Social Influence in Conversations

Social influence (SI) is the change in an individual's thoughts, feelings, attitudes, or behaviors from interacting with another individual or a group. For example, a buyer uses SI skills to negotiate trade-offs and build rapport with the seller. SI is ubiquitous in everyday life, and hence, realistic human-machine conversations must reflect these dynamics, making it essential to model and understand SI in dialogue research systematically. This would improve SI systems' ability to understand users’ utterances, tailor communication strategies, personalize responses, and actively lead conversations. These challenges draw on perspectives not only from NLP and AI research but also from Game Theory, Affective Computing, Communication, and Social Psychology.

SI dialogue tasks like negotiation, persuasion, therapy, and argumentation have recently gained traction. Current conversational systems emphasize modeling system strategies using dialogue acts and strategy annotations or modeling users. Prior work also explored related tasks crucial for the eventual development of SI systems, namely outcome prediction, argument mining, and lie detection. However, these efforts are scattered, and only limited efforts focus on building useful systems exhibiting SI skills, such as chatbots. Ensuring AI-driven models’ safety, interpretability, and integration into real-time applications that simulate or analyze SI remains challenging.

We are excited to host the Second Workshop on Social Influence in Conversations (SICon 2024). SICon 2024 will be a one-day hybrid event, co-located with EMNLP 2024 in Miami, Florida on November 15-16.

Important Dates

• 15 August 2024 - Paper submission deadline

• 01 October 2024 - Notification of Acceptance

• 08 October 2024 - Camera-ready paper submission deadline

Note: all deadlines are 11:59PM UTC-12:00. We will accept ARR submissions; corresponding deadlines will be announced at a later moment in time.

Sponsors

TBA