kth.sePublications
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
Predicting NFT Marketplace Growth Using Frequency of Tweets Regarding Safety Concerns
KTH, School of Electrical Engineering and Computer Science (EECS), Computer Science.
KTH, School of Electrical Engineering and Computer Science (EECS), Computer Science.
2022 (English)Independent thesis Basic level (degree of Bachelor), 10 credits / 15 HE creditsStudent thesisAlternative title
Förutspå NFT-marknadstillväxt genom frekvensen av Tweets angående säkerhetsproblem (Swedish)
Abstract [en]

NFTs, short for Non-Fungible Tokens, are one of the most talked about and controversial technologies to emerge from the crypto landscape. The digital assets, which derive the capabilities of other cryptocurrencies, have paved a new way for artists, musicians and other creators to monetize their works. At the same time, many have argued that the market for these tokens is plagued by overexitement, baseless investing and fraudulent practices. The topic divides different actors and, since the technology is fairly new, there is a lack of information regarding why the market operates the way that it does and if the technology is providing legitimate worth. Our study sets out to help bridge this information gap by investigating one of the potential driving forces of this market, namely the public perception over its safety. A regression analysis was conducted by monitoring Twitter posts regarding NFT safety and using this information to try and predict price movement. By applying several machine learning methods the study produced models that were able to predict the direction of the market with a 56% accuracy, indicating that a weak relation may exist. More research is needed but public perception should not be disregarded as a driving force of the markets.

Abstract [sv]

NFTs, förkortning av Non-fungible Tokens, är en av de mest omtalade och kontroversiella kryptoteknikerna som växt fram under de senaste åren. De digitala verken, som har egenskaper likt kryptovalutor, har skapat en nytt sätt för konstnärer och musiker att tjäna pengar på sitt arbete. Samtidigt har många hävdat att marknaderna associerade med dessa verk präglas av grundlösa investeringar och bedrägliga metoder. Ämnet splittrar olika aktörer och då teknologin är relativt ny finns det en brist på information angående varför marknaderna fungerar som de gör och huruvida de faktiskt tillför värde. Vår studie ämnar att öka förståelsen för tekniken genom att undersöka en av de potentiella drivkrafterna hos marknaderna: Allmänhetens uppfattning av teknikens säkerhet. En regressionsanalys utfördes genom att observera antalet Twitter-inlägg angående NFT-säkerhet och denna informationen användes sedan för att förutspå prisändringar. Genom att applicera flera maskininlärningsmetoder lyckades studien producera modeler som kunde förutspå riktning av prisutveckling med 56% noggranhet, vilket indikerar att en svag relation kan existera. Mer forskning är nödvändigt men allmänhetens säkerhetsuppfattning borde inte åsidosättas som en betydande drivfaktor till marknaden.

Place, publisher, year, edition, pages
2022. , p. 42
Series
TRITA-EECS-EX ; 2022:442
National Category
Computer and Information Sciences
Identifiers
URN: urn:nbn:se:kth:diva-320199OAI: oai:DiVA.org:kth-320199DiVA, id: diva2:1703919
Subject / course
Computer Science
Educational program
Master of Science in Engineering - Computer Science and Technology
Supervisors
Examiners
Available from: 2022-10-17 Created: 2022-10-15 Last updated: 2022-10-17Bibliographically approved

Open Access in DiVA

fulltext(691 kB)866 downloads
File information
File name FULLTEXT01.pdfFile size 691 kBChecksum SHA-512
ea5679d4124f5161c26560f57b5fa87061f37985a54492dd140c0ee6108868944ec7cda39823ead19e09b30052d4f5ca1c3f473431699ce5fb7fa8791dbdcebf
Type fulltextMimetype application/pdf

By organisation
Computer Science
Computer and Information Sciences

Search outside of DiVA

GoogleGoogle Scholar
Total: 877 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: 1366 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