Microblog Sentiment Analysis Based on Cross-media Bag-of-words Model

Abstract

Sentiment analysis on social networks has attracted ever increasing attention in recent years. To this end, most existing methods mainly focus on analyzing the textual information. This has faced huge difficulty as nowadays users are more likely to express their feelings in a hybrid manner not only with texts, but also with images. It is therefore essential to take images into account. In this paper, we propose a novel Cross-media Bag-of-words Model (CBM) for Microblog sentiment analysis. In this model, we represent the text and image of a Weibo tweet as a unified Bag-of-words representation. Based on this model, we use Logistic Regression to classify the Microblog sentiment. It performs well in the sentiment classification task since it doesn't require the conditional dependence assumption. We also use SVM and Naïve Bayes to make a comparison. Experiments on 5,000 Microblog messages demonstrate that our CBM model performs better than text-based methods. The sentiment classification accuracy on Microblog messages of our model is 80%, improved by 4% than the text-based methods.