Amazing technological breakthrough possible @S-Logix pro@slogix.in

Office Address

  • #5, First Floor, 4th Street Dr. Subbarayan Nagar Kodambakkam, Chennai-600 024 Landmark : Samiyar Madam
  • pro@slogix.in
  • +91- 81240 01111

Social List

Research Proposal on Deep Bi-directional Text Analysis for Sarcasm Detection

Research Proposal on Deep Bi-directional Text Analysis for Sarcasm Detection

  Sarcasm detection is a narrow research field in natural language processing (NLP) and the specific case of sentiment analysis. Sarcasm detection in the text identifies irony and incongruous that containing utterances that express user’s negative attitudes with positive contrary words. The deep learning model is highly used for automatic sarcasm detection by determining the discriminatory features in sarcastic sentences. A significant requirement of sarcasm detection is to analyze forward and backward information in utterances.

  Deep learning comprises bi-directional neural networks which process the information in forward and reverse directions simultaneously. Sarcasm detection in text analysis using deep bi-directional neural architectures improves performance and accurately predicts whether a sentence is sarcastic or non-sarcastic.

  • On account of the innate ambiguous nature of sarcasm, sarcasm detection is a critical step to sentiment analysis, considering the ubiquity and difficulties of sarcasm in sentiment-carrying text.

  • Deep learning models emerged as the prevalent method for sarcasm detection as it utilizes high-level abstractions in data using a deep network.

  • Sarcasm is context-sensitive.

  • Higher detective performance is yielded with bi-directional deep neural architectures compared to unidirectional deep neural architecture.

  • The bidirectional deep neural network analyzes both the left and right context information from the text for sarcasm detection.

  • Sarcasm detection using a bi-directional deep learning model from text produces superior performance by apprehending inter-sentence dependencies.