Sarcasm Detection using Hybrid Neural Network

TL;DR

This paper introduces a new dataset of news headlines for sarcasm detection and proposes a hybrid neural network with attention mechanism, achieving a 5% accuracy improvement over baseline models.

Contribution

The study presents a novel dataset from sarcastic news websites and a hybrid neural network architecture with attention for improved sarcasm detection.

Findings

Achieved approximately 5% higher accuracy than baseline models.

Introduced a new dataset with news headlines from sarcastic and real news sources.

Demonstrated the effectiveness of attention mechanisms in sarcasm detection.

Abstract

Sarcasm Detection has enjoyed great interest from the research community, however the task of predicting sarcasm in a text remains an elusive problem for machines. Past studies mostly make use of twitter datasets collected using hashtag based supervision but such datasets are noisy in terms of labels and language. To overcome these shortcoming, we introduce a new dataset which contains news headlines from a sarcastic news website and a real news website. Next, we propose a hybrid Neural Network architecture with attention mechanism which provides insights about what actually makes sentences sarcastic. Through experiments, we show that the proposed model improves upon the baseline by ~ 5% in terms of classification accuracy.