Method for automatically analyzing user comments in application store and recommending comments to developers

Abstract

The invention relates to a method for automatically analyzing user comments in an application store and recommending the user comments to developers. The method is technically characterized by comprising the following steps: collecting user comment data and preprocessing the user comment data; carrying out intention classification on the user comments and establishing a classification model; carrying out topic classification on the user comments under each intention classification; performing sentence clustering on the user comments under each topic category, and calculating the clustering center position; establishing a mechanism for evaluating the priority of the user comments, calculating comprehensive scores of the user comments and recommending the comprehensive scores to a software developer. According to the method, intention classification, topic classification and sentence clustering are performed through comment information, and comments are processed in combination with timesequence and sentiment analysis; the hotspot top-k comments recommended and returned by the system are obtained, comment contents with reference values are provided for developers, so that referencesare provided for development and maintenance of applications, intake of redundant information of the developers is effectively reduced, user experience is improved, and the method has the characteristics of accurate and reliable content analysis, convenience in use and the like.

Description

technical field [0001] The invention belongs to the technical field of data mining, in particular to a method for automatically analyzing user comments in an application store and recommending them to developers. Background technique [0002] With the prosperity and development of the mobile Internet and web2.0, mobile applications have penetrated into every aspect of our lives, and our basic necessities of life are inseparable from mobile applications. The application store provides a large number of application programs. If the application developers want to keep their products competitive, they must understand the needs of users and the user experience in order to improve the application software. Users can download and install application software in the application store, and they can also submit their feedback on the use of the application program in the application store. [0003] Due to the relatively short development cycle of the application, developers can learn ...

AI Technical Summary

Problems solved by technology

[0004] After searching, it is found that some existing methods of mining user comments are to classify user comments, combine text analysis, natural language processing and other technologies to classify application comments, or divide comments into functional information and non-functional information. Information, or to divide comments into user needs, functional defects, functional experience, etc. Although these works divide comments into different categories, they are actually filtering comments that are not valuable to developers. Although these methods can learn from redundant comments Extract effective information. However, for some popular applications, due to the large number of comments, the classified comments are still confusing and cannot provide developers with effective suggestions intuitively; other works are considered on the basis of classification Factors such as time and length of comments divide comments into different priorities. However, this method only considers the text of comments and does not consider other attribute information of the app store, such as the usefulness of comments to users. This indicator expresses other users’ opinions on comments. Recognition, where prioritization of user comments can be problematic

Images