Preconference at the Society for Affective Science Conference 2027

We are holding a pre-conference on Computational Affective Linguistics (CAL) at the Society of Affective Science (SAS) 2027 conference, happening from March 4-6 2027 in San Diego, California, USA.

Call for Participation

We invite submissions to the Computational Affective Linguistics (CAL) preconference at the 2027 Annual Conference of the Society for Affective Science (SAS)! This preconference will be a space for researchers to explore ideas at the intersection of computation, language, and emotion: what can computational analysis of language teach us about emotion, and what can emotion theory teach us about computational methods?

We are excited to see cross-disciplinary work that engages with qualitative and quantitative methodologies from diverse fields, including affective science, neuroscience, philosophy, linguistics, and natural language processing (NLP), to advance our understanding of affect and emotions.

We encourage submissions from early-stage and junior researchers in the affective science, computational linguistics, and natural language processing communities. Our goal is to foster learning and collaboration across these fields. Authors will have the option to publish the extended abstracts on the ACL Anthology.

Website: https://casworkshop.github.io/cal-sas

Motivation

Language is one of the most powerful mechanisms through which emotions are expressed, and natural language processing (NLP) methods increasingly draw on language data to answer fundamental questions about emotion. The Computational Affective Science (CAS) workshop series aims to be a dedicated venue for research on understanding of affect and emotions through language and computation.

The first CAS workshop was hosted at the Language Resources and Evaluation Conference (LREC) 2026. This iteration brings it to SAS, with the goal of bringing NLP researchers into a research environment they would not otherwise attend, to the mutual benefit of both.

Topics

CAL will accept submissions that discuss new ideas, new perspectives, new findings, and works-in-progress, on the topics of computational language processing and affective science. These topics include, but are not limited to:

• Qualitative and quantitative studies of natural language data that add to our understanding of affect and emotion, including findings relevant to:

  • theories and nature of emotion
  • models of emotions (dimensional models, appraisal models, models of constructed emotion)
  • emotion dynamics (emergence, intensification, decay, transitions)
  • emotion granularity and emotion regulation
  • affective embodiment
  • evolutionary and developmental affect
  • emotion–cognition interactions

• Demonstrations of innovative methods for processing, analyzing, and modeling language data to yield insights about affect and emotion.

• Creation of affective data and resources, for instance, compiling and annotating affect-related information in text, speech, facial and bodily expression, or other communicative modalities..

• Work on downstream applications of computational models of language for affect and emotion in various domains, such as:

  • artificial intelligence and GenerativeAI
  • health, psychopathology
  • behavioral social science, the humanities
  • education, commerce, etc.

• Discussions of ethics, fairness, and the philosophical implications of affective linguistic modeling, including:

  • bias and generalizability across demographics
  • privacy and ethics in data collection
  • examining whether automatic NLP systems rely on current and valid theories
  • implications of machines modeling or simulating affect
  • societal considerations surrounding affective artificial agents

Submission Details

Submissions must feature novel and recent work relating to the topics detailed above. Preliminary work is welcome! To diversify content across the preconference and the main SAS conference, we ask that speakers do not submit identical material to both forums. These abstracts are non-archival, offering the option for publication and presentation at other conference venues.

We have two main submission tracks:

• Ideas: These submissions showcase a new research idea, proof-of-concept methodology, or theoretical perspectives on the computational understanding of affect and emotion.
• Findings: These report new empirical resources, methods, or findings on affect and emotion resulting from a quantitative or qualitative analysis of data.

Format

Submissions can be one of two types:

• Abstract submissions must include: a title, speaker name, affiliation, and career stage; a summary (300 words maximum) that motivates the work, provides details necessary to evaluate the idea or findings (e.g., methods, results), and contextualizes the work within computational affective science/linguistics.

• Extended abstracts (2 pages max) that elaborate on these elements, including images and visualizations. These will be published on the ACL Anthology.

Key Dates

• Submissions open: December 1, 2026
• Submissions close: January 11, 2027 (11:59pm AoE)
• Acceptance notification: January 19, 2027
• Deadline to confirm intent to present (Early bird registration deadline): February 1, 2027
• Preconference: March 4, 2027

Presentation

Acceptance decisions will consider the quality of submissions while balancing diversity of topics, methods, and presenters. Work must be presented in person at the preconference by an author. All presenters must register for the preconference (details can be found on the SAS website) and are expected to attend the meeting in person in San Diego.

Accepted abstracts are to be presented as posters. A small number of submissions will be invited to present flash talks (~10 minutes).

Contact

Email cas-workshop@googlegroups.com with any questions!

Organizers

• Christopher Bagdon, University of Bamberg, Germany
• Krishnapriya Vishnubhotla, National Research Council Canada
• Katie Hoemann, University of Kansas, USA
• Kristen A. Lindquist, The Ohio State University, USA
• Lyle Ungar, University of Pennsylvania, USA
• Roman Klinger, University of Bamberg, Germany
• Saif M. Mohammad, National Research Council Canada