A natural language processing based technique for sentiment analysis of college english corpus

The college English corpus can help us better master English, but how to obtain the desired information from a large number of English corpus has become the focus of information technology. Based on the natural language processing (NLP) technology, a sentiment analysis model is built in this article. An improved term frequency–inverse document frequency (TF-IDF) algorithm is proposed in this article, where the weighted average method is used to determine the emotional value of each emotional word. The inspirational words are used to obtain the English corpus’s emotional tendency and emotional value. The results show that the model has high classification accuracy and operation efficiency when selecting feature words. Compared with the TF-IDF, the improved TF-IDF algorithm added the necessary information weight processing and word density weight processing to two new processing links, which can significantly improve the efficiency of college English learning.