Recent Trends in Web Intelligence and Agent Technology: Hybrid Topic Modeling Approaches

Digitalization and the widespread use of the internet have resulted in an exponential growth of information in the contemporary era. Determining the key themes in various fields has become essential for researchers and leaders to stay current. This study presents the design and implementation of several strategies for identifying topics within “Web Intelligence” and “Intelligent Agent Technology” to explore recent trends. To do this, the BERTopic model was hybridized with traditional topic modeling methods such as Latent Dirichlet Allocation (LDA), Non-Negative Matrix Factorization (NMF), and Latent Semantic Analysis (LSA). The coherence of these hybrid models was compared, and the resulting topics were analyzed. The findings indicate that the NMF-BERT method outperformed the others. The final analysis revealed that the main trends in the field include personalized information and search services, customer behavior analysis, e-commerce, artificial intelligence, decision support systems, and individualized education, driven by pervasive digitalization and internet use. The findings, highlighting trends such as personalized services and AI-driven decision support systems, offer actionable insights relevant to multiple sectors navigating digital transformation.