Skip to contents

Data containting sentiment dictionaries for negative fullform tokens with part-of-speech tags in Norwegian, based on the Sentiment Analysis for Norwegian Text project at the Department of Informatics, University of Oslo.

Usage

data(nor_fullform_pos_sent_negative)

Format

An object of class data.frame containing all negative fullform tokens and their parts-of speech over three variables:

tokenThe token (word) in fullform
posPart-of-speech for the token
is_base_formWhether the token is the base form of the word ("yes") or not ("no")

References

Barnes et al. (2019) Lexicon information in neural sentiment analysis: a multi-task learning approach. Proceedings of the 22nd Nordic Conference on Computational Linguistics. Turku, Finland (ACL Anthology)

Examples

data(nor_fullform_pos_sent_negative)

head(nor_fullform_pos_sent_negative)
#>         token                   pos is_base_form
#> 1 forgiftende Participle_Adjectives          yes
#> 2 forgiftende Participle_Adjectives           no
#> 3     avgrunn                  Noun          yes
#> 4  avgrunnene                  Noun           no
#> 5     avgrunn                  Noun           no
#> 6   avgrunner                  Noun           no