CroSentiLex
Please use the following text to cite this item or export to a predefined format:
Glavaš, Goran; Šnajder, Jan and Dalbelo Bašić, Bojana, 2012, CroSentiLex, HR-CLARIN, http://hdl.handle.net/20.500.14615/2-24
Authors
Item identifier
Date issued
2012
Size
37000 tokens
Language(s)
Description
CroSentiLex is a sentiment lexicon for Croatian. CroSentilex consists of two files (crosentilex-positives.txt and crosentilex-negatives.txt), each containing 37K Croatian lemmas ranked by positivity and negativity, respectively, with the corresponding PageRank scores. The rankings were created automatically based on small positive and negative seed sets and co-occurrence
frequencies, using the PageRank algorithm.
In addition to the automatically extracted lexicon, human (gold-standard) sentiment annotations for 1200 Croatian lemmas are provided in gs-sentiment-annotations.txt.
Collections
