User to Video: A Model for Spammer Detection Inspired by Video Classification Technology
Haoyang Zhang, Zhou Yang, Yucai Pang
TL;DR
This work tackles scalable spammer detection in social networks by reframing historical user behavior as a video-like representation. It introduces UVSD, a four-stage pipeline consisting of user pixelization, subspace imageization, video construction, and CNN-based video classification, underpinned by Node2vec and TSNE-based subspace-to-image transforms. Across WEIBO and TWITTER datasets, UVSD demonstrates strong performance relative to a range of baselines, with validity analyses confirming the benefits of the chosen user relations and CNN-based video modeling. By enabling video-classification techniques to operate on social network history, the approach offers a memory-efficient, scalable alternative to large graph models while preserving detection effectiveness.
Abstract
This article is inspired by video classification technology. If the user behavior subspace is viewed as a frame image, consecutive frame images are viewed as a video. Following this novel idea, a model for spammer detection based on user videoization, called UVSD, is proposed. Firstly, a user2piexl algorithm for user pixelization is proposed. Considering the adversarial behavior of user stances, the user is viewed as a pixel, and the stance is quantified as the pixel's RGB. Secondly, a behavior2image algorithm is proposed for transforming user behavior subspace into frame images. Low-rank dense vectorization of subspace user relations is performed using representation learning, while cutting and diffusion algorithms are introduced to complete the frame imageization. Finally, user behavior videos are constructed based on temporal features. Subsequently, a video classification algorithm is combined to identify the spammers. Experiments using publicly available datasets, i.e., WEIBO and TWITTER, show an advantage of the UVSD model over state-of-the-art methods.