du.sePublikationer
Ändra sökning
RefereraExporteraLänk till posten
Permanent länk

Direktlänk
Referera
Referensformat
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • chicago-author-date
  • chicago-note-bibliography
  • Annat format
Fler format
Språk
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Annat språk
Fler språk
Utmatningsformat
  • html
  • text
  • asciidoc
  • rtf
Improving Hashtag Recommendation for Instagram Images by Considering Hashtag Relativity and Sentiment.
Högskolan Dalarna, Akademin Industri och samhälle, Mikrodataanalys.
Högskolan Dalarna, Akademin Industri och samhälle, Mikrodataanalys.
2018 (Engelska)Självständigt arbete på avancerad nivå (masterexamen), 10 poäng / 15 hpStudentuppsats (Examensarbete)
Abstract [en]

Extracting knowledge from user-generated content (UGC) in social media platforms is a very hot research topic in the area of machine learning, nonetheless, the main challenge resides in the fact that UGC carries inference, abstraction and subjectivity alongside objectivity. With the aim of recognising the importance of subjectivity as an influential aspect for providing humanoid results from a machine learning algorithm, this study proposes a novel approach to improve Instagram hashtag recommendation by considering sentiment that can be expressed for images. Two main points are studied in this thesis; evaluating the relativity of Instagram image to hashtag for both objective and subjective features of an image and the effect of sentiment on said relativity. This work examines three machine learning methods for hashtag recommendation: AWS service, developed algorithms with and without sentiment considerations. The models are tested on a collected dataset of de-identified Instagram posts in location London gathered from public profiles. The results show that considering sentiment significantly improves Instagram hashtag recommendation.

Ort, förlag, år, upplaga, sidor
2018.
Nyckelord [en]
Machine learning, social media, Instagram, hashtag, prediction, sentiment, relativity, feature extraction, image processing, recommendation system.
Nationell ämneskategori
Annan samhällsvetenskap
Identifikatorer
URN: urn:nbn:se:du-29455OAI: oai:DiVA.org:du-29455DiVA, id: diva2:1287026
Tillgänglig från: 2019-02-08 Skapad: 2019-02-08

Open Access i DiVA

fulltext(1029 kB)136 nedladdningar
Filinformation
Filnamn FULLTEXT01.pdfFilstorlek 1029 kBChecksumma SHA-512
4e5909618f35fd5daf234a61e6ae45e28aa4d91af8bf813bfdb38da1769441f0910ccc4585f347050e906568e4506fd4e57c93a0050f491350e49ddb37043878
Typ fulltextMimetyp application/pdf

Av organisationen
Mikrodataanalys
Annan samhällsvetenskap

Sök vidare utanför DiVA

GoogleGoogle Scholar
Totalt: 136 nedladdningar
Antalet nedladdningar är summan av nedladdningar för alla fulltexter. Det kan inkludera t.ex tidigare versioner som nu inte längre är tillgängliga.

urn-nbn

Altmetricpoäng

urn-nbn
Totalt: 370 träffar
RefereraExporteraLänk till posten
Permanent länk

Direktlänk
Referera
Referensformat
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • chicago-author-date
  • chicago-note-bibliography
  • Annat format
Fler format
Språk
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Annat språk
Fler språk
Utmatningsformat
  • html
  • text
  • asciidoc
  • rtf