The Behavioral Modeling Approach for Sarcasm Detection on E-Commerce & OSN
Geeta Bhagwan Mehetre1, M. B. Kalkumbe2
1Geeta Bhagwan Mehetre, Department of Computer Science, MSSCET, Jalna, (Maharashtra), India.
2Prof. M. B. Kalkumbe, Department of Computer Science, MSSCET, Jalna, (Maharashtra), India.
Manuscript received on 10 June 2017 | Revised Manuscript received on 20 June 2017 | Manuscript Published on 30 June 2017 | PP: 8-12 | Volume-6 Issue-10, June 2017 | Retrieval Number: J24310661017/17©BEIESP
Open Access | Editorial and Publishing Policies | Cite | Mendeley | Indexing and Abstracting
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC-BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: Sarcasm transforms the polarity of an apparently positive or negative affirmation into its opposite. We propose a method to construct a sarcastic Twitter message corpus in which the determination of the sarcasm of each message is made by the system. We use this reliable corpus to compare sarcastic statements in Twitter with statements that express positive or negative attitudes without sarcasm. We study the impact of lexical and pragmatic factors on the effectiveness of automatic learning to identify sarcastic utterances and we compare the performance of automatic learning techniques and human judges in this task. Perhaps it is not surprising that neither human judges nor mechanical learning techniques work very well.
Keywords: Hashtags, Linguistics, Opinion Mining, Sarcasm Detection, Tweets, Open NLP.
Scope of the Article: e-Commerce