Social Influence in Conversations
Co-located with ACL 2023
Call for Papers
The First Workshop on Social Influence in Conversations (SICon 2023) invites submissions on recent advancements in social influence dialogue systems, along with other NLP tasks which will help to expand the social influence capabilities of these systems in the future. We aim to promote discussion around some key questions:
How should social influence systems model users and plan optimal responses systematically?
How can social influence systems benefit from linguistic theories (e.g., successful persuasion, negotiation tactics) developed in the social sciences?
What structurally differentiates and unites various social influence tasks?
What are the ethical issues involved with AI that engage in social influence and what guardrails must be implemented before using these systems in the wild?
Topics of Interest
Topics will include, but are not limited to:
Analysis-focused contributions
Analyzing linguistic behaviors in social influence interactions such as persuasion appeals, emotion expressions, promising therapy methods, or deception (e.g. strategic games like Diplomacy and Catan)
Associations between linguistic behaviors with social influence task outcomes (e.g. agent performance, user satisfaction, etc.)
Associations between user attributes, including demographics (e.g. gender, education, etc.) and personality traits (e.g. cooperativeness/competitiveness or Big-5 traits, etc.) with social influence task outcomes
Studying cultural differences in social influence interactions
Social influence in text grounded in other modalities (e.g. face-to-face multi-issue negotiations)
System design contributions
Dialogue systems for social influence tasks such as strategic games, negotiation, persuasion, argumentation, recommendation, or emotional support
Social influence systems for multi-agent interactions
Contributions advancing relevant sub-goals in social influence tasks
Detecting influence strategies in text, outcome prediction, stance detection, and argument mining
Partner/opponent modeling and emotion recognition in social influence interactions
Other specific contributions
Datasets that capture forms of social influence, especially in underrepresented languages (e.g. human-human datasets, wizard-of-oz paradigm, etc.)
Designing guardrails for Fairness, Accountability, Transparency, and Ethics for AI with social influence capabilities
Submission Guidelines
We welcome three kinds of submissions:
Short (4 pages of content) and Long (8 pages of content) papers for novel, unpublished work (archival). Camera-ready submissions will be given one additional page of content to address reviewers’ comments.
Extended abstracts (2 pages) for ongoing work (non-archival).
Short (5 pages of content) and Long (9 pages of content) papers for recent already-published work, that are highly relevant to the theme of the workshop and can help to encourage discussion (non-archival).
All submission types allow additional unlimited space for broader impact and ethics statements, limitations, and references. The submissions must follow the ACL 2023 style templates and ACL Policies for Submission, Review, and Citation.
Please also note the following:
The review will be double-blind. Please do not include any self-identifying information in the submission (covers all three submission types above). This includes anonymizing the already-published work by removing acknowledgments, self-citations, etc.
Non-archival submissions are expected to receive less-detailed reviews, compared to archival submissions.
SICon 2023 will use a separate ethics review, as required. Please ensure that any ethical concerns are appropriately addressed in the paper.
Parallel Submissions: Parallel submissions to other venues are NOT allowed.
Mode of Presentation: Presentations will be primarily based on poster sessions to foster thorough interaction and feedback, but we will recognize three exceptional papers by providing dedicated slots for lightning talks (5 minutes each).
Important Dates
Submission Site
SICon will accept all submissions through OpenReview (both direct and ARR): https://openreview.net/group?id=aclweb.org/ACL/2023/Workshop/SICon
Questions?
Please direct all queries to socialinfluencenlp@gmail.com