Emotion Recognition

Emotion detection is a central problem in NLP, with recent progress driven by transformer-based models trained on established datasets. However, little is known about the linguistic regularities that characterize how emotions are expressed across different corpora and labels. This study examines whether linguistic features can serve as reliable interpretable signals for emotion recognition in text. We extract emotion-specific linguistic signatures from 13 English datasets and evaluate how incorporating these features into transformer models impacts performance. Our RoBERTa-based models enriched with high level linguistic features achieve consistent performance gains of up to +2.4 macro F1 on the GoEmotions benchmark, showing that explicit lexical cues can complement neural representations and improve robustness in predicting emotion categories.

Emotion recognition from multi-modal physiological and behavioral signals plays a pivotal role in affective computing, yet most existing models remain constrained to the prediction of singular emotions in controlled laboratory settings. Real-world human emotional experiences, by contrast, are often characterized by the simultaneous presence of multiple affective states, spurring recent interest in mixed emotion recognition as an emotion distribution learning problem. Current approaches, however, often neglect the valence consistency and structured correlations inherent among coexisting emotions. To address this limitation, we propose a Memory-guided Prototypical Co-occurrence Learning (MPCL) framework that explicitly models emotion co-occurrence patterns. Specifically, we first fuse multi-modal signals via a multi-scale associative memory mechanism. To capture cross-modal semantic relationships, we construct emotion-specific prototype memory banks, yielding rich physiological and behavioral representations, and employ prototype relation distillation to ensure cross-modal alignment in the latent prototype space. Furthermore, inspired by human cognitive memory systems, we introduce a memory retrieval strategy to extract semantic-level co-occurrence associations across emotion categories. Through this bottom-up hierarchical abstraction process, our model learns affectively informative representations for accurate emotion distribution prediction. Comprehensive experiments on two public datasets demonstrate that MPCL consistently outperforms state-of-the-art methods in mixed emotion recognition, both quantitatively and qualitatively.

Mood instability is a key behavioral indicator of mental health, yet traditional assessments rely on infrequent and retrospective reports that fail to capture its continuous nature. Smartphone-based mobile sensing enables passive, in-the-wild mood inference from everyday behaviors; however, deploying such systems at scale remains challenging due to privacy constraints, uneven sensing availability, and substantial variability in behavioral patterns. In this work, we study mood inference using smartphone sensing data in a cross-country federated learning setting, where each country participates as an independent client while retaining local data. We introduce FedFAP, a feature-aware personalized federated framework designed to accommodate heterogeneous sensing modalities across regions. Evaluations across geographically and culturally diverse populations show that FedFAP achieves an AUROC of 0.744, outperforming both centralized approaches and existing personalized federated baselines. Beyond inference, our results offer design insights for mood-aware systems, demonstrating how population-aware personalization and privacy-preserving learning can enable scalable and mood-aware mobile sensing technologies.

Dog emotion recognition plays a crucial role in enhancing human-animal interactions, veterinary care, and the development of automated systems for monitoring canine well-being. However, accurately interpreting dog emotions is challenging due to the subjective nature of emotional assessments and the absence of standardized ground truth methods. We present the CREMD (Crowd-sourced Emotional Multimodal Dogs Dataset), a comprehensive dataset exploring how different presentation modes (e.g., context, audio, video) and annotator characteristics (e.g., dog ownership, gender, professional experience) influence the perception and labeling of dog emotions. The dataset consists of 923 video clips presented in three distinct modes: without context or audio, with context but no audio, and with both context and audio. We analyze annotations from diverse participants, including dog owners, professionals, and individuals with varying demographic backgrounds and experience levels, to identify factors that influence reliable dog emotion recognition. Our findings reveal several key insights: (1) while adding visual context significantly improved annotation agreement, our findings regarding audio cues are inconclusive due to design limitations (specifically, the absence of a no-context-with-audio condition and limited clean audio availability); (2) contrary to expectations, non-owners and male annotators showed higher agreement levels than dog owners and female annotators, respectively, while professionals showed higher agreement levels, aligned with our initial hypothesis; and (3) the presence of audio substantially increased annotators' confidence in identifying specific emotions, particularly anger and fear.

Recognition of signers' emotions suffers from one theoretical challenge and one practical challenge, namely, the overlap between grammatical and affective facial expressions and the scarcity of data for model training. This paper addresses these two challenges in a cross-lingual setting using our eJSL dataset, a new benchmark dataset for emotion recognition in Japanese Sign Language signers, and BOBSL, a large British Sign Language dataset with subtitles. In eJSL, two signers expressed 78 distinct utterances with each of seven different emotional states, resulting in 1,092 video clips. We empirically demonstrate that 1) textual emotion recognition in spoken language mitigates data scarcity in sign language, 2) temporal segment selection has a significant impact, and 3) incorporating hand motion enhances emotion recognition in signers. Finally we establish a stronger baseline than spoken language LLMs.

Affective computing has matured rapidly in laboratory settings, yet no prior dataset combines (i) months-to-years of duration, (ii) a naturalistic workplace context, (iii) a stable small-team social structure, and (iv) a fully passive sensing protocol that survives institutional review. We introduce WELD, the first dataset to satisfy all four. WELD comprises 733,780 per-frame seven-class facial-expression probability vectors from 49 employees of a Chinese software company over 30.1 months (Nov 2021 - May 2024) -- the longest naturalistic in-the-wild emotion corpus and the only multi-year corpus supporting both within-individual longitudinal and within-team relational analyses on the same subjects. Data are released under a four-tier access model with only aggregated probabilities publicly downloadable. We validate the corpus by replicating three established phenomena (+43.1% weekend valence boost; 13:00-trough diurnal cycle; Shanghai 2022 lockdown effect d=-0.40), and report four novel findings: (1) variance decomposition attributes 19.3% of daily-valence variance to between-person differences and 29.8% to month seasonality -- a quantitative ceiling for future predictive models; (2) Hidden Markov decomposition reveals six emotional regimes with asymmetric negative-state dwell times (16-18 d vs 3 d); (3) leave-one-person-out turnover prediction reaches AUC=0.79 yet a Cox concordance index of only 0.52, exposing a metric-trap when AUC is reported without survival-aware baselines; (4) the corpus reveals systematic over-prediction of "angry" by an off-the-shelf FER model on neutral Asian faces (0.194 vs ~0.05 Western priors), making WELD valuable for FER fairness audits. A complex-systems analysis of the corpus appears as a companion preprint (arXiv:2510.16046).

Curriculum learning (CL) structures training from simple to complex samples, facilitating progressive learning. However, existing CL approaches for emotion recognition often rely on heuristic, data-driven, or model-based definitions of sample difficulty, neglecting the difficulty for human perception, a critical factor in subjective tasks like emotion recognition. We propose CHUCKLE (Crowdsourced Human Understanding Curriculum for Knowledge Led Emotion Recognition), a perception-driven CL framework that leverages annotator agreement and alignment in crowd-sourced datasets to define sample difficulty, under the assumption that clips challenging for humans are similarly hard for neural networks. Experimental results suggest that CHUCKLE enhances the performance of LSTMs and Transformers over non-curriculum baselines, while reducing the number of gradient updates, thereby enhancing both training efficiency and model robustness in both subject-dependent and subject-independent settings.

Despite the wide-scale usage and development of emotion classification datasets in NLP, the field lacks a standardized, large-scale resource that follows a psychologically grounded taxonomy. Existing datasets either use inconsistent emotion categories, suffer from limited sample size, or focus on specific domains. The SuperEmotion dataset addresses this gap by harmonizing diverse text sources into a unified framework based on Shaver's empirically validated emotion taxonomy, enabling more consistent cross-domain emotion recognition research. This report describes version 2 of the dataset. We also report baseline results for a fine-tuned ModernBERT encoder.

Labeling corpora constitutes a bottleneck to create models for new tasks or domains. Large language models mitigate the issue with automatic corpus labeling methods, particularly for categorical annotations. Some NLP tasks such as emotion intensity prediction, however, require text regression, but there is no work on automating annotations for continuous label assignments. Regression is considered more challenging than classification: The fact that humans perform worse when tasked to choose values from a rating scale lead to comparative annotation methods, including best-worst scaling. This raises the question if large language model-based annotation methods show similar patterns, namely that they perform worse on rating scale annotation tasks than on comparative annotation tasks. To study this, we automate emotion intensity predictions and compare direct rating scale predictions, pairwise comparisons and best-worst scaling. We find that the latter shows the highest reliability. A transformer regressor fine-tuned on these data performs nearly on par with a model trained on the original manual annotations.