Conference paper Open Access

Word Clustering for Historical Newspapers Analysis

Lidia Pivovarova; Jani Marjanen; Elaine Zosa

This paper is a part of a collaboration between computer scientists and historians aimed at development of novel methods for historical newspapers analysis. We present a case study of ideological terms ending with -ism suffix in nineteenthcentury
Finnish newspapers. We propose a two-step procedure to trace differences in word usages over time: training of diachronic embeddings on several time slices and when clustering embeddings of selected words together with their neighbours
to obtain historical context. The obtained clusters turn out to be useful for historical studies. The paper also discusses
specific difficulties related to development of historian-oriented tools.

Files (908.2 kB)
Name Size
Word_Clustering_for_Historical_Newspapers_Analysis.pdf
md5:f5a5f2d37c946511e2ba35e9966adaad
908.2 kB Download
53
50
views
downloads
All versions This version
Views 5353
Downloads 5050
Data volume 45.4 MB45.4 MB
Unique views 4545
Unique downloads 4949

Share

Cite as