A Study of the Application of Weight Distributing Method Combining Sentiment Dictionary and TF-IDF for Text Sentiment Analysis

The most commonly used methods in text sentiment analysis are rule-based dictionary and machine learning, with the later referring to use of vectors represent followed by learning classify vectors. Both have their limitations, including inflexibility rules, non-prominence words. In this paper, we design a weight distributing method combining two for analysis, which sentence obtained can both highlight words meanings while retaining information. Empirical results show that based on new method, accuracy rate reach as high 82.1%, means 13.9% higher than 7.7% TF-IDF weighting method.