The 1st Workshop on Computational Affective Science

Co-located with LREC 2026 in Palma de Mallorca, 11-16 May.

The Computational Affective Science (CAS) workshop is a series dedicated to exploring the intersection of Natural Language Processing (NLP) and Affective Science. Over the course of the series we hope to explore the many subareas and modalities in which affect is studied. The first edition of the CAS workshop at LREC 2026 will focus on language based modalities.

Contact: workshop.cas1@gmail.com

Motivation

Affect refers to the fundamental neural processes that generate and regulate emotions, moods, and feeling states. Affect and emotions are central to how we organize meaning, to our behavior, to our health and well-being, and to our very survival. Despite this, and even though we are all intimately familiar with emotions in everyday life, there is much we do not know about how emotions work and how they impact our lives. Affective Science is a broad interdisciplinary field that explores these and other related questions about affect and emotions. Since language is a powerful mechanism of emotion expression, there is a growing use of language data and advanced natural language processing (NLP) algorithms to shed light on fundamental questions about emotions. Although there is a general field of affective computing with dedicated venues, there is no dedicated venue for work at the intersection of NLP and Affective Science. Therefore, we propose a new workshop on Computational Affective Science (CAS) for work on all research associated with understanding affect and emotions through language and computation.

CAS vs. Sentiment Analysis (SA)

While sentiment workshops and sentiment tracks have existed for almost two decades now, their focus has predominantly been on developing novel automatic algorithms for sentiment and emotion detection from text. However, papers published at CAS will focus on understanding emotions and associated phenomena. A novel algorithm that helps to achieve that goal is welcome, but not required. Researchers are encouraged to use approaches that best address the research question - even if the computational approach is simple or well known.

CAS vs Affective Computing (AC)

Affective Computing is an interdisciplinary field with a focus on developing systems and devices that can recognize, interpret, and express human emotions. In contrast CAS has a focus on the science of how emotions work and how they impact our lives.

CAS, SA, and AC have overlaps, but also clear differences, especially in terms of their purpose and focus. This also necessitates differences in how these works are reviewed. While SA and AC value algorithmic and computational novelty, CAS values new findings in the understanding of affect.

Interdisciplinary Focus

A common critique of NLP work is the lack of theory. CAS is co-organized by researchers in NLP, Psychology, and Cognitive Science. In addition to the usual archival publications, it will have a dedicated non-archival track for two-page abstracts (aimed at increasing participation from fields outside of Computer Science). We foresee this new workshop as an interdisciplinary hub that will foster innovative CAS research. Simultaneously, practitioners of emotion/sentiment analysis and generation will benefit from an increased exposure to the latest theories and findings in Affective Science.

Subareas

The Nature of Affect and Computational Modeling of Emotions

Computational experiments that add to our understanding of affect and emotions. This includes findings relevant to theories of emotion, the biology of emotions, the neuroscience of emotions, and models of emotions such as appraisal models, dimensional models, models of constructed emotion, cognitive-affective architectures, emotion dynamics, emotion granularity, emotion regulation, affective embodiment, evolutionary affect development, developmental affect, emotion and cognition, etc. Note that many of these can be applied to: human beings, animals, and even artificial agents.

Affective Data and Resources

Work on compiling and annotating affect-related information in text, speech, facial and bodily expression, physiological signal processing, etc. Since this proposal is for a workshop at an NLP conference, there will be a focus on text data (monolingual, multilingual) as well as multimodal data. Data from under served languages is especially welcome.

Emotion Recognition, Prediction, and Inference

This area encompasses both instance-level and aggregate-level analyses. At the instance level, it includes emotion classification, estimation of emotion intensity, detection of emotion causes in text video, and context-aware affect inference that accounts for cultural, situational, or social factors. At the aggregate level, it involves constructing emotion arcs from multiple utterances or posts, identifying large-scale emotional trends over time, across locations, or toward specific entities (e.g., climate change), and performing document-level and cross-document emotion analysis.

Applications

Possible topics include: affect and health, such as for understanding psychopathology and mental disorders, affect and behavior or social science, encompassing the modeling of interpersonal affect, empathy, group-level emotions, polarization, affect contagion, and computational models of emotion regulation. Additional topics extend to affect in education, the study of affect in literature, storytelling, digital humanities, and affect in commerce and consumer interactions.

Explainability and Interpretability in Computational Affective Models

Work aimed at improving the transparency and interpretability of affective systems. This includes understanding how models represent and infer emotions, and identifying key cues driving predictions.

Ethics, Fairness, Theory Integration, Philosophical Implications

Encompasses work addressing the bias and generalizability of affective systems across demographics, as well as privacy and ethical considerations in affective data collection. It also includes research that critically examines whether automatic NLP systems are grounded in current and valid theories of affect and emotion. Finally, this area invites discussions on the philosophical and societal implications of machines that model or simulate affect, including what it means for artificial agents to exhibit or respond to emotions.