Improve semantic similarity based on statistical approach and LLM based transformer model for extractive summarization

This study addresses the need for effective extractive text summarization methods specifically designed for Indonesian news texts, driven by the increasing volume of digital information and persistent challenges related to semantic drift and coherence instability. A key challenge in extractive summarization lies in maintaining semantic fidelity while preserving informative content and ensuring computational efficiency, particularly for morphologically complex languages such as Indonesian. To address this issue, this research proposes a hybrid extractive summarization approach that integrates statistical methods, namely Term Frequency–Inverse Document Frequency (TF-IDF) and Latent Semantic Analysis (LSA), with Indonesian-specific transformer models, including IndoBERT and GPT, to enhance semantic similarity measurement during sentence selection. The proposed framework employs a weighted hybrid formulation (α·TF-IDF + β·LSA + γ·IndoBERT + δ·GPT), combined with cosine similarity computation and diversity-aware sentence selection. The approach is evaluated under a consistent experimental setting using the Indonesian subset of the XL-Sum dataset, with experiments conducted on TPU V2-8 infrastructure. Experimental results demonstrate competitive performance across the evaluated baseline components. The TF-IDF + LSA model achieved the highest ROUGE-1 score of 63.76%, while the TF-IDF + Cosine Similarity model showed balanced performance across ROUGE metrics with a cosine similarity score of 0.8538. IndoBERT + Cosine Similarity and GPT + Cosine Similarity achieved higher semantic similarity scores, with GPT reaching 0.8677. Overall, the proposed approach demonstrates substantial improvements over Indonesian extractive summarization baselines under the same dataset and evaluation protocol, highlighting the effectiveness of hybrid statistical-transformer integration for low-resource language summarization.