Aim and Topics

Now in its sixth edition, the ROMCIR Workshop concerns providing information access systems to mitigate the human-generated or AI-generated information disorder phenomenon concerning distinct domains. By “information disorder”, we mean all forms of communication pollution, from misinformation made out of ignorance, automatically built based on biased content, to intentional sharing of false content (generated both manually and automatically).

In this context, all those approaches that aim to assess the factual accuracy (or other reliability-related relevance dimensions) of information circulating online, and particularly on social media, find their place. This topic is very broad, as it concerns different contents (e.g., Web pages, news, reviews, medical information, online accounts, etc.), different Web and social media platforms (e.g., microblogging platforms, social networking services, social question-answering systems, etc.), different purposes (e.g., identifying false information, accessing information based on its truthfulness, retrieving truthful information, hallucination detection, etc.), and different open issues related in particular to AI (e.g., explainability of search results, assessment of the truthfulness of automatically generated content, generative models to support IRSs, etc.).

The topics of interest include, but are not limited to, the following:

• Access to and retrieval of reliable information
• Bot/spam/troll detection
• Computational fact-checking
• Credibility assessment of online documents
• Crowdsourcing for information truthfulness assessment
• Disinformation/misinformation/bias detection
• Evaluation strategies to assess information truthfulness
• Generative models and information truthfulness assessment
• Human-in-the-loop misinformation detection
• Information polarization in online communities, echo chambers
• Propaganda identification/analysis
• Query reformulation strategies for truthful IR
• Search patterns and simulation strategies for information verification
• Security, privacy, and information truthfulness
• Societal reaction to misinformation
• Stance detection
• Trust and reputation

Data-driven approaches, supported by publicly available datasets, are more than welcome.