Digitala Vetenskapliga Arkivet

Change search
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf
Exploring Sentiment Analysis on TikTok Social Media Platform: Comparison of Four Sentiment Polarity Prediction Methods on TikTok Content
Stockholm University, Faculty of Social Sciences, Department of Computer and Systems Sciences.
2024 (English)Independent thesis Advanced level (degree of Master (Two Years)), 20 credits / 30 HE creditsStudent thesis
Abstract [en]

This thesis explores the effectiveness of various sentiment analysis techniques on the TikTok social media platform, particularly in the context of fashion-related content. Given the popularity of TikTok among Generation Z, understanding sentiment on this platform is crucial for marketers and businesses targeting this demographic. The study employs four distinct sentiment analysis methods: Support Vector Machines (SVM), VADER (Valence Aware Dictionary for sEn- timent Reasoning), Convolutional Neural Networks (CNN), and Bi-directional Long Short-Term Memory networks (biLSTMs), to analyze user-generated con- tent on TikTok. Data were collected through scraping TikTok videos related to fashion brands, followed by manual labeling to prepare for sentiment analysis. The analysis revealed varied accuracy performances across the methods, with each showing strengths and weaknesses depending on the specific characteris- tics of the data. The results indicate that no single method outperforms others consistently across all types of data, highlighting the complexity of applying SA to the informal and evolving content on TikTok. This research contributes to the understanding of sentiment analysis applications in new social media con- texts and suggests directions for future work, including expanding the amount of data analyzed, the range of content and platform features included, and the adaptability of sentiment analysis tools to changes in online language use. The insights gained are particularly relevant for developing more nuanced sentiment analysis strategies aimed at researching the digitally native Generation Z on emerging social media platforms.

Place, publisher, year, edition, pages
2024.
Keywords [en]
Sentiment Analysis, TikTok, Generation Z, Natural Language Pro- cessing, Support Vector Machines, VADER, Convolutional Neural Networks, Bi-directional Long Short-Term Memory, Social Media
National Category
Computer Sciences
Identifiers
URN: urn:nbn:se:su:diva-242717OAI: oai:DiVA.org:su-242717DiVA, id: diva2:1955649
Available from: 2025-04-30 Created: 2025-04-30

Open Access in DiVA

fulltext(1187 kB)92 downloads
File information
File name FULLTEXT01.pdfFile size 1187 kBChecksum SHA-512
3d3df77fa9ea477c82b6b9f6d0408b54fee482e05f691259635b626d545f876c5dc79ffaaa3a3247d4b9f3876d172161a34025b55271a377b9251ec2a61f8078
Type fulltextMimetype application/pdf

Search in DiVA

By author/editor
Aispurs, Valters
By organisation
Department of Computer and Systems Sciences
Computer Sciences

Search outside of DiVA

GoogleGoogle Scholar
Total: 92 downloads
The number of downloads is the sum of all downloads of full texts. It may include eg previous versions that are now no longer available

urn-nbn

Altmetric score

urn-nbn
Total: 20 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf