Park text comment emotion scoring method based on machine learning

Abstract

The invention discloses a park comment text emotion scoring method and system based on machine learning. The method comprises the steps of obtaining comment text data, preprocessing the obtained comment text data, including word segmentation and stop word removal processing, then performing vectorization representation on the comment text, then inputting the comment text into a regression device,establishing a mapping relationship with emotion scores, and performing emotion analysis by using a trained model. The park comment text is subjected to eigenvector representation, the relationship between the eigenvector and the emotion score is established, training is performed, and emotion scoring is performed by using the trained model. The score has continuity and diversity, the emotion positivity of public comments can be obtained, and the method is efficient, rapid, low in cost, suitable for research work in the field of urban parks and capable of achieving large-scale rapid analysis of emotions of users.

Description

technical field [0001] The invention relates to the technical field of machine learning, in particular to a machine learning-based sentiment scoring method for park text comments. Background technique [0002] With the development of Internet application technology, users have gradually become important creators of content on the Internet. Users can express their emotions and emotions through the Internet. Facing the impact of the huge amount of text data brought by social media, text review information is not only the basis for consumers to choose, but also provides suggestions for important decisions of providers. [0003] The analysis of comment information is mainly sentiment analysis, and sentiment analysis is generally carried out by means of sentiment scoring. At present, the emotion scoring methods are mainly divided into two categories. The first category is based on rules and emotion dictionaries. The results are not easy to standardize; the second largest categ...

AI Technical Summary

Problems solved by technology

[0005] It can be seen that the methods in the field of text sentiment analysis ignore the positive degree of emotion and only consider a single positive

Images