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
Troll detection with sentiment analysis and nearest neighbour search
KTH, School of Computer Science and Communication (CSC).
KTH, School of Computer Science and Communication (CSC).
2017 (English)Independent thesis Basic level (degree of Bachelor), 10 credits / 15 HE creditsStudent thesisAlternative title
Identifiering av troll med sentimentanalys och nearest neighbour search (Swedish)
Abstract [en]

Internet trolls are gaining more influence in society due to the rapidgrowth of social media. A troll farm is a group of Internet trolls that get paid to spread certain opinions or information online. Identifying a troll farm can be difficult, since the trolls try to stay hidden. This study examines if it is possible to identify troll farms on Twitter by conducting a sentiment analysis on user tweets and modeling it as a nearest neighbor problem. The experiment was done with 4 simulated trolls and 150 normal twitter users. The users were modelled into datapoints based on the sentiment, frequency and time of their tweets. The result of the nearest neighbor search could not show a clear link between the trolls as their behaviour was not similar enough.

Abstract [sv]

Internet-troll har de senaste åren fått ökat inflytande i och med ökat användande av sociala medier. En trollfarm är en grupp troll som får betalt för att sprida specifika åsikter eller information online. Det kan vara svårt att urskilja användarna i en trollfarm från vanliga användare då de ständigt försöker undvika upptäckt. I denna studie undersöks hurvida man kan finna en trollfarm  på Twitter genom att utföra en sentimentanalys på användares tweets och sedan modelera det som ett nearest neighbor problem. Experimentet utfördes med 4 simulerade troll och 150 vanliga twitteranvändare. Användarna modelerades efter tid, frekvens och sentiment på deras tweets. Resultatet från modeleringen kunde inte påvisa ett samband mellan trollen då deras beteendemönster skiljde sig åt allt för mycket.

Place, publisher, year, edition, pages
2017.
National Category
Computer Sciences
Identifiers
URN: urn:nbn:se:kth:diva-209474OAI: oai:DiVA.org:kth-209474DiVA, id: diva2:1112405
Supervisors
Examiners
Available from: 2017-06-21 Created: 2017-06-20 Last updated: 2018-01-13Bibliographically approved

Open Access in DiVA

fulltext(617 kB)138 downloads
File information
File name FULLTEXT01.pdfFile size 617 kBChecksum SHA-512
09ed44d06029195f928ed8b8148cf64d68cb62d5a210af7b671330c87f475c923eaba99064028c689dc60f59e158f61982fa715a264aba1357466a8dd1da926b
Type fulltextMimetype application/pdf

By organisation
School of Computer Science and Communication (CSC)
Computer Sciences

Search outside of DiVA

GoogleGoogle Scholar
Total: 138 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: 276 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