Social Media Mining of the Icelandic Blogosphere

Sindri Freyr Sigursteinsson

AbstractThis thesis presents experiments related to the Icelandic Twitter network. It is based on an analysis made from two perspectives, a general analysis of the overall network, including its users, followed by a more detailed sentiment analysis. The main objective of the general analysis was to identify features of the Icelandic network as a whole and characteristics of its Icelandic users. The growth rate of the Icelandic Twitter network was studied as well as tweeter activity among Icelandic Twitter users. Additionally, the relationship between different variables was viewed, for example between activity level and the numbers of followers, which has been used in prior work for identifying influential tweeters. The purpose of the sentiment analysis was to detect and extract the emotional content of Icelandic tweets, whether they are positive, neutral or negative.
TypeMaster's thesis [Academic thesis]
PublisherTechnical University of Denmark, DTU Informatics, E-mail:
AddressAsmussens Alle, Building 305, DK-2800 Kgs. Lyngby, Denmark
NoteSupervised by Associate Professor Finn Årup Nielsen,, DTU Informatics
Electronic version(s)[pdf]
Publication link
BibTeX data [bibtex]
IMM Group(s)Intelligent Signal Processing

Back  ::  IMM Publications