Sarcasm Detection in Tweets with BERT and GloVe Embeddings

TL;DR

This paper presents a machine learning approach combining BERT and GloVe embeddings, along with user context, to improve sarcasm detection in tweets, addressing the ambiguity inherent in sarcastic expressions.

Contribution

It introduces a novel sarcasm detection model that integrates contextual user information with advanced embeddings, enhancing detection accuracy over existing methods.

Findings

Improved sarcasm detection accuracy using combined embeddings and context.

Effective preprocessing and embedding extraction for Twitter data.

Demonstrated the importance of user context in understanding sarcasm.

Abstract

Sarcasm is a form of communication in whichthe person states opposite of what he actually means. It is ambiguous in nature. In this paper, we propose using machine learning techniques with BERT and GloVe embeddings to detect sarcasm in tweets. The dataset is preprocessed before extracting the embeddings. The proposed model also uses the context in which the user is reacting to along with his actual response.