Hybrid Clustering for Subject Classification Analysis: A Case Study of the Psychology, Sociology, and Education Domain

Abstract

This paper presents a novel approach to subject classification analysis using hybrid clustering techniques, focusing specifically on the interdisciplinary domain of psychology, sociology, and education. Traditional subject classification methods often face challenges in effectively capturing the complex and overlapping nature of interdisciplinary research areas. In response to these challenges, this study proposes a hybrid clustering framework that integrates multiple clustering algorithms, including hierarchical clustering, k-means clustering, and density-based clustering, to analyze and classify scholarly literature in the psychology, sociology, and education domain. Through a case study approach, utilizing a comprehensive dataset of scholarly publications from leading journals and databases, the research demonstrates the effectiveness of the hybrid clustering approach in identifying distinct subject clusters, capturing interdisciplinarity, and revealing emerging research trends and thematic areas within the domain. Moreover, the study explores the interpretability and robustness of the clustering results through qualitative analysis and expert validation. The findings contribute to advancing methodological approaches for subject classification analysis, particularly in interdisciplinary research domains, and offer insights for researchers, librarians, and information professionals involved in knowledge organization and information retrieval.