VISU at WASSA 2023 Shared Task: Detecting Emotions in Reaction to News Stories Leveraging BERT and Stacked Embeddings
This work addresses emotion detection in complex dialogues for natural language processing applications, but it is incremental as it builds on existing methods for a specific shared task.
The paper tackled emotion classification from essays reacting to news articles by developing deep learning models using stacked embeddings and BiLSTM/Transformer architectures, achieving a Macro F1-Score of 0.2717 and ranking tenth in the WASSA 2023 shared task.
Our system, VISU, participated in the WASSA 2023 Shared Task (3) of Emotion Classification from essays written in reaction to news articles. Emotion detection from complex dialogues is challenging and often requires context/domain understanding. Therefore in this research, we have focused on developing deep learning (DL) models using the combination of word embedding representations with tailored prepossessing strategies to capture the nuances of emotions expressed. Our experiments used static and contextual embeddings (individual and stacked) with Bidirectional Long short-term memory (BiLSTM) and Transformer based models. We occupied rank tenth in the emotion detection task by scoring a Macro F1-Score of 0.2717, validating the efficacy of our implemented approaches for small and imbalanced datasets with mixed categories of target emotions.