Sökning: "Text och data mining"

Visar resultat 21 - 25 av 45 uppsatser innehållade orden Text och data mining.

  1. 21. Terrorist eller ensam galning? : En analys av Aftonbladets och Svenska Dagbladets nyhetsrapportering om Anders Behring Breivik och Rakhmat Akilov

    Kandidat-uppsats, Umeå universitet/Institutionen för kultur- och medievetenskaper

    Författare :Wilhelm Sandelin Anton; [2020]
    Nyckelord :Digital text analysis; data mining; frame analysis; news media; Anders Behring Breivik; Rakhmat Akilov; terrorism; framing; orientalism; ethnicity.; Digital textanalys; datautvinning; framinganalys; nyhetsmedier; Anders Behring Breivik; Rakhmat Akilov; terrorism; gestaltningsteori; orientalism; etnicitet.;

    Sammanfattning : This study aims to survey and compare Swedish newspaper coverage relating to convicted terrorists Anders Behring Breivik and Rakhmat Akilov. The pivotal question of the study is whether this coverage differs depending on factors such as each perpetrator’s ethnicity and political beliefs. LÄS MER

  3. 22. Upphovsrättsligt intrång vid automatiserad datorstödd analys av information - Om användningen av data vid text- och datautvinning innebär ett upphovsrättsligt intrång

    Kandidat-uppsats, Lunds universitet/Institutionen för handelsrätt

    Författare :Linn Månsson; [2020]
    Nyckelord :Immaterialrätt; upphovsrätt; ensamrätt; exemplarframställning; Copyright; Text- och datautvinning; Text och data mining; DSM-direktivet; KDD; tillfällig exemplarframställning; mode algoritmer; myndighetsbeslut; Government decisions; fashion algorithms; Infosoc-direktivet; Intellectual property; IP; Artificiell intelligens; AI; intrång; EU-rätt; EU-law; DSM-directive; Law and Political Science;

    Sammanfattning : The essay studies the problem between text and data mining (TDM) and copyrighted works. Through technological development, TDM is used, among other things, to make automated decisions in the authorities and in the fashion industry as tools that find similarities between different garments. LÄS MER

  4. 23. Recognising Moral Foundations in Online Extremist Discourse : A Cross-Domain Classification Study

    Master-uppsats, Uppsala universitet/Institutionen för lingvistik och filologi

    Författare :Anne Fleur van Luenen; [2020]
    Nyckelord :text mining; moral foundations; twitter; BERT; Word2Vec; latent semantics; extremism; natural language processing; ;

    Sammanfattning : So far, studies seeking to recognise moral foundations in texts have been relatively successful (Araque et al., 2019; Lin et al., 2018; Mooijman et al., 2017; Rezapouret al. LÄS MER

  5. 24. Customer Behaviour Analysis of E-commerce : What information can we get from customers' reviews through big data analysis

    Magister-uppsats, KTH/Entreprenörskap och Innovation

    Författare :Kelvin Soen; Bo Yin; [2019]
    Nyckelord :Customer behaviour analysis; Online reviews; text analysis; cultures; genders; e-commerce;

    Sammanfattning : Online transactions have been growing exponentially in the last decade, contributing to up to 11% of total retail sales. One of the parameters of success in online transactions are online reviews where customers have the chance to assign level of satisfaction regarding their purchase. LÄS MER

  7. 25. Text feature mining using pre-trained word embeddings

    Master-uppsats, KTH/Matematisk statistik

    Författare :Henrik Sjökvist; [2018]
    Nyckelord :Word embeddings; Feature engineering; Unsupervised learning; Deep learning; fast Text; Operational risk; Ordvektorer; Attributgenerering; Oövervakat lärande; Djupinlärning; fastText; Operativ risk;

    Sammanfattning : This thesis explores a machine learning task where the data contains not only numerical features but also free-text features. In order to employ a supervised classifier and make predictions, the free-text features must be converted into numerical features.  In this thesis, an algorithm is developed to perform that conversion. LÄS MER