Topic Modelling and Sentiment Analysis on YouTube Sustainable Fashion Comments

機構典藏 > College of Business and Management > Department of Management Sciences > Journal Article > Item 987654321/125042

Please use this identifier to cite or link to this item: https://tkuir.lib.tku.edu.tw/dspace/handle/987654321/125042

Title:	Topic Modelling and Sentiment Analysis on YouTube Sustainable Fashion Comments
Authors:	Lee, Hsu-Hua;Nguyen, MTN
Keywords:	Topic modelling;sentiment analysis;latent dirichlet allocation;natural language processing;sustainable fashion;YouTube comments
Date:	2023-2-27
Issue Date:	2024-02-20 12:06:17 (UTC+8)
Publisher:	Tech Science Press
Abstract:	YouTube videos on sustainable fashion enable the public to gain basic knowledge about this concept. In this paper, we analyse user comments on YouTube videos that contain sustainable fashion content. The paper’s main objective is to help content creators and business managers effectively understand the perspectives of viewers, thus improving video quality and developing business. We analysed a dataset of 17,357 comments collected from 15 sustainable fashion YouTube videos. First, we use Latent Dirichlet Allocation (LDA), a topic modelling technique, to discover the abstract topics. In addition, we use two approaches to rank these topics: ranking based on proportion and Rank-1 method. Second, we apply sentiment analysis to identify the user’s emotional tone in the comments. As a result, 14 topics were identified. The most common positive and negative scores are 1 and −1, respectively. In total, there are 28.42% positive comments, 22.35% negative comments and 49.23% neutral comments.
Relation:	Journal of New Media 5(1), p.65-80
DOI:	10.32604/jnm.2023.045792
Appears in Collections:	[Department of Management Sciences] Journal Article

Files in This Item:

File	Description	Size	Format
index.html		0Kb	HTML	49	View/Open