Analysis of Text Emotion Based on Logistic Regression Model
Chengxiang Wen, Jiaoyi Wu, Dan Chen · 2022 IEEE 5th International Conference on Automation, Electronics and Electrical Engineering (AUTEEE) · 2022
In recent years, text clustering technology, as an unsupervised learning method in the field of machine learning, has become one of the most concerned technologies in the field of data mining. To some extent, it is easy to group small-scale text data into several categories. However, when faced with a large number of high-dimensional Chinese text data, the text clustering in this case will face high-dimensional and sparse data. Under the condition of ensuring the clustering quality, improving the speed of clustering and ensuring the effectiveness and accuracy of sentiment analysis become one of the topics of clustering research. In this paper, 99452 lines of film review data collected from web pages are used as experimental objects, and TFID+LSA is used to extract text features. The extracted features are analyzed with logical regression and Bayesian model, and then the accuracy is verified with the AUC of the reserve method and 10 fold cross test method. The experimental results show that the logical regression model is more suitable for text emotion analysis than Bayesian model.