Blar i ODA Open Digital Archive på forfatter "Bai, Aleksander"

Viser treff 1-6 av 6

    • Automatic security classification by machine learning for cross-domain information exchange 

      Hammer, Hugo Lewi; Kongsgård, Kyrre Wahl; Yazidi, Anis; Bai, Aleksander; Nordbotten, Nils Agne; Engelstad, Paal E. (MILCOM IEEE Military Communications Conference;, Journal article; Peer reviewed, 2015)
      Cross-domain information exchange is necessary to obtain information superiority in the military domain, and should be based on assigning appropriate security labels to the information objects. Most of the data found ...

    • Building domain specific sentiment lexicons combining information from many sentiment lexicons and a domain specific corpus 

      Hammer, Hugo Lewi; Yazidi, Anis; Bai, Aleksander; Engelstad, Paal E. (Computer Science and Its Applications: 5th IFIP TC 5 International Conference, CIIA 2015, Saida, Algeria, May 20-21, 2015, Proceedings;, Peer reviewed; Chapter, 2015)
      Most approaches to sentiment analysis requires a sentiment lexicon in order to automatically predict sentiment or opinion in a text. The lexicon is generated by selecting words and assigning scores to the words, and the ...

    • Building sentiment Lexicons applying graph theory on information from three Norwegian thesauruses 

      Hammer, Hugo; Bai, Aleksander; Yazidi, Anis; Engelstad, Paal (Norsk Informatikkonferanse;2014, Journal article; Peer reviewed, 2014)
      Sentiment lexicons are the most used tool to automatically predict sentiment in text. To the best of our knowledge, there exist no openly available sentiment lexicons for the Norwegian language. Thus in this paper ...

    • Categorization and Comparison of Accessibility Testing Methods for Software Development 

      Bai, Aleksander; Fuglerud, Kristin Skeide; Skjerve, Rannveig Alette; Halbach, Till (Studies in Health Technology and Informatics;Volume 256: Transforming our World Through Design, Diversity and Education, Journal article; Peer reviewed, 2018)
      There are many methods for testing accessibility and universal design, ranging from checklists and guidelines to automated testing and finally to human testing with participants from different user groups. It is, however, ...

    • Improving Classification of Tweets Using Linguistic Information from a Large External Corpus 

      Hammer, Hugo Lewi; Yazidi, Anis; Bai, Aleksander; Engelstad, Paal E. (Journal article; Peer reviewed, 2016)
      The bag of words representation of documents is often unsat- isfactory as it ignores relationships between important terms that do not co-occur literally. Improvements might be achieved by expanding the vocabulary with ...

    • Improving classification of tweets using word-word co-occurrence information from a large external corpus 

      Hammer, Hugo Lewi; Yazidi, Anis; Bai, Aleksander; Engelstad, Paal E. (Chapter; Peer reviewed; Chapter, 2016)
      Classifying tweets is an intrinsically hard task as tweets are short messages which makes traditional bags of words based approach ine cient. In fact, bags of words approaches ig- nores relationships between important ...