Enhance a Deep Neural Network Model for Twitter Sentiment Analysis by Incorporating User Behavioral Information

Sentiment analysis on social media such as Twitter has become a very important and challenging task. Most existing sentiment classification methods for social media detect the sentiment polarity primarily based on the textual content and neglect of other information. Therefore, in this paper, we propose a neural network model that incorporates user behavioral information with a given document (tweet). The neural network used in this paper is Convolutional Neural Network (CNN). The system is evaluated on two datasets provided by SemEval. The proposed model outperforms the baselines. That means going beyond the content of tweets benefits sentiment classification; providing the classifier with a deep understanding of the task.