Application of Latent Dirichlet Allocation (LDA) and BERTopic Algorithms for Headline and Topic Analysis of Palestine–Israel Conflict News in Indonesian Online Media

The news coverage of the Palestine–Israel conflict has become one of the most dominant international issues in Indonesian online media, necessitating a systematic analysis to understand the topic structures formed from the intensity and variation of the narratives presented. The main challenges arise from the high volume of text, differences in writing styles across media outlets, and the diversity of terminology, all of which hinder consistent and manual topic identification. To address these challenges, this study proposes a combined and comparative approach using two topic modeling algorithms, LDA and BERTopic, to obtain a more accurate, structured, and interpretable topic mapping. The modeling process begins with data collection through web scraping, followed by a preprocessing stage consisting of cleansing, case folding, tokenization, normalization, filtering, and stemming. The LDA model is developed by determining the optimal number of topics based on Coherence Score and Perplexity, whereas BERTopic leverages transformer-based embeddings, UMAP dimension reduction, and HDBSCAN clustering. Evaluation is conducted using Coherence Score, Perplexity, Silhouette Score, and visualizations such as Intertopic Distance Maps and Word Clouds to assess topic quality. The results show that BERTopic achieves the highest coherence score of 0.99 and lower perplexity, producing semantically cohesive topics. Meanwhile, LDA remains advantageous in providing a stable and measurable probabilistic structure. The combination of both models yields a mapping of five main topics: attacks in Gaza, Indonesian diplomacy, international support, humanitarian issues, and global political dynamics. These findings demonstrate that integrating LDA and BERTopic enhances the quality of topic analysis on complex issues