Transformer models have significantly advanced the field of emotion recognition. However, there are still open challenges when exploring open-ended queries for Large Language Models (LLMs). Although current models offer good results, automatic emotion analysis in open texts presents significant challenges, such as contextual ambiguity, linguistic variability, and difficulty interpreting complex emotional expressions. These limitations make the direct application of generalist models difficult. Accordingly, this work compares the effectiveness of fine-tuning and prompt engineering in emotion detection in three distinct scenarios: (i) performance of fine-tuned pre-trained models and general-purpose LLMs using simple prompts; (ii) effectiveness of different emotion prompt designs with LLMs; and (iii) impact of emotion grouping techniques on these models. Experimental tests attain metrics above 70% with a fine-tuned pre-trained model for emotion recognition. Moreover, the findings highlight that LLMs require structured prompt engineering and emotion grouping to enhance their performance. These advancements improve sentiment analysis, human-computer interaction, and understanding of user behavior across various domains.

While Ukrainian NLP has seen progress in many texts processing tasks, emotion classification remains an underexplored area with no publicly available benchmark to date. In this work, we introduce EmoBench-UA, the first annotated dataset for emotion detection in Ukrainian texts. Our annotation schema is adapted from the previous English-centric works on emotion detection (Mohammad et al., 2018; Mohammad, 2022) guidelines. The dataset was created through crowdsourcing using the Toloka.ai platform ensuring high-quality of the annotation process. Then, we evaluate a range of approaches on the collected dataset, starting from linguistic-based baselines, synthetic data translated from English, to large language models (LLMs). Our findings highlight the challenges of emotion classification in non-mainstream languages like Ukrainian and emphasize the need for further development of Ukrainian-specific models and training resources.

Emotions manifest through physical experiences and bodily reactions, yet identifying such embodied emotions in text remains understudied. We present an embodied emotion classification dataset, CHEER-Ekman, extending the existing binary embodied emotion dataset with Ekman's six basic emotion categories. Using automatic best-worst scaling with large language models, we achieve performance superior to supervised approaches on our new dataset. Our investigation reveals that simplified prompting instructions and chain-of-thought reasoning significantly improve emotion recognition accuracy, enabling smaller models to achieve competitive performance with larger ones. Our dataset is publicly available at: https://github.com/menamerai/cheer-ekman.

This study presents a comprehensive comparative evaluation of four state-of-the-art Large Language Models (LLMs)--Claude 3.7 Sonnet, DeepSeek-V3, Gemini 2.0 Flash, and GPT-4o--for sentiment analysis and emotion detection in Persian social media texts. Comparative analysis among LLMs has witnessed a significant rise in recent years, however, most of these analyses have been conducted on English language tasks, creating gaps in understanding cross-linguistic performance patterns. This research addresses these gaps through rigorous experimental design using balanced Persian datasets containing 900 texts for sentiment analysis (positive, negative, neutral) and 1,800 texts for emotion detection (anger, fear, happiness, hate, sadness, surprise). The main focus was to allow for a direct and fair comparison among different models, by using consistent prompts, uniform processing parameters, and by analyzing the performance metrics such as precision, recall, F1-scores, along with misclassification patterns. The results show that all models reach an acceptable level of performance, and a statistical comparison of the best three models indicates no significant differences among them. However, GPT-4o demonstrated a marginally higher raw accuracy value for both tasks, while Gemini 2.0 Flash proved to be the most cost-efficient. The findings indicate that the emotion detection task is more challenging for all models compared to the sentiment analysis task, and the misclassification patterns can represent some challenges in Persian language texts. These findings establish performance benchmarks for Persian NLP applications and offer practical guidance for model selection based on accuracy, efficiency, and cost considerations, while revealing cultural and linguistic challenges that require consideration in multilingual AI system deployment.

The SemEval-2025 Task 11, Bridging the Gap in Text-Based Emotion Detection, introduces an emotion recognition challenge spanning over 28 languages. This competition encourages researchers to explore more advanced approaches to address the challenges posed by the diversity of emotional expressions and background variations. It features two tracks: multi-label classification (Track A) and emotion intensity prediction (Track B), covering six emotion categories: anger, fear, joy, sadness, surprise, and disgust. In our work, we systematically explore the benefits of two contrastive learning approaches: sample-based (Contrastive Reasoning Calibration) and generation-based (DPO, SimPO) contrastive learning. The sample-based contrastive approach trains the model by comparing two samples to generate more reliable predictions. The generation-based contrastive approach trains the model to differentiate between correct and incorrect generations, refining its prediction. All models are fine-tuned from LLaMa3-Instruct-8B. Our system achieves 9th place in Track A and 6th place in Track B for English, while ranking among the top-tier performing systems for other languages.

This paper presents our system built for the WASSA-2024 Cross-lingual Emotion Detection Shared Task. The task consists of two subtasks: first, to assess an emotion label from six possible classes for a given tweet in one of five languages, and second, to predict words triggering the detected emotions in binary and numerical formats. Our proposed approach revolves around fine-tuning quantized large language models, specifically Orca~2, with low-rank adapters (LoRA) and multilingual Transformer-based models, such as XLM-R and mT5. We enhance performance through machine translation for both subtasks and trigger word switching for the second subtask. The system achieves excellent performance, ranking 1st in numerical trigger words detection, 3rd in binary trigger words detection, and 7th in emotion detection.

--Emotion recognition is a key task in affective computing with applications in healthcare, human-computer interaction, and surveillance systems. This study proposes a Conditional Generative Adversarial Network (cGAN)-based approach to generate synthetic emotion-specific facial images to augment training data and mitigate class imbalance. The generator learns to synthesize grayscale 64 64 facial images conditioned on emotion labels, while the discriminator distinguishes between real and generated images using label conditioning. The model was trained on the FER-2013 dataset and evaluated over 300 epochs. Training results demonstrate stable adversarial loss convergence, indicating effective learning and generation capability.

This paper explores the application of a simple weighted loss function to Transformer-based models for multi-label emotion detection in SemEval-2025 Shared Task 11. Our approach addresses data imbalance by dynamically adjusting class weights, thereby enhancing performance on minority emotion classes without the computational burden of traditional resampling methods. We evaluate BERT, RoBERTa, and BART on the BRIGHTER dataset, using evaluation metrics such as Micro F1, Macro F1, ROC-AUC, Accuracy, and Jaccard similarity coefficients. The results demonstrate that the weighted loss function improves performance on high-frequency emotion classes but shows limited impact on minority classes. These findings underscore both the effectiveness and the challenges of applying this approach to imbalanced multi-label emotion detection.

Emotion detection in older adults is crucial for understanding their cognitive and emotional well-being, especially in hospital and assisted living environments. In this work, we investigate an edge-based, non-obtrusive approach to emotion identification that uses only physiological signals obtained via wearable sensors. Our dataset includes data from 40 older individuals. Emotional states were obtained using physiological signals from the Empatica E4 and Shimmer3 GSR+ wristband and facial expressions were recorded using camera-based emotion recognition with the iMotion's Facial Expression Analysis (FEA) module. The dataset also contains twelve emotion categories in terms of relative intensities. We aim to study how well emotion recognition can be accomplished using simply physiological sensor data, without the requirement for cameras or intrusive facial analysis. By leveraging classical machine learning models, we predict the intensity of emotional responses based on physiological signals. We achieved the highest 0.782 r2 score with the lowest 0.0006 MSE on the regression task. This method has significant implications for individuals with Alzheimer's Disease and Related Dementia (ADRD), as well as veterans coping with Post-Traumatic Stress Disorder (PTSD) or other cognitive impairments. Our results across multiple classical regression models validate the feasibility of this method, paving the way for privacy-preserving and efficient emotion recognition systems in real-world settings.

We investigate the feasibility of inferring emotional states exclusively from physiological signals, thereby presenting a privacy-preserving alternative to conventional facial recognition techniques. We conduct a performance comparison of classical machine learning algorithms and hybrid quantum machine learning (QML) methods with a quantum kernel-based model. Our results indicate that the quantum-enhanced SVM surpasses classical counterparts in classification performance across all emotion categories, even when trained on limited datasets. The F1 scores over all classes are over 80% with around a maximum of 36% improvement in the recall values. The integration of wearable sensor data with quantum machine learning not only enhances accuracy and robustness but also facilitates unobtrusive emotion recognition. This methodology holds promise for populations with impaired communication abilities, such as individuals with Alzheimer's Disease and Related Dementias (ADRD) and veterans with Post-Traumatic Stress Disorder (PTSD). The findings establish an early foundation for passive emotional monitoring in clinical and assisted living conditions.