Critical Evaluation on Spam Content Detection in Social Media

Google Drive Link

The spam content detection problem is still challenging due to its complexity, feature extraction process, language, context-aware detection capabilities, performance, and evaluation method. Spam content detection is different from spammers' detection and thus requires a different approach. This paper aimed to conduct a comprehensive literature review for "spam content detection" to identify the various approaches taken and generate up to date issues, especially in the social media case study. Literature data are collected from 2015 to 2021 based on seven journal repository databases and filtered into 69 main articles. This research compared the latest approaches and methods to see the gaps between these studies. Discussions on the approach, research media, dataset, feature extraction & selection, the language, context-based or not, the algorithm, performance, future research direction, and challenges were carried out. Additionally, this paper also discussed spam content on Indonesian social media and provided comprehensive suggestions for possible implementation, further research direction, and a possible new approach. This article can be used to develop new approaches, methods, and models in detecting spam content on social media.