The Selection and Optimization of a Negative comment Identification Method

Abstract

This paper introduces the research background and significance of negative comments, and analyzes the present situation and development trend of negative comments identification at home and abroad. Several popular classification algorithms of naive Bayes, support vector machines and neural network are introduced. The word bag model, TF-IDF model and Word2Vec/Doc2Vec model feature model are also introduced. The data of feature extraction and classification algorithm in IMDB movie review website are simulated, and the results are compared and analyzed, and an optimal combination of feature extraction and classification algorithm is obtained.