arXiv:1703.02256cs.SE
On the Emotion of Users in App Reviews
Early discovery. Linked by one identifiable commenter. This paper is outside the main ranking; a mention is not an endorsement.
Abstract
App store analysis has become an important discipline in recent software engineering research. It empirically studies apps using information mined from their distribution platforms. Information provided by users, such as app reviews, are of high interest to developers. Commercial providers such as App Annie analyzing this information became an important source for companies developing and marketing mobile apps. In this paper, we perform an exploratory study, which analyzes over seven million reviews from the Apple AppStore regarding their emotional sentiment. Since recent research in this field used sentiments to detail and refine their results, we aim to gain deeper insights into the nature of sentiments in user reviews. In this study we try to evaluate whether or not the emotional sentiment can be an informative feature for software engineers, as well as pitfalls of its usage. We present our initial results and discuss how they can be interpreted from the software engineering perspective.
> - I assume sentiment and star ratings are strongly correlated, but are there cases where these deviate? > - Are there interesting differences in sentiment mean+variance by app category? For example, are utility app reviews more polarized than games? These are answered in the…
MasterScratView on HNParent context