A NLP framework based on meaningful latent-topic detection and sentiment analysis via fuzzy lattice reasoning on youtube
- PDF / 3,809,244 Bytes
- 27 Pages / 439.642 x 666.49 pts Page_size
- 10 Downloads / 201 Views
A NLP framework based on meaningful latent-topic detection and sentiment analysis via fuzzy lattice reasoning on youtube comments Hamed Jelodar1 · Yongli Wang1 · Mahdi Rabbani1 · Sajjad Bagheri Baba Ahmadi1 · Lynda Boukela1 · Ruxin Zhao1 · Raja Sohail Ahmed Larik1 Received: 23 December 2019 / Revised: 9 July 2020 / Accepted: 28 August 2020 / © Springer Science+Business Media, LLC, part of Springer Nature 2020
Abstract Social media platforms such as Twitter, Facebook, and YouTube have unique architecture, norms, and culture. These platforms are valuable sources of people’s opinions which should be examined for knowledge discovery and user behavior analysis. This paper proposed a novel content analysis to examine user reviews or movie comments on YouTube. In fact, the proposed hybrid framework is based on semantic and sentiment aspects using fuzzy lattice reasoning to meaningful latent-topic detection and utilizing sentiment analysis of user comments of the Oscar-nominated movie trailers on YouTube. Based on the word vector feature, classification algorithms are employed to detect the comments’ sentiment level. The results of this study suggest that the hybrid framework could be effective to extract features associated and latent topics with sentiment valence on user comments. In addition, NLP methods can have an impressive role for exploring the relationship between user opinion and Oscar movies comments on YouTube. Keywords Natural language processing · Topic model · LDA · Social media · YouTube
1 Introduction Social Media provides a solid platform for finding, sharing and broadcasting videos, images, etc. An important factor in the development of these technologies is the capability to easily create user-generated data. Twitter and YouTube are only a few examples of these
Hamed Jelodar
[email protected] Yongli Wang [email protected] 1
School of Computer Science and Technology, Nanjing University of Science and Technology, Nanjing 210094, China
Multimedia Tools and Applications
media that are strongly changing the Internet perspective today. These platforms motivate the users to publish and annotate content and more importantly, sharing information with their social media account. However, social media serves as a significant platform for both non-professional content creators and multimedia organizations. For instance, in terms of releasing movies, YouTube role is remarkable in introducing and popularizing new movies. Besides, YouTube users can review, comment and share their personal opinions about a movie online [32, 52]. Topic modeling based on LDA is an unsupervised machine learning technique that aims to arrange large corpora of text into candidate topics [52]. These topics explain thematic relations and patterns among text-contents. In this study, also, we designed a semantic model based on Latent Dirichlet Allocation (LDA), which is a probabilistic unsupervised classification method in topic modeling. In fact, for the current research, LDA is utilized to extract semantic topics from YouTu
Data Loading...
