MApp-IDEA: Monitoring App for Issue Detection and Prioritization

  • Vitor Mesaque Alves de Lima UFMS
  • Jacson Rodrigues Barbosa UFG
  • Ricardo Marcondes Marcacini USP


Opinion mining for app reviews uses machine learning-based methods to analyze people’s comments on app stores, aiming to support software maintenance and evolution. The challenge of manually analyzing a large amount of textual data can be solved through automatic opinion mining. We present MApp-IDEA tool to detect and classify emerging issues from user feedback in a risk matrix with prioritization levels and monitor evolution over time. The tool includes automatic app review tracking and an analytical data exploration instrument that allows engineers to browse the risk matrix, time series, heat map, issue tree, alerts, and notifications. Additionally, our tool has a performance analysis module, where it was possible to verify that in 6 million processed reviews of 50 popular apps, MApp-IDEA detected approximately 240,000 issues, where the peaks of the time series of issues are related to release dates of app versions. The tool is available on Github 1 and there is a presentation about the tool in Video 2 3.

Palavras-chave: opinion mining, issue prioritization, issue detection, app reviews
LIMA, Vitor Mesaque Alves de; BARBOSA, Jacson Rodrigues; MARCACINI, Ricardo Marcondes. MApp-IDEA: Monitoring App for Issue Detection and Prioritization. In: SIMPÓSIO BRASILEIRO DE ENGENHARIA DE SOFTWARE (SBES), 37. , 2023, Campo Grande/MS. Anais [...]. Porto Alegre: Sociedade Brasileira de Computação, 2023 . p. 180–185.