Deep emotion recognition in textual conversations: A survey

P Pereira, H Moniz, JP Carvalho - Artificial Intelligence Review, 2025 - Springer
Abstract Emotion Recognition in Conversations (ERC) is a key step towards successful
human–machine interaction. While the field has seen tremendous advancement in the last …

Arabic Emotion Recognition in Low-Resource Settings: A Novel Diverse Model Stacking Ensemble with Self-Training

MJ Althobaiti - Applied Sciences, 2023 - mdpi.com
Emotion recognition is a vital task within Natural Language Processing (NLP) that involves
automatically identifying emotions from text. As the need for specialized and nuanced …

Fuzzy fingerprinting transformer language-models for emotion recognition in conversations

P Pereira, R Ribeiro, H Moniz, L Coheur… - … on Fuzzy Systems …, 2023 - ieeexplore.ieee.org
Fuzzy Fingerprints have been successfully used as an interpretable text classification
technique, but, like most other techniques, have been largely surpassed in performance by …

ConText at WASSA 2024 Empathy and Personality Shared Task: History-Dependent Embedding Utterance Representations for Empathy and Emotion Prediction in …

P Pereira, H Moniz, JP Carvalho - arXiv preprint arXiv:2407.03818, 2024 - arxiv.org
Empathy and emotion prediction are key components in the development of effective and
empathetic agents, amongst several other applications. The WASSA shared task on …

SEC: contexte émotionnel phrastique intégré pour la reconnaissance émotionnelle efficiente dans la conversation

B Gendron, G Guibon - Actes de JEP-TALN-RECITAL 2024 …, 2024 - inria.hal.science
L'essor des modèles d'apprentissage profond a apporté une contribution significative à la
reconnaissance des émotions dans les conversations (ERC). Cependant, cette tâche reste …

An Emotion Recognition Method in Conversations Based on Knowledge Selection and Fuzzy Fingerprints

Y You, Y Wang - International Artificial Intelligence Conference, 2023 - Springer
In the context of large-scale pre-trained language models such as BERT or RoBERTa, they
exhibit outstanding performance in natural language processing tasks, but they suffer from a …