Research map / Time series / Causal and generative time series
Steering Social Activity: A Stochastic Optimal Control Point Of View
Ali Zarezade, Abir De, Utkarsh Upadhyay, Hamid R. Rabiee, Manuel Gomez-Rodriguez
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add time-varying follower significance to RedQueen (ablation) | RedQueen · Twitter user | average position: 389{.}45 -> 425{.}25 | Hurt |
| use RedQueen instead of user's original posting schedule | Twitter broadcasters · Twitter user | average position: 698{.}04 -> 425{.}25 | Improved |
| RedQueen vs Karimi et al. with many followers (over 5) | RedQueen · Synthetic multiple followers | time at the top: ~10% higher values for >5 followers | Improved |
| RedQueen vs Karimi et al. with few followers (1-4) | RedQueen · Synthetic multiple followers | time at the top: ~18% lower values for 1-4 followers | Hurt |
| RedQueen vs Karimi et al. on position over time | RedQueen · Synthetic multiple followers | position over time: factor of 2 | Improved |
| use RedQueen on real Twitter data vs true posts | broadcasters · Twitter when-to-post | time at the top: 3.5x higher; 99.1% of users | Improved |
| apply Cheshire control to uncontrolled network | 64-node Kronecker networks · Kronecker 64 nodes | non-incentivized actions: ~4,800 -> ~96,000 actions | Improved |
| Cheshire vs second best method | Cheshire · Kronecker 512 nodes | posts triggered: up to 50%-100% more posts | Improved |
| Cheshire vs second best on Twitter datasets | Cheshire · Twitter datasets (5) | posts triggered: up to 100%-400% more posts | Improved |
| Cheshire vs second best at low budget | Cheshire · Twitter datasets (5) | time to 30,000 tweets: 20%-50% faster | Improved |
| use network structure only (PageRank, degree) to allocate budget | PRK and DEG baselines · Kronecker and Twitter | overall tweets | Hurt |
| MSC spends budget early | MSC · Kronecker 512 nodes | overall tweets over time | Mixed |
Closest papers by meaning
- Multistage Campaigning in Social Networks (NeurIPS 2016 · similarity 0.87)
- COEVOLVE: A Joint Point Process Model for Information Diffusion and Network Evolution (JMLR 2017 · similarity 0.87)
- Online Influence Maximization under Independent Cascade Model with Semi-Bandit Feedback (NeurIPS 2017 · similarity 0.85)
- Optimizing Social Network Interventions via Hypergradient-Based Recommender System Design (ICML 2025 · similarity 0.83)
- Reaching a Consensus in Predictive Loops (NeurIPS 2026 · similarity 0.83)
- Steering the Herd: A Framework for LLM-based Control of Social Learning (ICLR 2026 · similarity 0.83)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
