Sentiment Analysis-Enhancements and Applications
Aayush Gupta1, Anant Gandhi2, Saarthak Agarwal3, Shamin Chokshi4, Saravanakumar Kandasamy5
1Aayush Gupta, School of Computer Science and Engineering, VIT Vellore, India,
2Anant Gandhi, School of Computer Science and Engineering, VIT Vellore, India.
3Saarthak Agarwal, School of Computer Science and Engineering, VIT Vellore, India.
4Shamin Chokshi*, School of Computer Science and Engineering, VIT Vellore, India.
5Saravanakumar K., School of Information Technology and Engineering, VIT Vellore, India.
Manuscript received on September 09, 2021. | Revised Manuscript received on September 16, 2021. | Manuscript published on September 30, 2021. | PP: 56-70 | Volume-10 Issue-4, November 2021. | Retrieval Number: 100.1/ijrte.A1409059120 | DOI: 10.35940/ijrte.A1409.1110421
Open Access | Ethics and Policies | Cite | Mendeley
© The Authors. Published By: 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: The concept of Natural Language Processing that deals with problems of identifying the sentiment from the voice or text of a speaker or writer and then use that analysis further for making predictions, market survey, customer service, product satisfaction, precision targeting etc. is called Sentiment analysis. From one viewpoint, it is an abstract evaluation of something dependent on close to home observational experience. It Is mostly established in target realities and incompletely governed by feelings. Then again, a sentiment can be deciphered as a kind of measurement in the information in regards to a specific subject. It is a lot of markers that mix present a point of view, i.e., perspective for the specific issue. So as to enhance the accuracy of sentiment analysis/classification, it is imperative to appropriately recognize the semantic connections between the various words and phrases that are describing the subject or aspect. This can be done by applying semantic analysis with a syntactic parser and supposition vocabulary. This research will discuss different sets of approaches for application or domain specific problems and then compare them to obtain the best possible approaches to the problem of sentiment analysis.
Keywords: Sentiment Analysis, Lexicon, Support vector machine, Regression