Abstract
Abstract In this paper, a random forest model is built using movie lines, each regression tree's prediction values are aggregated, and the final average is used as the prediction result. The fuzzy comprehensive evaluation decision is taken, and it is based on the fuzzy transformation principle and the maximum affiliation principle. The single-level fuzzy comprehensive evaluation can effectively cope with various fuzzy and uncertain information, which makes the comprehensive evaluation results more stable and reliable. The research results show that the training accuracy of the fuzzy comprehensive evaluation method is 96% and the testing accuracy is as high as 97%, and the proposed research can provide new ideas and research methods for the fields of film linguistics and text analysis.
Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
