DoSVis: Document stance visualization

Kostiantyn Kucher, Carita Paradis, Andreas Kerren

Forskningsoutput: Kapitel i bok/rapport/Conference proceedingKonferenspaper i proceedingPeer review

1 Citering (SciVal)

Sammanfattning

Text visualization techniques often make use of automatic text classification methods. One of such methods is stance analysis, which is concerned with detecting various aspects of the writer's attitude towards utterances expressed in the text. Existing text visualization approaches for stance classification results are usually adapted to textual data consisting of individual utterances or short messages, and they are often designed for social media or debate monitoring tasks. In this paper, we propose a visualization approach called DoSVis (Document Stance Visualization) that focuses instead on individual text documents of a larger length. DoSVis provides an overview of multiple stance categories detected by our classifier at the utterance level as well as a detailed text view annotated with classification results, thus supporting both distant and close reading tasks. We describe our approach by discussing several application scenarios involving business reports and works of literature.

Originalspråkengelska
Titel på värdpublikationProceedings of the 13th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications
FörlagSciTePress
Sidor168-175
Antal sidor8
Volym3
ISBN (elektroniskt)9789897582899
StatusPublished - 2018 jan. 1
Evenemang13th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications, VISIGRAPP 2018 - Funchal, Madeira, Portugal
Varaktighet: 2018 jan. 272018 jan. 29

Konferens

Konferens13th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications, VISIGRAPP 2018
Land/TerritoriumPortugal
OrtFunchal, Madeira
Period2018/01/272018/01/29

Ämnesklassifikation (UKÄ)

  • Språkteknologi (språkvetenskaplig databehandling)

Fingeravtryck

Utforska forskningsämnen för ”DoSVis: Document stance visualization”. Tillsammans bildar de ett unikt fingeravtryck.

Citera det här