SenSALDO
A Swedish sentiment lexicon based on SALDO
Jacobo Rouces, Lars Borin, Nina Tahmasebi, Stian Rødven Eide
SenSALDO is a sentiment lexicon for Swedish based on the full-scale Swedish semantic lexicon for language technology applications, SALDO. SenSALDO has been developed in the research program Towards a knowledge-based culturomics, and with support by the Swe-Clarin research infrastructure, both funded by the Swedish Research Council.
SenSALDO v. 0.2 contains 12,287 word senses from SALDO labeled for sentiment (prior lexical polarity) with one of the sentiment labels "-1" (negative), "0" (neutral), or "1" (positive). The sentiment labels have been assigned in a partly automatic, partly manual process described in the publications listed below. The final set of word senses has been manually curated.
In addition to the list of sentiment-labeled word senses, the downloadable dataset contains a list of sentiment labeled text words with their parts of speech (almost 85,000 words).
The word senses in SenSALDOS can have only one sentiment label each, but a text word may appear with more than one label, in the cases where a text word corresponds to more than one word sense, with different sentiment labels. See the information in the file header.
If you use SenSALDO in research resulting in a publication, please cite one or more of the publications listed below among your references.
Publikationer • Publications
-
Jacobo Rouces, Nina Tahmasebi, Lars Borin, Stian Rødven-Eide
(2018):
SenSALDO: Creating a Sentiment Lexicon for Swedish, in
LREC 2018, Eleventh International Conference on Language Resources and Evaluation, 7-12 May 2018, Miyazaki (Japan)
-
Jacobo Rouces, Nina Tahmasebi, Lars Borin, Stian Rødven-Eide
(2018):
Generating a Gold Standard for a Swedish Sentiment Lexicon, in
LREC 2018, Eleventh International Conference on Language Resources and Evaluation, May 7-12, 2018, Miyazaki (Japan)
-
Jacobo Rouces, Lars Borin, Nina Tahmasebi, Stian Rødven-Eide
(2018):
Defining a gold standard for a Swedish sentiment lexicon: Towards higher-yield text mining in the digital humanities, in
CEUR Workshop Proceedings vol. 2084. Proceedings of the Digital Humanities in the Nordic Countries 3rd Conference Helsinki, Finland, March 7-9, 2018. Edited by Eetu Mäkelä Mikko Tolonen Jouni Tuominen