MApp-KG: Mobile App Knowledge Graph for Document-Based Feature Knowledge Generation

Mobile app repositories serve as large-scale crowdsourced information systems used for various document-based software engineering tasks, leveraging product descriptions, user reviews, and other natural language documents. Particularly, feature extraction (i.e., identifying functionalities or capabilities of a mobile app mentioned in these documents) is key for product recommendation, topic modelling, and feedback analysis. However, researchers often face domain-specific challenges in mining these repositories, including the integration of heterogeneous data sources, large-scale data collection, normalization and ground-truth generation for feature-oriented tasks. In this paper, we introduce MApp-KG, a combination of software resources and data artefacts in the field of mobile app repositories aimed at supporting feature-oriented knowledge generation tasks. Our contribution provides a framework for automatically constructing a knowledge graph that models a domain-specific catalog of natural language documents related to mobile applications. We distribute MApp-KG through a public triplestore, enabling its immediate use for future research and replication of our findings.