Science Core Collection published from 2015 to 2024. Publications distribution are analyzed to measure productivity on contries, institutions, and sources. Scientific collaboration networks are generated to analyze the influence as well as communications between countries and institutions. Research topics and trends are formulated by using a keyword co-occurrence network. Results: Over the last decade, researches on utilization of chatbots in mental health has appeared to be increasing steadily at an annual rate of 46.19%. The United States have made substantial contributions to the growth of publications. England came second to the US in terms of publications and citations, and followed by Australia, China, and France. National Center for Scientific Research in France ranked first among all institutions identified, followed by Imperial College London and University of Zurich. The number of articles published in the Journal of Medical Internet Research was exceptionally high, and JMIR Mental Health is the most influential publication sources. Collaboration among universities in the USA, United Kingdom, Switzerland, and Singapore demonstrated a high level. The keyword co-occurrence network highlights the representative techniques in this multidisciplinary area and reveals 5 research topics, showing a significant overlap between clusters. High frequency keywords such as “ChatGPT”, “machine learning”, and “large language models” represent the latest research trends and frontiers in this field. Conclusions: This study serves as a valuable resource for mental health experts without an AI background or individuals interested in the field of mental health chatbots. It indicates that chatbots play an important role in promoting mental health and have a great potential to exhibit empathy, curiosity, understanding, and a sense of working collaboratively with users.