Software feature evaluation method based on comment data

Abstract

The invention provides a software feature evaluation method based on comment data. The software feature evaluation method comprises the following steps: S1, collecting description information of a software product and a plurality of pieces of comment data; S2, performing word segmentation on the description information and the comment data; S3, generating a corresponding software comment feature set according to a comment data word segmentation result; S4, establishing a feature description set according to a word segmentation result of the description information; extracting feature word-viewpoint word pairs from a word segmentation result of the comment data according to the feature description set; S5, judging the evaluation polarity and polarity intensity of the extracted feature word-viewpoint word pair according to the constructed polarity dictionary; S6, generating a non-consistency feature set according to the similarity between the feature description set and the software comment feature set; S7, classifying the non-consistency feature set according to the plurality of established software application quality evaluation indexes; and S8, visually displaying the polarity, the statistical result of the polarity intensity and the classification result of the non-consistency feature set.

Description

technical field [0001] The invention relates to a software evaluation method, in particular to a software feature evaluation method based on comment data. Background technique [0002] With the rapid development of computer technology and software industry, software has penetrated into various industries and profoundly affected people's lives. Various software application services such as open source software and mobile software are widely used. At the same time, the demand for software is increasing, and the quality requirements for software are also getting higher and higher. People use software all the time in their lives. become an integral part. At present, a large number of software application markets have emerged in China to provide people with application download services. However, in the face of a large number of applications in the software market, users choose products based on software product description information and review information. Because software pr...

AI Technical Summary

Problems solved by technology

[0004] However, in the face of numerous comments and ratings, it is difficult to directly reflect the user's evaluation. The validity of these comments and the accuracy of the description are the focus of users' attention.

In order to find high-quality applications that truly meet their needs, users need to spend a lot of time browsing, which is time-consuming and laborious, and it is extremely difficult for users to judge the emotions of comments, which hinders users from choosing applications

Images