Towards Opinion Shaping: A Deep Reinforcement Learning Approach in Bot-User Interactions

TL;DR

This paper explores using deep reinforcement learning, specifically DDPG, to control social network bots for effective opinion shaping and targeted advertising, demonstrating promising results in social platform interventions.

Contribution

It introduces a novel application of deep reinforcement learning to optimize bot control for opinion influence and advertising in social networks.

Findings

DRL-based approach effectively shapes opinions in social networks

Targeted advertising with DRL improves resource efficiency

Experimental results show potential for social platform interventions

Abstract

This paper aims to investigate the impact of interference in social network algorithms via user-bot interactions, focusing on the Stochastic Bounded Confidence Model (SBCM). This paper explores two approaches: positioning bots controlled by agents into the network and targeted advertising under various circumstances, operating with an advertising budget. This study integrates the Deep Deterministic Policy Gradient (DDPG) algorithm and its variants to experiment with different Deep Reinforcement Learning (DRL). Finally, experimental results demonstrate that this approach can result in efficient opinion shaping, indicating its potential in deploying advertising resources on social platforms.