Računalniška analiza slovenskih zgodovinskih časopisov (1771–1914): jezikovni, tematski in državotvorni uvidi
Computational Analysis of Slovenian Historical Newspapers (1771–1914): Linguistic, Thematic, and Nation-Building Insights

Summary/Abstract: This paper presents a computational linguistic analysis of sPeriodika, a historical corpus of Slovenian periodicals published between 1771 and 1914. Using keyword analysis and diachronic analysis, we explore the linguistic, thematic, and historical dimensions of ten prominent newspapers in the corpus. Our findings reveal the centrality of these newspapers in shaping Slovenian nation-building during the post-1848 period, while also highlighting the diverse thematic orientations of individual periodicals, including agriculture, pedagogy, literature, and advertising. Moreover, the study examines the challenges posed by low-quality Optical Character Recognition (OCR) in historical text digitisation and its implications for linguistic and content analysis. By combining computational methods with historical inquiry, this research provides insights into the evolution of the Slovenian language, the media’s role in nation- -building, and the potential for improving OCR-based textual resources.

• Details
• Contents