Investigating the relationship between price, rating, and popularity in the Blackberry World App Store

摘要: Context: App stores provide a software development space and market place that are both different from those to which we have become accustomed for traditional development: The granularity is finer there far greater source of information available research analysis. Information on price, customer rating and, through the data mining approach presented in this paper, features claimed by app developers. These attributes make ideal empirical engineering analysis.Objective: This paper11This paper an extended version our short at MSR 2012 [1]; technical report also [2]. exploits Store Analysis understand rich interplay between customers their developers.Method: We use extract descriptions, rating, popularity Blackberry World Store, natural language processing elicit each apps its description.Results: findings reveal strong correlations (rank downloads). found evidence mild correlation price number higher priced tended be lower rated users. free significantly (p-value < 0.001) ratings than non-free apps, with moderately high effect size (A^12=0.68). All experiments analysis made on-line support further investigations.