Hybrid Extractive Abstractive Summarization for Multilingual Sentiment Analysis

TL;DR

This paper introduces a hybrid multilingual sentiment analysis method combining extractive and abstractive summarization, improving accuracy and efficiency across multiple languages, especially low-resource ones.

Contribution

It presents a novel hybrid model integrating TF-IDF extraction with a fine-tuned XLM-R abstractive module, enhancing multilingual sentiment analysis performance.

Findings

Achieves 0.90 accuracy in English and 0.84 in low-resource languages.

Demonstrates 22% greater computational efficiency than traditional methods.

Effective for real-time brand monitoring and cross-cultural discourse analysis.

Abstract

We propose a hybrid approach for multilingual sentiment analysis that combines extractive and abstractive summarization to address the limitations of standalone methods. The model integrates TF-IDF-based extraction with a fine-tuned XLM-R abstractive module, enhanced by dynamic thresholding and cultural adaptation. Experiments across 10 languages show significant improvements over baselines, achieving 0.90 accuracy for English and 0.84 for low-resource languages. The approach also demonstrates 22% greater computational efficiency than traditional methods. Practical applications include real-time brand monitoring and cross-cultural discourse analysis. Future work will focus on optimization for low-resource languages via 8-bit quantization.