Mapping and Visualizing the Intersection of Sentiment Analysis and Mental Health

Introduction: Sentiment analysis, a computational approach to evaluating emotions in textual data, has gained significance in mental health research. It assesses public sentiments on mental health issues and aids in early disorder detection through social media and digital platforms. Objectives: This study aims to analyze the intersection of sentiment analysis and mental health research, identifying key scholarly trends, thematic developments, and global collaborations from 2013 to 2024. Methods: A bibliometric analysis was conducted using 521 documents from Scopus, including journal articles, book chapters, and conference papers. Biblioshiny, VOSviewer, and CiteSpace were used to analyze publication trends, co-authorship networks, and keyword co-occurrences. Results: The field has grown at an annual rate of 42.45%, with research output peaking in 2023 (134 articles). Key themes include AI applications in mental health, sentiment-based diagnosis, and the impact of COVID-19. China, the USA, and Australia are the leading contributors, while Bangladesh and Switzerland have the highest citation impact per article. The study maps extensive international research collaborations. Conclusions: Sentiment analysis is an evolving field with global collaboration. Advances in machine learning and NLP enhance its potential for real-time mental health monitoring and predictive analysis. Future research should focus on personalized AI-driven interventions, ethical considerations, and expanding datasets to improve diagnostic accuracy. This study provides insights for researchers, practitioners, and policymakers in leveraging sentiment analysis for mental health advancements.