LANGUAGE · AGENTS · NETWORKS

Information Programme Center, DSTA

We study how language, artificial agents, and networked structures co-produce influence, deception, and collective behavior online; and build the tools to detect, simulate, and govern it.

Language

Psycholinguistic and narrative analysis of online discourse — stance, framing, and coordinated narratives across platforms and communities.

Focus: Language exploration across online communities · LLM-based studies · stance studies

Agents

Detecting and simulating synthetic and human-AI hybrid actors — from individual bots to large-scale multi-agent social simulations.

Focus: BotBuster · cyborg accounts · AuraSight

Networks

Structural and diffusion analysis of how narratives, influence, and coordination move through networked publics.

Focus: MASS framework · structural balance & triad analysis · narrative diffusion · information operations

Preliminary Readings

Papers to get new LAN Shop members up to speed. Full list on Google Scholar.

Language

• Examining the influence of political bias on large language model performance in stance classification
  Ng, Cruickshank, Lee. AAAI ICWSM 19: 1315–1328 (2025)
• Moral and emotional influences on attitude stability towards COVID-19 vaccines on social media
  Phillips, Ng, Zhou, Carley. SBP-BRiMS pp. 25–34, Springer (2024)
• Love-Hate Dataset: A Multi-Modal Multi-Platform Dataset Depicting Emotions in the 2023 Israel-Hamas War
  Ng, Lim, Lee. ACM Web Conf. 2024, pp. 1807–1815
• Is my stance the same as your stance? A cross validation study of stance detection datasets
  Ng, Carley. Information Processing & Management 59(6): 103070 (2022)
• Pro or anti? A social influence model of online stance flipping
  Ng, Carley. IEEE Transactions on Network Science and Engineering 10(1): 3–19 (2022)

Agents

• Bots, Bias, and Influence: The Hidden Architects of Social Media
  Ng, Carley. Cambridge Scholars Publishing (2026)
• BotSim: Mitigating the Formation of Conspiratorial Societies with Useful Bots
  Ng, Carley. Journal of Artificial Societies and Social Simulation (JASSS) 29(1): 4 (2026)
• Simulating Misinformation Vulnerabilities with Agent Personas
  Farr, Ng, Prochaska, Cruickshank, West. Proc. WSC 2025, 1907–1918. IEEE
• AuraSight: Generating Realistic Social Media Data
  Ng, Kang, Carley. Tech. Report CMU-S3D-25-109, Carnegie Mellon University (2025)
• Botbuster: Multi-platform bot detection using a mixture of experts
  Ng, Carley. AAAI ICWSM 17: 686–697 (2023)
• Are LLM-Powered Social Media Bots Realistic?
  Ng, Carley. SBP-BRiMS pp. 14–23, Springer (2025)
• Tiny-BotBuster: Identifying Automated Political Coordination in Digital Campaigns
  Ng, Bartulovic, Carley. SBP-BRiMS pp. 25–34, Springer (2024)

Networks

• Social Theory Should Be a Structural Prior for Agentic AI: A Formal Framework for Multi-Agent Social Systems
  Ng, Cruickshank, Lim, Carley. arXiv:2605.07069 (2026)
• Star Network Motifs on X During COVID-19
  Ng, Sinha, Carley. SBP-BRiMS pp. 193–202, Springer (2025)
• Deflating the Chinese balloon: types of Twitter bots in US-China balloon incident
  Ng, Carley. EPJ Data Science 12(1): 63 (2023)
• A combined synchronization index for evaluating collective action social media
  Ng, Carley. Applied Network Science 8, 1 (2023)
• Coordinating Narratives Framework for cross-platform analysis in the 2021 US Capitol riots
  Ng, Cruickshank, Carley. Computational and Mathematical Organization Theory (2022)
• It Takes Two to Negotiate: Modeling Social Exchange in Online Multiplayer Games
  Jaidka, Ahuja, Ng. Proc. ACM HCI 8, CSCW1: 1–22 (2024)