Sentiment analysis of short text has posed a great challenge in natural language processing, particularly for context-rich and low-resource languages such as Vietnamese. Review texts generated by users are usually brief, therefore they do not explicitly express their sentiments. Consequently, it is difficult for traditional models to process those reviews. This paper introduces a new approach by embracing the strengths of large language models in filling this gap of context scarcity. The method works primarily through 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 way to deal with the problem of missing context in low-resource languages. This will bring value to both the commercial world and academic study.