Detecting Intents of Fake News Using Uncertainty-Aware Deep Reinforcement Learning

Zhen Guo, Qi Zhang, QISHENG ZHANG, Lance M. Kaplan, Audun Jøsang, Feng Chen, DONG HYUN JEONG, Jin-Hee Cho

Abstract: Intent mining is critical for controlling the spread of false information across online social networks (OSNs). To this end, we develop deep reinforcement learning (DRL) agents guided by a delayed reward based on intent prediction using a classifier of long short-term memory (LSTM). Additionally, we incorporate an uncertainty-aware function that leverages subjective opinions derived from Subjective Logic (SL). Through evaluation using an annotated fake news tweet dataset, our results demonstrate that our intent classification framework surpasses competing methods in terms of intent accuracy. Our intent mining solutions using DRL algorithms can support effective and efficient intervention strategies for fake news spreading on OSNs.