A Sentimental Analysis for YouTube Data using Supervised Learning Approach
Ashutosh Bansal1, Chunni Lal Gupta2,  A Muralidhar3

1Ashutosh Bansal, MCA, Vellore Institute of Technology, Chennai (Tamil Nadu), India.
2Chunni Lal Gupta, MCA, Vellore Institute of Technology, Chennai (Tamil Nadu), India.
3Muralidhar A, School of Computing Science and Engineering, Vellore Institute of Technology, Chennai (Tamil Nadu), India.

Manuscript received on 18 June 2019 | Revised Manuscript received on 25 June 2019 | Manuscript published on 30 June 2019 | PP: 2314-2318 | Volume-8 Issue-5, June 2019 | Retrieval Number: E7756068519/19©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: As there are lots of social media applications which are getting closer to the users in very less time. So as the users are so much excited to interact with this application. There are lots of social media application which is booming are Facebook, Twitter, YouTube etc. So in this application users can not only see the content posted even they can also post their feelings what they are feeling after seeing the content. In YouTube there are lots of channels which are increasing day by day and the channel manager post the content according to their channel, so they need to analyze the customer’s feedback or reviews which is posted on the contents. If these comments and feedback get analyzed the channel manager will get some decisions according to customers whether the customers are liking the content or not. If there is any requirement of changes in the content by looking at the reviews they can easily change. So for doing the sentiment analysis of customer reviews, different classification algorithm has been taken such as Decision Tree, K Nearest Neighbors and Support vector machine. Then the algorithm which is giving the highest accuracy is taken for building the model which will work as sentiment analysis model for other channel managers.
Keywords: Social Media, Classification, Reviews, Opinion Mining, Sentiment Analysis, Feedback

Scope of the Article: Social Networks