Naslov
The application of textual and visual data analysis tools on the text corpus of the magazine Der Sturm

Autori
Kolešnik, Ljiljana ; Šilić Artur

Vrsta, podvrsta i kategorija rada
Sažeci sa skupova, ostalo, znanstveni

Skup
3rd Conference on Empirical Methods in Art History and Visual Studies

Mjesto i datum
Beč, Austrija, 17.11.2017. - 18.11.2017

Vrsta sudjelovanja
Predavanje

Vrsta recenzije
Međunarodna recenzija

Ključne riječi
Digital art history, historical avant-garde, text analysis, topic modeling

Sažetak
In this presentation we are providing the example of a numerous text analysis methods applied on the entire textual corpus of Der Sturm magazine, which marks a starting point in explorations of the avant-garde movements in the first half of the 20th century, conducted at the project ARTNET. Approached by using both explorative analysis and hypothesis testing, textual analysis of Der Sturm is an example of art historical research that utilizes IT tools and methods of computational data processing. It also provides the grounds for comparison between computational and empirical methodology research results and the research results obtained by more traditional disciplinary methods. Quantitative analysis, applied in this case study, are borrowed from the field of natural language processing, including topic modelling, entity extraction and linking, as well as network visualization. Taken together, they allow for the innovative data exploration. The application of computational methods is justified by the problems of grasping large textual corpora that would be otherwise left unread, and avoiding possibility of human bias in reading done by individual researcher.

Izvorni jezik
Engleski

Znanstvena područja
Informacijske i komunikacijske znanosti, Povijest umjetnosti, Interdisciplinarne humanističke znanosti

POVEZANOST RADA