Book

Description

There are millions of apps on a regular basis, where the creators are uploading. The millions of consumers uninstall such applications without testing duplicated data. Such applications impact users' personal information which damages the confidence of the users in Google Store and also causes users to lose. In addition, there is some detail on such programs, which is provided on a play page. In this analysis job, with the aid of a crawler or scraper that is used to catalog, calculate and evaluate the millions of play store applications, we have scraped a Google play store dataset. We have specific types of applications after having collected the details regarding the applications from the play shop. Such apps are charged and optional, so we have a selection of different types of home apps so gaming applications. In this work we examined the quality of the applications by addressing different testing questions dependent on a dataset 's attributes. We also tested the causal constructs from databases, correlations, correlation, repeated trends, user feedback sentiment analysis, utilizing the different machine learning approaches that can support developers and consumers alike. We evaluated consumer feedback on game apps utilizing latent sentiment research, which is a text mining technique. We consider the determinants generating either user-positivity or hostility against game applications. We evaluated the association between the average measurement of the emotions and the average client ranking. We analyzed that in feedback sentiment analysis graph much of the application displaying the top ranking in the rating graph is not right. The fundamental explorations&