ePrints.FRI - University of Ljubljana, Faculty of Computer and Information Science

Online news analysis with the techniques of word occurrence visualization

Paula Vouk (2016) Online news analysis with the techniques of word occurrence visualization. EngD thesis.

Download (10Mb)


    There is an enormous amount of publications in Slovenian language waiting to be analysed. With simple algorithms we can reveal interesting facts about our society and it’s culture, science, politics as well as many other aspects. In this thesis we focused on online articles that were published by newspaper Dnevnik between 1998 and 2006. By evaluating word-usage frequency graphs we wanted to investigate the influence of some important phenomena on Slovenian press. We found that higher usage frequencies of specific words chronologically match with associated phenomena. We also studied how the names of well-known people co-occur with words that pertain to a specific topic. With several examples we examined how appropriate Sieve and Circos diagrams are to visualising these types of results. Word connections presented with selected visualization tools are meaningful and expected but on the other hand the diagrams bring forward some interesting and unexpected relations.

    Item Type: Thesis (EngD thesis)
    Keywords: Circos, Sieve diagram, n-gram, word co-occurrences, word frequency
    Number of Pages: 41
    Language of Content: Slovenian
    Mentor / Comentors:
    Name and SurnameIDFunction
    prof. dr. Blaž Zupan106Mentor
    Link to COBISS: http://www.cobiss.si/scripts/cobiss?command=search&base=51012&select=(ID=1537107907)
    Institution: University of Ljubljana
    Department: Faculty of Computer and Information Science
    Item ID: 3426
    Date Deposited: 18 Aug 2016 14:54
    Last Modified: 15 Sep 2016 10:46
    URI: http://eprints.fri.uni-lj.si/id/eprint/3426

    Actions (login required)

    View Item