GP-FACL: A Dataset of FAlse CLaim Descriptions and Functionalities of Google Play Apps

Mehregan, Sepehr; Tamjidi, Mahdi; Rahimi, Amir Hossein; Razavi, Ava; Eskandari, Sadegh; Tabatabaei, Seyed Amir Hossein

doi:10.22042/isecure.2026.243622

GP-FACL: A Dataset of FAlse CLaim Descriptions and Functionalities of Google Play Apps

Articles in Press

Document Type : Research Article

Authors

Sepehr Mehregan ¹

Mahdi Tamjidi ¹

Amir Hossein Rahimi ²

Ava Razavi ³

Sadegh Eskandari ¹

Seyed Amir Hossein Tabatabaei ¹

¹ Department of Computer Science, University of Guilan, Rasht, Iran

² Department of Computer Science, Aston University, Birmingham, United Kingdom

³ Department of Computer Science, Brock University St. Catharines, Canada

10.22042/isecure.2026.243622

Abstract

Mobile phones are among the most significant technological advancements, offering unmatched convenience and seamlessly integrating into modern lifestyles. However, their widespread use also facilitates both beneficial and harmful practices. The absence of comprehensive datasets with reliable app descriptions undermines user confidence in Google Play as a trustworthy platform for software. To address this gap, we introduce a new dataset, GP-FACL, in this study. This dataset contains "fake apps” that make false claims in their descriptions and pretend to offer features that do not actually exist. Applications were first manually collected, after which keywords were extracted to generate 2-gram key phrases. These key phrases were then used to automate the collection of additional applications. The final dataset provides a systematic approach for identifying false-claim applications across a variety of app categories. Our approach resulted in 117 applications being verified as containing erroneous or misleading claims. This dataset offers researchers and practitioners a valuable resource for advancing fraud detection and mitigating deceptive applications on mobile platforms.

Keywords

Automated Collection

Dataset Creation

Fraud Detection

Mobile Applications

Textual Deception

[1] Statista. Number of available applications in the Google Play Store from March 2017 to June 2024, 2024. URL https://www.statista.com/ statistics/266210/number-of-availableapplications-in-the-google-play-store/.

[2] Kevin Allix, Tegawendé F Bissyandé, Jacques Klein, and Yves Le Traon. Androzoo: Collecting millions of android apps for the research community. In Proceedings of the 13th international conference on mining software repositories,pages 468–471, 2016.

[3] Jonathan Crussell, Ryan Stevens, and Hao Chen. Madfraud: Investigating ad fraud in android applications. In Proceedings of the 12th annual international conference on Mobile systems, applications, and services, pages 123–134, 2014.

[4] Mahmudur Rahman, Mizanur Rahman, Bogdan Carbunar, and Duen Horng Chau. Search rank fraud and malware detection in google play. IEEE Transactions on Knowledge and Data Engineering, 29(6):1329–1342, 2017.

[5] Kireet Muppavaram. Analysis and detection of fake apps in android environment. NeuroQuantology, 20(10):9253–9267, 2023. . URL https://www.neuroquantology.com.

[6] TP Rani, S Susila Sakthy, P Kalaichelvi, et al. Fake app detection using sentiment analysis. 2023IntelligentComputingandControlforEngineering and Business Systems (ICCEBS), pages 1–6, 2023.

[7] Maarten Grootendorst. Keybert: Minimal keyword extraction with bert, 2020. URL https:// doi.org/10.5281/zenodo.4461265. Accessed on 2025-07-18.

[8] Mayur Makwana and Rupa Mehta. Keyphrasebased literature recommendation: Enhancing user queries with hybrid co-citation and cooccurrence networks. Journal of Scientometric Research, 13(1):217–229, 2024.

[9] Mohammad Nadim, David Akopian, and Adolfo Matamoros. A comparative assessment of unsupervised keyword extraction tools. IEEE access, 11:144778–144798, 2023.

[10] Google play scraper. URL https://github. com/JoMingyu/google-play-scraper.