TubeRate: YouTube Rating System
Published: 2023
Author(s) Name: Prahlad Gurjar, Naitik Yadav, Ahimsa Jain and Nisha Rathi |
Author(s) Affiliation: Acropolis Institute of Technology and Research, Indore, Madhya Pradesh, India.
Locked
Subscribed
Available for All
Abstract
YouTube is one of the comprehensive video information sources on the web where video is uploaded continuously in real time. It is one of the most popular sites, where users interact with sharing, commenting and rating (like/views) videos. Generally the quality, relevancy and popularity of the video is maintained based on this rating. Sometimes irrelevant and low quality videos ranked higher in the search result due to the number of views or likes, which seems untenable. To minimize this issue, we present a Natural Language Processing (NLP) based sentiment analysis approach on user comments. A sentiment classifier model is built which identifies tweets positive, negative or neutral. In this technique, the collected corpus was divided into 3 sets namely positive emotions- happiness, amusement or joy; Negative emotions- sadness, anger or disappointment and Neutral-text doesn’t contain emotions. YouTube data is also automatically classified into positive, negative and neutral according to query terms used in user review comments. In the paper the author uses Parts Of Speech (POS) polarity technique and tree kernel technique. Research work uses two types of resources such as a hand dictionary of emotions and a dictionary collected from the web. Different types of classification and feature extraction algorithms are used [1]. This analysis helps to find out the most relevant and popular video of YouTube according to the sentimental analysis of the comments posted by users on YouTube videos. Using sentiment analysis, these users’ opinions and emotions can be extracted and quantified. TubeRate examines the current papers on sentiment analysis on YouTube comments as well as present the work done on proposed idea of user comment based YouTube video rating that is analyzed through polarity and segregation as positive, negative or neutral. This can be useful in predicting the like proportion of a YouTube video. These ratings will be on a scale from 1 to 5, where 1 means extremely dissatisfied and 5 means extremely pleased with the content of the video.
Keywords: Machine learning, Sentimental analysis, Support vector machine, YouTube.
View PDF