Multilingual Sentiment Analysis of Summarized Texts: A Cross-Language Study of Text Shortening Effects
This addresses the problem of sentiment accuracy loss in multilingual applications due to summarization, offering insights for social media monitoring and market analysis, though it is incremental in proposing a hybrid approach.
The study investigated how extractive and abstractive summarization affect sentiment analysis across eight languages, finding that extractive summarization better preserves sentiment, especially in morphologically complex languages like Finnish and Hungarian, while abstractive summarization introduces distortion and reduces accuracy.
Summarization significantly impacts sentiment analysis across languages with diverse morphologies. This study examines extractive and abstractive summarization effects on sentiment classification in English, German, French, Spanish, Italian, Finnish, Hungarian, and Arabic. We assess sentiment shifts post-summarization using multilingual transformers (mBERT, XLM-RoBERTa, T5, and BART) and language-specific models (FinBERT, AraBERT). Results show extractive summarization better preserves sentiment, especially in morphologically complex languages, while abstractive summarization improves readability but introduces sentiment distortion, affecting sentiment accuracy. Languages with rich inflectional morphology, such as Finnish, Hungarian, and Arabic, experience greater accuracy drops than English or German. Findings emphasize the need for language-specific adaptations in sentiment analysis and propose a hybrid summarization approach balancing readability and sentiment preservation. These insights benefit multilingual sentiment applications, including social media monitoring, market analysis, and cross-lingual opinion mining.