Context-Enriched Sentiment Analysis for Short Vietnamese Restaurant Reviews Using Large Language Models

Sentiment analysis of short text has posed a significant challenge in natural language processing, particularly for context rich and low-resource languages such as Vietnamese. User generated texts are usually brief therefore, they do not explicitly express their sentiments. Consequently, traditional models struggle to process those reviews. This paper introduces a new approach that leverages the strengths of large language models to address the gap in context scarcity. The method works primarily in two ways: a) by feeding in structured metadata, such as restaurant name and location, directly into the model input, and b) using large language models to automatically generate likely contextual sentences so that short reviews become long informative statements. Results from comprehensive experiments carried out on a newly assembled Vietnamese food review dataset show improved sentiment analysis output based on this kind of context enrichment, beating several strong baselines, including the state of-the-art monolingual PhoBERT model, particularly when it came to resolving semantic vagueness typical of ultra-short word reviews or even short reviews with implicit subjects. This work offers a strong, flexible approach to addressing the problem of missing context in low-resource languages. This will bring value to both the commercial world and academic study.