Hyperbolic Feature-based Sarcasm Detection in Telugu Conversation Sentences

Recognition of sarcastic statements has been a challenge in the process of sentiment analysis. A sarcastic sentence contains only positive words conveying a negative sentiment. Therefore, it is tough for any automated machine to identify the exact sentiment of the text in the presence of sarcasm. Th...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Bharti Santosh Kumar, Naidu Reddy, Babu Korra Sathya
Formato:	article
Lenguaje:	EN
Publicado:	De Gruyter 2020
Materias:	hyperbolic features natural language processing sarcasm sentiment telugu 68t50 68t10 68t05 Science Q Electronic computers. Computer science QA75.5-76.95
Acceso en línea:	https://doaj.org/article/1cb34d5fb9404eaeb2b55ef54bef6a4f
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:1cb34d5fb9404eaeb2b55ef54bef6a4f
record_format	dspace
spelling	oai:doaj.org-article:1cb34d5fb9404eaeb2b55ef54bef6a4f2021-12-05T14:10:51ZHyperbolic Feature-based Sarcasm Detection in Telugu Conversation Sentences2191-026X10.1515/jisys-2018-0475https://doaj.org/article/1cb34d5fb9404eaeb2b55ef54bef6a4f2020-07-01T00:00:00Zhttps://doi.org/10.1515/jisys-2018-0475https://doaj.org/toc/2191-026XRecognition of sarcastic statements has been a challenge in the process of sentiment analysis. A sarcastic sentence contains only positive words conveying a negative sentiment. Therefore, it is tough for any automated machine to identify the exact sentiment of the text in the presence of sarcasm. The existing systems for sarcastic sentiment detection are limited to the text scripted in English. Nowadays, researchers have shown greater interest in low resourced languages such as Hindi, Telugu, Tamil, Arabic, Chinese, Dutch, Indonesian, etc. To analyse these low resource languages, the biggest challenge is the lack of available resources, especially in the context of Indian languages. Indian languages are very rich in morphology which pose a greater challenge for the automated machines. Telugu is one of the most popular languages after Hindi among Indian languages. In this article, we have collected and annotated a corpus of Telugu conversation sentences in the form of a question followed by a reply for sarcasm detection. Further, a set of algorithms are proposed for the analysis of sarcasm in the corpus of Telugu conversation sentences. The proposed algorithms are based on hyperbolic features namely, Interjection, Intensifier, Question mark and Exclamation symbol. The achieved accuracy is 94%.Bharti Santosh KumarNaidu ReddyBabu Korra SathyaDe Gruyterarticlehyperbolic featuresnatural language processingsarcasmsentimenttelugu68t5068t1068t05ScienceQElectronic computers. Computer scienceQA75.5-76.95ENJournal of Intelligent Systems, Vol 30, Iss 1, Pp 73-89 (2020)
institution	DOAJ
collection	DOAJ
language	EN
topic	hyperbolic features natural language processing sarcasm sentiment telugu 68t50 68t10 68t05 Science Q Electronic computers. Computer science QA75.5-76.95
spellingShingle	hyperbolic features natural language processing sarcasm sentiment telugu 68t50 68t10 68t05 Science Q Electronic computers. Computer science QA75.5-76.95 Bharti Santosh Kumar Naidu Reddy Babu Korra Sathya Hyperbolic Feature-based Sarcasm Detection in Telugu Conversation Sentences
description	Recognition of sarcastic statements has been a challenge in the process of sentiment analysis. A sarcastic sentence contains only positive words conveying a negative sentiment. Therefore, it is tough for any automated machine to identify the exact sentiment of the text in the presence of sarcasm. The existing systems for sarcastic sentiment detection are limited to the text scripted in English. Nowadays, researchers have shown greater interest in low resourced languages such as Hindi, Telugu, Tamil, Arabic, Chinese, Dutch, Indonesian, etc. To analyse these low resource languages, the biggest challenge is the lack of available resources, especially in the context of Indian languages. Indian languages are very rich in morphology which pose a greater challenge for the automated machines. Telugu is one of the most popular languages after Hindi among Indian languages. In this article, we have collected and annotated a corpus of Telugu conversation sentences in the form of a question followed by a reply for sarcasm detection. Further, a set of algorithms are proposed for the analysis of sarcasm in the corpus of Telugu conversation sentences. The proposed algorithms are based on hyperbolic features namely, Interjection, Intensifier, Question mark and Exclamation symbol. The achieved accuracy is 94%.
format	article
author	Bharti Santosh Kumar Naidu Reddy Babu Korra Sathya
author_facet	Bharti Santosh Kumar Naidu Reddy Babu Korra Sathya
author_sort	Bharti Santosh Kumar
title	Hyperbolic Feature-based Sarcasm Detection in Telugu Conversation Sentences
title_short	Hyperbolic Feature-based Sarcasm Detection in Telugu Conversation Sentences
title_full	Hyperbolic Feature-based Sarcasm Detection in Telugu Conversation Sentences
title_fullStr	Hyperbolic Feature-based Sarcasm Detection in Telugu Conversation Sentences
title_full_unstemmed	Hyperbolic Feature-based Sarcasm Detection in Telugu Conversation Sentences
title_sort	hyperbolic feature-based sarcasm detection in telugu conversation sentences
publisher	De Gruyter
publishDate	2020
url	https://doaj.org/article/1cb34d5fb9404eaeb2b55ef54bef6a4f
work_keys_str_mv	AT bhartisantoshkumar hyperbolicfeaturebasedsarcasmdetectioninteluguconversationsentences AT naidureddy hyperbolicfeaturebasedsarcasmdetectioninteluguconversationsentences AT babukorrasathya hyperbolicfeaturebasedsarcasmdetectioninteluguconversationsentences
_version_	1718371661444546560

Hyperbolic Feature-based Sarcasm Detection in Telugu Conversation Sentences

Ejemplares similares