Feature Expansion Word2Vec for Sentiment Analysis of Public Policy in Twitter

Abstract

Social media users, especially on Twitter, can freely express opinions or other information in the form of tweets about anything, including responding to a public policy. In a written tweet, there is a limit of 280 characters per tweet and this allows for problems such as vocabulary mismatches. Therefore, in this study, the feature expansion Word2vec method was applied to overcome when the vocabulary mismatches occur. This study implements and compares the Twitter sentiment analysis using the feature expansion Word2vec method and the baseline model. To perform classification on this sentiment data, two different machine learning algorithms including Support Vector Machine (SVM) and Logistic Regression (LR) are used to compare the model. The result is feature expansion Word2Vec with SVM classifier has a slightly better performance which succeeded in increasing the system accuracy up to 0,99% with 78,99% accuracy score, rather than LR classifier which achieved 78,31% accuracy score.