Sentiment analysis using Latent Dirichlet Allocation and topic polarity wordcloud visualization

Abstract

Sentiment analysis is a field of study that analyzes sentiment. One method for doing sentiment analysis is Latent Dirichlet Allocation (LDA) that extracts the topic of documents where the topic is represented as the appearance of the words with different topic probability. Therefore, we need data representation in visual form that is easier to understand than text and tables. One form of data visualization is wordcloud that provides a visual representation of words frequency. This research will perform sentiment analysis from the students' comments toward a university, in this case the Universitas Diponegoro, using LDA and topic polarity wordcloud visualization. The purpose of this study is to generate the topic polarity wordcloud of the students' comments by using the best combination of parameters. The best combination is the parameter with the value of alpha 0.1, value of beta 0.1, number of topics 9, threshold 10−7, and perplexity values 8.07. Such parameter combination produces 3 topics as positive sentiment and 6 topics as negative sentiment. In addition, we also compare the proposed method to several algorithms such as Naïve Bayes and Logistic Regression. The final result shows that the proposed method outperforms the Naïve Bayes and Logistic Regression in terms of F-Measure by 61%, 54%, and 56%, respectively.