On Vietnamese Sentiment Analysis: A Transfer Learning Method

Abstract

Sentiment analysis (also known as opinion mining or emotion AI) refers to the use of natural language processing (NLP) and text analysis to systematically identify, extract and quantify states and subjective information. Transfer learning (TL) [1] is a study in machine learning focusing on storing knowledge gained while solving one problem and applying it to a different but related problem. In NLP, recent results also demonstrated the effectiveness of models using pre-training on a language modeling task [2], [3]. The transfer learning based models help to rapidly increase understanding of words and sentences arrangement in which semantics and connections are easily grasped. In this paper, we present the results from applying BERT [16], a transfer learning method, in Vietnamese benchmark [17] for one of text classification problems, the Aspect Based Sentiment Analysis problem. The experiments were conducted on two data sets, named Hotel and Restaurant [17], in two task (A) Aspect Detection and (B) Aspect Polarity. The obtained results have outperformed some previous systems [18]-[20] in precision, recall, as well as the F1 measures.