Lexicon-based sentiment analysis of Facebook comments in Vietnamese language

Abstract

Social media websites like Twitter, Facebook etc. are a major hub for users to express their opinions online. Sentiment analysis which is also called opinion mining, involves in building a system to collect and examine opinions about the product made in blog posts, comments, or reviews. Sentiment analysis can be useful in real life. In this paper, we propose a lexicon based method for sentiment analysis with Facebook data for Vietnamese language by focus on two core component in a sentiment system. That is to build Vietnamese emotional dictionary (VED) including 5 sub-dictionaries: noun, verb, adjective, and adverb and propose features which based-on the English emotional analysis method and adaptive with traditional Vietnamese language and then support vector machine classification method to be use to identify the emotional of the user’s message. The experimental show that our system has very good performance.