Research map / Large language models / AI and society
Expressive and Flexible Simulation of Information Spread Strategies in Social Networks Using Planning
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's full text. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Presents a numeric PDDL model for opinion dynamics and an interactive web demo that uses the Metric-FF planner to plan opinion-influencing action sequences on social networks.
Problem
Steering opinion dynamics and information spread in social networks toward specific outcomes is hard because traditional opinion models rely on broad strategies and ignore node-level interplay.
Approach
Encodes opinion dynamics (bounded trust-weighted opinion updates) as a numeric PDDL domain so that automated planning can devise node-level action sequences that move a network from its current opinion state to a user-specified goal, exposed through an interactive visualization platform.
Key results
- Introduces, to the authors' knowledge, the first numeric PDDL model for opinion dynamics with fluents have-opinion (-1.0 to 1.0) and have-trust.
- Opinion update follows a trust-weighted rule: ai(t+1) = ai(t) + mu_ij (aj(t) - ai(t)).
- Provides an online demo where users set goals and the Metric-FF planner generates propagation plans executed incrementally.
Limitations
- No quantitative evaluation of planning quality or scalability reported in the text.
- Evaluation limited to a demonstration platform description.
Experimental setup
Builds on: Metric-FF DeGroot consensus model Voter model bounded confidence model topic dependency model (Anderson and Ye 2019)
Closest papers by meaning
- Towards Effective Planning Strategies for Dynamic Opinion Networks (NeurIPS 2024 · similarity 0.87)
- Reaching a Consensus in Predictive Loops (NeurIPS 2026 · similarity 0.87)
- AI-Mediated Communication Can Steer Collective Opinion (NeurIPS 2026 · similarity 0.86)
- DEBATE: A Large-Scale Benchmark for Evaluating Opinion Dynamics in Role-Playing LLM Agents (NeurIPS 2026 · similarity 0.85)
- Sample Complexity of Linear Regression Models for Opinion Formation in Networks (AAAI 2025 · similarity 0.84)
- Opinion Maximization in Social Networks by Modifying Internal Opinions (NeurIPS 2025 · similarity 0.84)
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.