Sarcasm Detection in Twitter -- Performance Impact while using Data Augmentation: Word Embeddings
This work addresses the problem of sarcasm detection for natural language processing applications like sentiment analysis, but it is incremental as it builds on existing methods with data augmentation.
The paper tackles sarcasm detection in Twitter by proposing a contextual model using RoBERTa and data augmentation with GloVe word embeddings to balance datasets, achieving a 3.2% performance gain on the iSarcasm dataset with an F-score of 40.4% compared to 37.2% without augmentation.
Sarcasm is the use of words usually used to either mock or annoy someone, or for humorous purposes. Sarcasm is largely used in social networks and microblogging websites, where people mock or censure in a way that makes it difficult even for humans to tell if what is said is what is meant. Failure to identify sarcastic utterances in Natural Language Processing applications such as sentiment analysis and opinion mining will confuse classification algorithms and generate false results. Several studies on sarcasm detection have utilized different learning algorithms. However, most of these learning models have always focused on the contents of expression only, leaving the contextual information in isolation. As a result, they failed to capture the contextual information in the sarcastic expression. Moreover, some datasets used in several studies have an unbalanced dataset which impacting the model result. In this paper, we propose a contextual model for sarcasm identification in twitter using RoBERTa, and augmenting the dataset by applying Global Vector representation (GloVe) for the construction of word embedding and context learning to generate more data and balancing the dataset. The effectiveness of this technique is tested with various datasets and data augmentation settings. In particular, we achieve performance gain by 3.2% in the iSarcasm dataset when using data augmentation to increase 20% of data labeled as sarcastic, resulting F-score of 40.4% compared to 37.2% without data augmentation.