Internet user comment analysis method and system based on big data text analysis

Abstract

The invention discloses an internet user comment analysis method based on big data text analysis. The method comprises the following steps: obtaining and sending user evaluation information; performing data cleaning processing on the user evaluation information to obtain and send target pure text information; extracting user emotion data in the target pure text information, classifying the user emotion data according to a set rule, and generating and sending a classification report; performing word segmentation operation on the text information in the classification report by using a Chinese word segmentation framework to obtain and send word segmentation text data; performing word vectorization operation on the word segmentation text data, and removing interference information to obtain vectorized words; and performing operation on the vectorized words by utilizing a naive Bayes algorithm, and outputting and displaying an operation result. The invention further discloses an internet user comment analysis system based on big data text analysis. According to the invention, the user comment analysis efficiency and accuracy can be effectively improved.

Description

technical field [0001] The present invention relates to the technical field of data analysis, in particular to a method and system for analyzing Internet user comments based on big data text analysis. Background technique [0002] For App operating units, user experience is very important. However, Internet operating units have limited ways to obtain users’ opinions and suggestions on products. "The acquisition of functional modules, and the analysis of user comments is only limited to the implementation of spreadsheets combined with manual combing. This method has the following defects: [0003] 1. The number of analyzed samples is seriously insufficient, resulting in inaccurate analysis conclusions. [0004] 2. The source of the analysis sample itself has certain limitations, and the output results can only focus on one aspect. [0005] Third, the efficiency is low, and the rigor of the analysis results is insufficient. [0006] Fourth, it takes up a lot of human resour...

AI Technical Summary

Problems solved by technology

[0003] 1. The number of analyzed samples is seriously insufficient, resulting in inaccurate analysis conclusions

[0004] 2. The source of the analysis sample itself has certain limitations, and the output results can only focus on a certain aspect

[0005] 3. Low efficiency and insufficient rigor of analysis results

[0006] 4. Occupying a lot of human resources

Images