Skip to contents

The polarity table of sentiment-thematic dictionary of economic, financial and legal terms - EcSentiThemeLex. Table contains 15235 words forms, and 9841 has non-neutral sentiment scores.

Usage

data(hash_sentiment_ecsentithemelex)

Format

A data table with 15235 rows and 2 variables:

token

a token (word)

score

a sentiment score: from −2 (strongly negative) to +2 (strongly positive) with step 1

Details

The polarity table was generated from original lexicon table (see key_ecsentithemelex) based on the following rules:

  • tokens consisting of more than one word were discarded (as required for bag-of-words sentiment analysis)

  • all possible word forms were added as separete tokens

  • for the words containing the letter "ё" the spelling option with letter "е" were added as separete token

License

The dictionary is published under Creative Commons "Attribution-NonCommercial-ShareAlike" 4.0 International License (CC BY-NC-SA 4.0). For additional permissions (including the commercial use) please contact to Elena Fedorova <ecolena@mail.ru>.

References

Fedorova, E., Afanasyev, D., Demin, I., Lazarev, A., Nersesyan, R., Pyltsin, I.V. (2020). Development of a tonal-thematic dictionary EcSentiThemeLex for the analysis of economic texts in Russian. Journal of Applied Informatics, 6 (15), 58–77. DOI: https://doi.org/10.37791/2687-0649-2020-15-6-58-77.