A Proposed Approach for Sentiment Analysis and Sarcasm Detection on Textual Data
Himani Khullar1, Amritpal Singh2
1Himani Khullar, M.Tech student at the Lovely Professional University, Punjab, India.
2Amritpal Singh, Assistant Professor in Computer Science and Engineering at the Lovely Professional University, Punjab, India.
Manuscript received on 08 April 2019 | Revised Manuscript received on 16 May 2019 | Manuscript published on 30 May 2019 | PP: 33 | Volume-8 Issue-1, May 2019 | Retrieval Number: A1386058119/19©BEIESP
Open Access | Ethics and 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 in straightforward dialect infers the utilization of incongruity to taunt or pass on hatred. It is portrayed as the unexpected and humorous mind. It changes the extremity of a clearly positive or negative articulation to inverse of it. Sarcasm is a rich method for the passing on message in understood way which makes difficult to recognize it. The objective of this paper is to detect sarcasm with high accuracy. In this paper bagged gradient boosting is proposed with particle swarm optimization as feature selection. It is compared with other classifiers such as random forest, gradient boosting, bagged gradient boosting. The emoji and acronym dictionary mapping is done, part of speech labelling is introduced. Hashtags and stop words are recognized and removed. Particle swarm optimization is used to remove noisy data.
Keywords: Bagging, Gradient Boosting, Particle Swarm Optimization, Sarcasm.
Scope of the Article: Discrete Optimization