A Bibliometric Analysis of Natural Language Processing in the Study of Human Behavior

Over the past decade, Natural Language Processing (NLP) has emerged as a key tool for understanding human behavior through large-scale textual data. However, the rapid increase in publications has led to fragmentation that makes it difficult to identify clear trends, thematic gaps, and emerging research areas. This situation limits the development of focused studies and hinders interdisciplinary collaboration in fields such as mental health, education, and social media analysis. The aim of this study is to conduct a bibliometric analysis to map the scientific evolution of NLP research applied to human behavior, highlighting key topics, collaboration networks, and future research directions. Following the PRISMA 2020 guidelines, a final corpus of 22 articles from the Scopus database (2010-2024) was analyzed using the Bibliometrix software package for quantitative analysis. The results reveal a steady growth in scientific output, with a thematic concentration in sentiment analysis, digital mental health, and emotion detection. Strong collaboration networks were identified in North America, Europe, and Asia, although low participation from regions in Latin America and Africa was noted. This study provides a comprehensive overview of the current landscape, highlighting research opportunities and the need to develop explainable and ethically auditable models to guide future interdisciplinary work.