Detecting collusive spammers on e-commerce websites based on reinforcement learning and adversarial autoencoder

作者：

Highlights：

• A modified Sarsa reinforcement learning algorithm is proposed.

• A reinforcement learning-based method is proposed to discover candidate groups.

• An adversarial autoencoder-based model is constructed to detect collusive spammers.

• We formulate the group vector representations as a sequence embedding problem.

摘要

•A modified Sarsa reinforcement learning algorithm is proposed.•A reinforcement learning-based method is proposed to discover candidate groups.•An adversarial autoencoder-based model is constructed to detect collusive spammers.•We formulate the group vector representations as a sequence embedding problem.

论文关键词：Collusive spammers,Collusive spammer detection,Reinforcement learning,Adversarial autoencoder

论文评审过程：Received 25 November 2021, Revised 28 April 2022, Accepted 29 April 2022, Available online 11 May 2022, Version of Record 16 May 2022.

论文官网地址：https://doi.org/10.1016/j.eswa.2022.117482