Title: | Lexicons for Portuguese Text Analysis |
---|---|
Description: | Provides easy access for sentiment lexicons for those who want to do text analysis in Portuguese texts. As of now, two Portuguese lexicons are available: 'SentiLex-PT02' and 'OpLexicon' (v2.1 and v3.0). |
Authors: | Sillas Gonzaga [aut, cre] |
Maintainer: | Sillas Gonzaga <[email protected]> |
License: | GPL-2 | file LICENSE |
Version: | 0.1.0 |
Built: | 2024-11-23 06:19:18 UTC |
Source: | https://github.com/sillasgonzaga/lexiconpt |
Lookup word or term in datasets available on lexiconPT
get_word_sentiment(word, dictionary = c("all", "oplexicon_v2", "oplexicon_v3", "sentilex"))
get_word_sentiment(word, dictionary = c("all", "oplexicon_v2", "oplexicon_v3", "sentilex"))
word |
character. |
A list of all datasets available on lexiconPT filtered by the inputed word.
{ get_word_sentiment("cantar") }
{ get_word_sentiment("cantar") }
OpLexicon is a sentiment lexicon for the Portuguese language. Please see SOUZA and VIEIRA (2012) and SOUZA et al. (2012) for its complete reference and documentation.
oplexicon_v2.1
oplexicon_v2.1
A data frame with 30677 rows and 3 variables:
term
character. The word or term.
type
character. Grammar classification of the word or term.
polarity
integer. Numeric classification of the polarity or sentiment. It can only assume the values of -1, 0, and 1
http://ontolp.inf.pucrs.br/Recursos/downloads-OpLexicon.php
OpLexicon is a sentiment lexicon for the Portuguese language. Please see SOUZA and VIEIRA (2012) and SOUZA et al. (2012) for its complete reference and documentation.
oplexicon_v3.0
oplexicon_v3.0
A data frame with 32191 rows and 4 variables:
term
character. The word of term. It also includes emoticons.
type
character. The type of the term.
polarity
integer. Numeric classification of the polarity or sentiment.
polarity_revision
character. Was the polarity obtained manually (A) or automatically (C)?
http://ontolp.inf.pucrs.br/Recursos/downloads-OpLexicon.php
A sentiment lexicon designed for the extraction of sentiment and opinion about human entities in Portuguese texts. Please see SILVA, CARVALHO, COSTA and SARMENTO (2010) for its complete reference and documentation.
sentiLex_lem_PT02
sentiLex_lem_PT02
A data frame with 7014 rows and 5 variables:
term
character The word of term.
grammar_category
character. The grammar classification of the term.
polarity
double. Numeric classification of the polarity or sentiment.
polarity_target
character. Polarity target. It can be N0 (subject), N1 (complement) or N2 (no documentation was found for what it means).
polarity_classification
character. Was the polarity obtained manually (MAN) or automatically (JALC)?.
Mário J. Silva, Paula Carvalho, Carlos Costa, Luís Sarmento, Automatic Expansion of a Social Judgment Lexicon for Sentiment Analysis Technical Report. TR 10-08. University of Lisbon, Faculty of Sciences, LASIGE, December 2010. doi: 10455/6694