TikNep: content analysis of Nepali TikTok users using natural language processing

Thumbnail
View/Open
Date
2024-05
Publisher
Brac University
Author
Dhakal, Aakar
Lamichhane, Ashok
Jha, Aatish Kumar
Singh, Mukund Prasad
Metadata
Show full item record
URI
http://hdl.handle.net/10361/24343
Abstract
Nepal, with an approximate population of 29 million, has over 2.2 million active TikTok users, TikTok has gained attention as a platform for self-expression and social connection among diverse age groups. Users in Nepal are using TikTok to share their opinions on matters related to politics, social issues, pop culture, lifestyle and beauty, sports, etc. While the content on platforms like Facebook and Twitter has been studied and evaluated thoroughly, the impact and influence of TikTok’s content on Nepali society have not been assessed yet. In this study, we propose to analyze content on Nepal’s TikTok using Natural Language Processing (NLP) tools to draw conclusions regarding where the conversation is being shifted towards. To meet this objective, we will focus on the comments posted by users on popular TikTok videos in Nepal and conduct Sentiment Analysis, Hate-Offense Detection, Political Stance Detection, and Multi-label Topic Classification.
Keywords
Natural language processing; Content analysis; TikTok; Social influence; Sentiment analysis; Hate speech; Multi-label topic classification; Machine learning
 
LC Subject Headings
Natural language processing (Computer science).; Content analysis (Communication)--Data processing.
 
Description
This thesis is submitted in partial fulfillment of the requirements for the degree of Bachelor of Science in Computer Science, 2024.
 
Cataloged from PDF version of thesis.
 
Includes bibliographical references (pages 49-52).
Department
Department of Computer Science and Engineering, Brac University
Type
Thesis
Collections