Leveraging Emotion-specific Features to Improve Transformer Performance for Emotion Classification
This work addresses emotion classification for news analysis, but it is incremental as it builds on existing transformer methods with minor modifications.
The paper tackled emotion classification from news essays by enhancing transformer models with emotion-specific features and ensembling, achieving an accuracy of 0.619 and a macro F1 score of 0.520.
This paper describes the approach to the Emotion Classification shared task held at WASSA 2022 by team PVGs AI Club. This Track 2 sub-task focuses on building models which can predict a multi-class emotion label based on essays from news articles where a person, group or another entity is affected. Baseline transformer models have been demonstrating good results on sequence classification tasks, and we aim to improve this performance with the help of ensembling techniques, and by leveraging two variations of emotion-specific representations. We observe better results than our baseline models and achieve an accuracy of 0.619 and a macro F1 score of 0.520 on the emotion classification task.