Dalarna University's logo and link to the university's website

du.sePublications
System disruptions
We are currently experiencing disruptions on the search portals due to high traffic. We are working to resolve the issue, you may temporarily encounter an error message.
Change search
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • chicago-author-date
  • chicago-note-bibliography
  • 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
The Influence of Artificial Intelligence on Education: Sentiment Analysis on YouTube Comments: What is people´s sentiment on ChatGPT for educational purposes?
Dalarna University, School of Information and Engineering, Microdata Analysis.
2024 (English)Independent thesis Advanced level (degree of Master (One Year)), 10 credits / 15 HE creditsStudent thesis
Abstract [en]

The use of artificial intelligence (AI), especially ChatGPT, has increased exponentially in the past years, and it can be seen how AI-based tools are being used in several fields, including education. The literature on AI on education (AIEd), how it has been used, its potential uses, opportunities and challenges were reviewed as well as the literature on sentiment analysis on social media to evaluate the best approach. Since education might face notorious changes due to this technology, assessing how people feel about this potential change in the paradigm is essential. Sentiment analysis on YouTube comments of videos related to ChatGPT, the most popular AI tool for education across learners and educators, was performed. It was found that 62.1% of thes ample had a positive feeling regarding this technology for educational purposes, whereas 19.4% had a negative sentiment and 18.5% were neutral. To contribute to the literature on sentiment analysis of YouTube comments, the two most used and best-performing algorithms were used for this task: Naive Bayes and Support Vector Machine. The results show that the first algorithm had a 61.30% accuracy, whereas SVM had a 71.79%.

Place, publisher, year, edition, pages
2024.
Keywords [en]
Education, YouTube, Artificial Intelligence, Chatbot, ChatGPT, Sentiment Analysis, Lexicon-based, VADER, Machine Learning, Naive Bayes, SVM
National Category
Information Systems
Identifiers
URN: urn:nbn:se:du-48524OAI: oai:DiVA.org:du-48524DiVA, id: diva2:1858017
Subject / course
Microdata Analysis
Available from: 2024-05-15 Created: 2024-05-15

Open Access in DiVA

fulltext(822 kB)300 downloads
File information
File name FULLTEXT01.pdfFile size 822 kBChecksum SHA-512
5cdd7a49c97f0c7c27d62183fd0081ea5f9c780ad98af32f41f5943dcb3969aebe4f81e2101ad4cb4f4c106e6a05c2c9f44677f528157ed20e0afd094855af73
Type fulltextMimetype application/pdf

By organisation
Microdata Analysis
Information Systems

Search outside of DiVA

GoogleGoogle Scholar
Total: 300 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: 594 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • chicago-author-date
  • chicago-note-bibliography
  • 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