id	author	title	date	pages	extension	mime	words	sentences	flesch	summary	cache	txt
work_qblac7ctoveq5ldft75qxl6k3a	Lidia Pivovarova	Word Clustering for Historical Newspapers Analysis	2019	8	.pdf	application/pdf	4464	331	52	Word Clustering for Historical Newspapers Analysis We propose a two-step procedure to trace differences in word usages over time: training This paper focuses on a case study of ideological terms ending with -ism suffix—such as liberalism, socialism, or conservatism—in nineteenth century Finnish newspapers and how usage of ideological isms is different from other words with Figure 1: A selection of the most frequent words ending with suffix -ism/ismi. We cluster word embeddings into semantically only clusters that contain at least one ism word are Finnish data that contain words related to rheumaTable 3: Clusters containing Finnish words related to rheumatism. Swedish data that contain the word spiritism. Table 4: Clusters containing Swedish word spiritism. Table 5: Swedish clusters containing word separatism Table 6: Finnish clusters containing word separatismi The 1880-1899 cluster contains completely different set of words, including reference to specific political entities, such as clustering embeddings of selected words together	./cache/work_qblac7ctoveq5ldft75qxl6k3a.pdf	./txt/work_qblac7ctoveq5ldft75qxl6k3a.txt