What type of study is this?

September 10, 2025Open Access

EmoBERTa–CNN: Hybrid Deep Learning Approach Capturing Global Semantics and Local Features for Enhanced Emotion Recognition in Conversational Settings

Key Points

The EmoBERTa–CNN model significantly improves emotion recognition accuracy in conversational settings.
Experimental results include F1-scores of 96.0% on SemEval-2019 and 79.45% on MELD datasets.
This framework combines the strengths of transformer-based models and convolutional neural networks.
The approach highlights the importance of capturing both global context and local emotional cues.

Abstract

Emotion recognition in conversations is a key task in natural language processing that enhances the quality of human–computer interactions. Although existing deep learning and Transformer-based pretrained language models have shown remarkably enhanced performances, both approaches have inherent limitations. Deep learning models often fail to capture the global semantic context, whereas Transformer-based pretrained language models can overlook subtle, local emotional cues. To overcome these challenges, we developed EmoBERTa–CNN, a hybrid framework that combines EmoBERTa’s ability to capture global semantics with the capability of convolutional neural networks (CNNs) to extract local emotional features. Experiments on the SemEval-2019 Task 3 and Multimodal EmotionLines Dataset (MELD) demonstrated that the proposed EmoBERTa–CNN model achieved F1-scores of 96.0% and 79.45%, respectively, significantly outperforming existing methods and confirming its effectiveness for emotion recognition in conversations.

Read Full Paperexternally

Bookmark

View Full Paper

Cite This Study

Zhang et al. (Tue,) studied this question.

synapsesocial.com/papers/68c1ae6654b1d3bfb60e609c https://doi.org/https://doi.org/10.3390/math13152438

Also Consider

Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context:

Bookmark

View Full Paper