Balancing Accuracy and Explainability in Ai-Based Fraud Detection (Social Media Platforms)
International Journal of Drug Delivery Technology · 22.05.2026 · 16 (29s)
DOI: 10.25258/ijddt.16.29s.89 ↗Kurz gefasst
Fachartikel in der Zeitschrift International Journal of Drug Delivery Technology, online erschienen am 22.05.2026. Verfasst von Dr. M S Khatib und 1 weiteren Autor:innen.
Abstract (Originalsprache)
The rising issue of fake social media accounts is associated with many risks, including the dissemination of disinformation, cybercrime, and misappropriation of identities. In this paper, we propose a machine learning approach to detect fake Instagram accounts based on profile characteristics and behavioral traits. A dataset with such variables as username format, length of biographies, followers-to-following ratio, and frequency of posts was utilized to train the Random Forest Classifier. The classifier showed excellent performance in identifying fake accounts. In order to make the developed solution convenient for users, we implemented it into a web application built with the help of Flask. The web app enables users to input an Instagram account username, automatically retrieve necessary information about the profile with the help of Instaloader, and get instant prediction results. Predictions are stored in a CSV file.
Zitieren
APA
Khatib, D. M. S., & Rehman, M. S. (2026). Balancing Accuracy and Explainability in Ai-Based Fraud Detection (Social Media Platforms). International Journal of Drug Delivery Technology, 16(29s). https://doi.org/10.25258/ijddt.16.29s.89
Vancouver
Khatib DMS, Rehman MS. Balancing Accuracy and Explainability in Ai-Based Fraud Detection (Social Media Platforms). International Journal of Drug Delivery Technology. 2026;16(29s). doi:10.25258/ijddt.16.29s.89
BibTeX
@article{Khatib2026,
author = {Khatib, Dr. M S and Rehman, Ms. Shumaila},
title = {Balancing Accuracy and Explainability in Ai-Based Fraud Detection (Social Media Platforms)},
journal = {International Journal of Drug Delivery Technology},
year = {2026},
volume = {16},
number = {29s},
doi = {10.25258/ijddt.16.29s.89}
}
EUVIMED