查看文章

Social media data are increasingly used for smart computing applications, e.g., social event detection and sentiment analysis. Sentiment analysis, an important natural language processing task, has been applied in many real-world applications such as recommender systems and intelligence business systems. To process such social media data, natural language processing techniques such as BERT can be applied to extract essential language representations and produce state-of-the-art results. In this paper, we utilize the pre-trained BERT model as the backbone network and propose the BERT-SAN model to perform aspect-based sentiment analysis. The result demonstrates that our proposed model has a significant improvement against other baselines.