Text Sentiment Analysis Based on Emotion Adjustment

Abstract

Text sentiment analysis is used to find out how much the public’s appreciation and preferences for specific events or objects. In order to effectively extract the deep emotional features of words, this paper proposes two sentiment analysis methods, which are emotion adjustment method based on semantic similarity and skip-gram model. In these two methods, word vectors containing semantic information obtained from Word2vec and emotional seeds are used to adjust the sentiment orientation of the words so that word vectors can trained both the semantic information and the sentiment contents. And the TF-IDF method is used to calculate the word’s weight in the text, the vector of the whole text is represented by adding the weighted word vectors. Experiments show that the emotion-adjusted word vector improves the accuracy of the text sentiment analysis more effectively than the traditional method, and proves the validity of these two methods in the sentiment analysis task. At the same time, the emotion adjustment method based on skip-gram model is more effective than the method based on semantic similarity.