Sarcasm Detection using Genetic Optimization on LSTM with CNN
Darkunde Mayur Ashok, Agrawal Nidhi Ghanshyam, Sayed Saniya Salim, Dungarpur Burhanuddin Mazahir, Bhushan Thakare
Abstract
The challenging problem of 21 <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">st</sup> Century is to detect sarcasm in vivid data available on a large scale. Over 20 years of study in this field, the past 10 years have shown a significant progress not only in semantic features, but also an upward trend has also been observed in the various machine-learning approaches to analyze and process the data. To enlist a few, theories of sarcasm, it's syntactical and semantic properties; lexical features have been an area of interest for almost all of them. In this paper, we propose a unique deep neural network model whose Bidirectional LSTM undergo Hyper parameters optimization using genetic algorithm followed by a Convolution Neural Network for sarcasm detection. We put forward the results in a robust way, which may result in a better future work in this field.