Classifying Mobile Applications Using Word Embeddings

Modern application stores enable developers to classify their apps by choosing from a set of generic categories, or genres, such as health, games, and music. These categories are typically static—new categories do not necessarily emerge over time to reflect innovations in the mobile software landscape. With thousands of apps classified under each category, locating apps that match a specific consumer interest can be a challenging task. To overcome this challenge, in this article, we propose an automated approach for classifying mobile apps into more focused categories of functionally related application domains. Our aim is to enhance apps visibility and discoverability. Specifically, we employ word embeddings to generate numeric semantic representations of app descriptions. These representations are then classified to generate more cohesive categories of apps. Our empirical investigation is conducted using a dataset of 600 apps, sampled from the Education, Health&Fitness, and Medical categories of the Apple App Store. The results show that our classification algorithms achieve their best performance when app descriptions are vectorized using GloVe, a count-based model of word embeddings. Our findings are further validated using a dataset of Sharing Economy apps and the results are evaluated by 12 human subjects. The results show that GloVe combined with Support Vector Machines can produce app classifications that are aligned to a large extent with human-generated classifications.

Unfolding #Anonymous on Twitter

This paper presents a comprehensive empirical investigation of the range of actors, issues and sub-groups related to the hashtag Anonymous on Twitter between 2012 and 2015. Complementing existing studies that have provided in-depth accounts of Anonymous from a specific point of view, this research provides an overview of the network related to the discursive construction of Anonymous on Twitter from a synoptic standpoint. In particular, the analysis covers three dimensions: the structure and dynamics of the #Anonymous interaction network; the range of issues that Anonymous has been associated with; and the relation between Anonymous and its offshoots. This research provides a descriptive characterization of the topological and semantic complexity of Anonymous and invites to reflect on the simplifications that our vocabulary and methods entail vis a vis the complexity of digital entities delimited by and individuated through hashtags.