Maximizing Opinion Polarization Using Double Deep Q-Learning in Social Networks
Bibliographic record
Abstract
Social media networks, such as Facebook and X (formerly Twitter), have become crucial platforms for public discourse, but they also contribute to the rise of misinformation and opinion polarization. This polarization has profound social, economic, and political implications, making it a critical area of study. In this research, we investigate the impact of automated adversary agents on social media networks by introducing a novel approach using Double-Deep Q-learning reinforcement learning (RL) to deliberately increase polarization within social media networks. The RL agent requires minimal interaction with the system and can flexibly adapt to changes within the network, allowing it to effectively exploit structural vulnerabilities and amplify divisions among users. By learning how to influence the flow of information, the agent intensifies polarization and disagreement with fewer interventions compared to traditional methods. Through simulations and experiments with real-world datasets, we demonstrate that our RL-based approach significantly outperforms conventional techniques in escalating polarization. These findings underscore the risks posed by such techniques and the urgent need to develop safeguards against malicious manipulation of social media platforms by intelligent adversary agents.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.004 | 0.013 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.001 | 0.000 |
| Science and technology studies | 0.001 | 0.002 |
| Scholarly communication | 0.001 | 0.002 |
| Open science | 0.001 | 0.002 |
| Research integrity | 0.001 | 0.002 |
| Insufficient payload (model declined to judge) | 0.002 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".