Large language models (LLMs) are increasingly used to generate self-explanations alongside their predictions, a practice that raises concerns about the faithfulness of these explanations, especially in low-resource languages. This study evaluates the faithfulness of LLM-generated explanations in the context of emotion classification in Persian, a low-resource language, by comparing the influential words identified by the model against those identified by human annotators. We assess faithfulness using confidence scores derived from token-level log-probabilities. Two prompting strategies, differing in the order of explanation and prediction (Predict-then-Explain and Explain-then-Predict), are tested for their impact on explanation faithfulness. Our results reveal that while LLMs achieve strong classification performance, their generated explanations often diverge from faithful reasoning, showing greater agreement with each other than with human judgments. These results highlight the limitations of current explanation methods and metrics, emphasizing the need for more robust approaches to ensure LLM reliability in multilingual and low-resource contexts.

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.

Understanding emotions in the Indonesian language is essential for improving customer experiences in e-commerce. This study focuses on enhancing the accuracy of emotion classification in Indonesian by leveraging advanced language models, IndoBERT and DistilBERT. A key component of our approach was data processing, specifically data augmentation, which included techniques such as back-translation and synonym replacement. These methods played a significant role in boosting the model's performance. After hyperparameter tuning, IndoBERT achieved an accuracy of 80\%, demonstrating the impact of careful data processing. While combining multiple IndoBERT models led to a slight improvement, it did not significantly enhance performance. Our findings indicate that IndoBERT was the most effective model for emotion classification in Indonesian, with data augmentation proving to be a vital factor in achieving high accuracy. Future research should focus on exploring alternative architectures and strategies to improve generalization for Indonesian NLP tasks.

The emotional content of song lyrics plays a pivotal role in shaping listener experiences and influencing musical preferences. This paper investigates the task of multi-label emotional attribution of song lyrics by predicting six emotional intensity scores corresponding to six fundamental emotions. A manually labeled dataset is constructed using a mean opinion score (MOS) approach, which aggregates annotations from multiple human raters to ensure reliable ground-truth labels. Leveraging this dataset, we conduct a comprehensive evaluation of several publicly available large language models (LLMs) under zero-shot scenarios. Additionally, we fine-tune a BERT-based model specifically for predicting multi-label emotion scores. Experimental results reveal the relative strengths and limitations of zero-shot and fine-tuned models in capturing the nuanced emotional content of lyrics. Our findings highlight the potential of LLMs for emotion recognition in creative texts, providing insights into model selection strategies for emotion-based music information retrieval applications. The labeled dataset is available at https://github.com/LLM-HITCS25S/LyricsEmotionAttribution.

Emotion recognition in low-resource languages like Marathi remains challenging due to limited annotated data. We present L3Cube-MahaEmotions, a high-quality Marathi emotion recognition dataset with 11 fine-grained emotion labels. The training data is synthetically annotated using large language models (LLMs), while the validation and test sets are manually labeled to serve as a reliable gold-standard benchmark. Building on the MahaSent dataset, we apply the Chain-of-Translation (CoTR) prompting technique, where Marathi sentences are translated into English and emotion labeled via a single prompt. GPT-4 and Llama3-405B were evaluated, with GPT-4 selected for training data annotation due to superior label quality. We evaluate model performance using standard metrics and explore label aggregation strategies (e.g., Union, Intersection). While GPT-4 predictions outperform fine-tuned BERT models, BERT-based models trained on synthetic labels fail to surpass GPT-4. This highlights both the importance of high-quality human-labeled data and the inherent complexity of emotion recognition. An important finding of this work is that generic LLMs like GPT-4 and Llama3-405B generalize better than fine-tuned BERT for complex low-resource emotion recognition tasks. The dataset and model are shared publicly at https://github.com/l3cube-pune/MarathiNLP

Recent advancements in EEG-based emotion recognition have shown promising outcomes using both deep learning and classical machine learning approaches; however, most existing studies focus narrowly on binary valence prediction or subject-specific classification, which limits generalizability and deployment in real-world affective computing systems. To address this gap, this paper presents a unified, multigranularity EEG emotion classification framework built on the GAMEEMO dataset, which consists of 14-channel EEG recordings and continuous self-reported emotion ratings (boring, horrible, calm, and funny) from 28 subjects across four emotion-inducing gameplay scenarios. Our pipeline employs a structured preprocessing strategy that comprises temporal window segmentation, hybrid statistical and frequency-domain feature extraction, and z-score normalization to convert raw EEG signals into robust, discriminative input vectors. Emotion labels are derived and encoded across three complementary axes: (i) binary valence classification based on the averaged polarity of positive and negative emotion ratings, and (ii) Multi-class emotion classification, where the presence of the most affective state is predicted. (iii) Fine-grained multi-label representation via binning each emotion into 10 ordinal classes. We evaluate a broad spectrum of models, including Random Forest, XGBoost, and SVM, alongside deep neural architectures such as LSTM, LSTM-GRU, and CNN-LSTM. Among these, the LSTM-GRU model consistently outperforms the others, achieving an F1-score of 0.932 in the binary valence task and 94.5% and 90.6% in both multi-class and Multi-Label emotion classification.

Research on understanding emotions in written language continues to expand, especially for understudied languages with distinctive regional expressions and cultural features, such as Bangla. This study examines emotion analysis using 22,698 social media comments from the EmoNoBa dataset. For language analysis, we employ machine learning models--Linear SVM, KNN, and Random Forest--with n-gram data from a TF-IDF vectorizer. We additionally investigated how PCA affects the reduction of dimensionality. Moreover, we utilized a BiLSTM model and AdaBoost to improve decision trees. To make our machine learning models easier to understand, we used LIME to explain the predictions of the AdaBoost classifier, which uses decision trees. With the goal of advancing sentiment analysis in languages with limited resources, our work examines various techniques to find efficient techniques for emotion identification in Bangla.

People exploit the predictability of lexical structures during text comprehension. Though predictable structure is also present in speech, the degree to which prosody, e.g. intonation, tempo, and loudness, contributes to such structure independently of the lexical content is unclear. This study leverages self-supervised learning (SSL) to examine the temporal granularity of structures in the acoustic correlates of prosody. Representations from our proposed Masked Prosody Model can predict perceptual labels dependent on local information, such as word boundaries, but provide the most value for labels involving longer-term structures, like emotion recognition. Probing experiments across various perceptual labels show strong relative gains over untransformed pitch, energy, and voice activity features. Our results reveal the importance of SSL training objective timescale and highlight the value of complex SSL-encoded structures compared to more constrained classical structures.

Understanding and predicting human emotional and physiological states using wearable sensors has critical applications in stress monitoring, mental health assessment, and affective computing. In this study, we present a novel Multi - Task Physics - Informed Neural Network (PINN) that simultaneously performs Electrodermal Activity (EDA) prediction and emotion classification using the publicly available WESAD dataset. Our model integrates psychological self - reports (PANAS and SAM) with a physics - inspired differential formulation of EDA dynamics, enforcing biophysically grounded constraints through a custom loss that balances data - driven learning and physiological interpretability. The architecture supports dual outputs -- regression for EDA and classification for emotional states -- trained under a unified multi - task framework. Evaluated via 5 - fold cross - validation, the proposed method achieves an average EDA RMSE of 0.0362, Pearson correlation (r) of 0.9919, and F1 - score of 94.08%, outperforming both classical baselines (e.g., SVR, XGBoost) and ablated variants such as emotion - only and EDA - only models. Comparative ablation and multi - task experiments show that including both physics constraints and emotion prediction enhances generalization, reduces overfitting, and leads to physiologically consistent outputs. Moreover, the learned physical parameters -- decay rate (α), emotion influence weights (β), and temporal scaling (γ) -- remain interpretable and stable across folds, confirming the alignment between the model's latent representation and known stress - response theory. This is the first work to introduce a multi - task PINN architecture for wearable affective computing, bridging black - box deep learning and domain knowledge. Our framework lays the groundwork for interpretable, multimodal, and deployable systems in healthcare and human - computer interaction.

This paper presents our approach for SemEval 2025 Task 11 Track A, focusing on multilabel emotion classification across 28 languages. We explore two main strategies: fully fine-tuning transformer models and classifier-only training, evaluating different settings such as fine-tuning strategies, model architectures, loss functions, encoders, and classifiers. Our findings suggest that training a classifier on top of prompt-based encoders such as mE5 and BGE yields significantly better results than fully fine-tuning XLMR and mBERT. Our best-performing model on the final leaderboard is an ensemble combining multiple BGE models, where CatBoost serves as the classifier, with different configurations. This ensemble achieves an average F1-macro score of 56.58 across all languages.