This paper presents a study on using the RoBERTa language model for emotion classification of essays as part of the ‘Shared Task on Empathy Detection, Emotion Classification and Personality Detection in Interactions’ organized as part of ‘WASSA 2023’ at ‘ACL 2023’. Emotion classification is a challenging task in natural language processing, and imbalanced datasets further exacerbate this challenge. In this study, we explore the use of various data balancing techniques in combination with RoBERTa to improve the classification performance. We evaluate the performance of our approach (denoted by adityapatkar on Codalab) on a benchmark multi-label dataset of essays annotated with eight emotion categories, provided by the Shared Task organizers. Our results show that the proposed approach achieves the best macro F1 score in the competition’s training and evaluation phase. Our study provides insights into the potential of RoBERTa for handling imbalanced data in emotion classification. The results can have implications for the natural language processing tasks related to emotion classification.