An empirical study on sentiment analysis for Vietnamese

Abstract

This paper presents an empirical study on machine learning based sentiment analysis for Vietnamese, in which we focus on the task of sentiment classification. We investigate the task regarding both learning model and linguistics feature aspects. We also introduce an annotated corpus for sentiment classification extracted from hotel reviews in Vietnamese and conduct a series of experiments and analyses on that corpus. The paper provides useful information for further research as well as for building a real sentiment analysis system for Vietnamese.