{"title":"Feature-based evaluation of competing apps","authors":"Faiz Ali Shah, Yevhenii Sabanin, Dietmar Pfahl","doi":"10.1145/2993259.2993267","DOIUrl":null,"url":null,"abstract":"App marketplaces, i.e. Google Play Store and Apple AppStore,comprise many competing apps offering a fair set of similar features. Users of competing apps can submit feedback in the form of ratings and textual comments. The feedback is useful for app developers to get a better understanding of where their app stands in the competition. However, app ratings don’t provide concrete information regarding users’ perceptions about an app’s features compared to similar apps. Studies have shown that users express sentiments on app features in app reviews. Therefore, user reviews are a valuable information source to compare competing apps based on users' sentiments regarding features. So far, researchers have analyzed app reviews to summarize the users’ sentiments on app features but the existing approaches have not been used for the comparison of competing apps. In this direction, we analyze app reviews of 25 apps to extract app features, determine competing apps based on feature commonality, and then compare competing apps based on users’ sentiments regarding features. We developed a tool prototype that helps app developers in identifying features which have been perceived negatively by its users. The tool prototype is also useful to find a set of features loved by users in other similar apps but missing in one’s app. We demonstrate the usefulness of the tool prototype and give pointers to future work.","PeriodicalId":268579,"journal":{"name":"Proceedings of the International Workshop on App Market Analytics","volume":"304 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2016-11-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"25","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Proceedings of the International Workshop on App Market Analytics","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1145/2993259.2993267","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 25
Abstract
App marketplaces, i.e. Google Play Store and Apple AppStore,comprise many competing apps offering a fair set of similar features. Users of competing apps can submit feedback in the form of ratings and textual comments. The feedback is useful for app developers to get a better understanding of where their app stands in the competition. However, app ratings don’t provide concrete information regarding users’ perceptions about an app’s features compared to similar apps. Studies have shown that users express sentiments on app features in app reviews. Therefore, user reviews are a valuable information source to compare competing apps based on users' sentiments regarding features. So far, researchers have analyzed app reviews to summarize the users’ sentiments on app features but the existing approaches have not been used for the comparison of competing apps. In this direction, we analyze app reviews of 25 apps to extract app features, determine competing apps based on feature commonality, and then compare competing apps based on users’ sentiments regarding features. We developed a tool prototype that helps app developers in identifying features which have been perceived negatively by its users. The tool prototype is also useful to find a set of features loved by users in other similar apps but missing in one’s app. We demonstrate the usefulness of the tool prototype and give pointers to future work.
应用市场,如Google Play Store和Apple AppStore,包含了许多提供相似功能的竞争性应用。竞争应用程序的用户可以以评分和文字评论的形式提交反馈。这些反馈有助于应用开发者更好地了解自己的应用在竞争中的位置。然而,应用评级并不能提供用户对同类应用的看法的具体信息。研究表明,用户会在应用评论中表达对应用功能的情感。因此,用户评论是一个有价值的信息来源,可以根据用户对功能的看法来比较竞争应用。到目前为止,研究人员已经通过分析应用评论来总结用户对应用功能的看法,但现有的方法还没有被用于竞争应用的比较。在这个方向上,我们分析了25个应用的应用评论,提取应用功能,根据功能共性确定竞争应用,然后根据用户对功能的看法对竞争应用进行比较。我们开发了一个工具原型,帮助应用开发者识别被用户认为是负面的功能。工具原型对于找到其他类似应用中用户喜爱但在自己的应用中缺失的一组功能也很有用。我们展示了工具原型的有用性,并为未来的工作提供了指导。