A Survey on Sarcasm Detection in Social Media Audio and Text Conversation Using Support Vector Machine
Keywords:
SVM, Bag of Words, SarcasmAbstract
Emotion recognition plays a major role in making the human-machine interactions more natural. In spite of the different techniques to boost machine intelligence, machines are still not able to make out human emotions and expressions correctly. Emotion recognition automatically identifies the emotional state of the human from his or her speech. One of the greatest challenges in speech technology is evaluating the speaker’s emotion. Usually emotion recognition tasks focus on extracting features from audio. Speaker’s emotion can also be detected using text mining technique on audio material after translating it into text. One of the most important emotions is sarcasm[3]. Sarcasm is the use of language that normally signifies the opposite in order to mock or convey contempt. The goal of Sarcasm Detection is to determine whether a sentence is sarcastic or non-sarcastic. In this paper we are trying to detect sarcasm from the audio and text conversations present in social media. Here we will use SVM machine learning approach to classify sarcasm from the given data.This method aims to enhance the efficiency of sarcasm classification by consolidating the features of both audio and text into a single feature vector which is then given to the SVM classifier. Before applying the SVM approach, both text and audio are handled separately and classified .This allows the comparison of these methods with our proposed approach.
IndexTerms—SVM, Bag of Words, Sarcasm
References
. Agrawal, A. (2020) “Did you really mean what you said?” :SarcasmDetection in Hindi-English Code-Mixed Data using Bilingual WordEmbeddings, Proceedings of the Sixth Workshop on Noisy User-generatedText (W-NUT 2020).
. Babanejad, N. (2020) Affective and Contextual Embedding for SarcasmDetection, Proceedings of the 28th International Conference onComputational Linguistics.
. Gupta, S. (2021) FiLMing Multimodal Sarcasm Detection with Attention, International Conference on Neural Information Processing .ICONIP2021: Neural Information Processing pp 178–18618.
. Handoyo, A. T. (2021) Sarcasm Detection in Twitter -- Performance Impactwhile using Data Augmentation: Word Embeddings.
. Liu, Yiyi. (2022) A Dual-Channel Framework for Sarcasm Recognition byDetecting Sentiment Conflict Accepted by Findings of NAACL 2022.
. Misra, R (2018) Sarcasm Detection using Hybrid Neural Network, ResearchGate.
. Nigam, S. K. (2022) Robust Approaches for Sarcasm Detection for Englishand Arabic Using Transformers and Data Augmentation Plumeria atSemEval-2022 Task 6.
. Pelser, D. (2019) deep and dense sarcasm detection, Deep AI Publication.
. Rambam, S. G.-T. (2005). 1. R Neumayer , A Rauber. Integration of Textand Audio Features for Genre Classification in Music Information Retrieval.
In: Advances in Information Retrieval; 2007. p. 724-727.
. R. K. (2018). Sarcasm Detection Using Machine Learning Techniques.International Publication of Recent Scientific Research, 26368-26372.
. Shmueli, B. (2020) Reactive Supervision: A New Method for CollectingSarcasm Data, https://www.researchgate.net/publication/344411248
. Yang, Y. (2014) Toward Multi-Modal Music Emotion Classification.Advances in Multimedia Information Processing- PCM; 2008. p. 70-79.
Downloads
Published
How to Cite
Issue
Section
License
This work is licensed under a Creative Commons Attribution 4.0 International License.
Re-users must give appropriate credit, provide a link to the license, and indicate if changes were made. You may do so in any reasonable manner, but not in any way that suggests the licensor endorses you or your use. This license allows for redistribution, commercial and non-commercial, as long as the original work is properly credited.
