Mitigating Problematic Social Media Use through Paired Recommender Systems with Contrasting Objectives

Overview

Social media platforms enable connection and entertainment, but engagement-optimizing algorithms may drive compulsive overuse and harm well-being. We propose a paired-trained recommender with two shared modules: one maximizes engagement, while the other discourages excessive sessions. To investigate user-recommender interactions, we model users with a dual-system reinforcement learning framework from computational neuroscience, capturing individual differences such as variations in impulsivity and habit formation.

Repository Structure

This repository is organized into two main folders:

1. results: Contains the results from the experiments.
2. src: Includes all the code for running simulations and analyzing results.

Citation

Stefano Livella, Luca Bolis, Sabrina Patania, Matteo Papini, and Dimitri Ognibene.
"Mitigating Problematic Social Media Use through Paired Recommender Systems with Contrasting Objectives."
In Proceedings of the 25th International Conference on Autonomous Agents and Multi-Agent Systems, 2026.