Skip to content

Lexicon.labMT

Lexicon.labMT

labMT(language: labMTLanguage) -> Lexicon

A set of "happiness" sentiment lexicons constructed for various languages.

The 10,000 most frequent words for each language were rated by Mechanical Turk (MT) workers on a scale from 1 to 9, where 1 is the most negative ("saddest") and 9 is the most positive ("happiest"). The words were sourced from several sources, including the Google Books project, the Google Web Crawl, Twitter, the New York Times, music lyrics, and movie and television titles.

Example
import wordlevel as wl

labmt = wl.lex.labMT("english")
Note

The first call for a given language downloads that lexicon from HuggingFace. Later calls for the same language read from the local cache, so each language is only ever downloaded once.

License

This data is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0) License.

Citation

If you use the English lexicon, please cite the following paper.

Dodds, P. S., Harris, K. D., Kloumann, I. M., Bliss, C. A., & Danforth, C. M. (2011). Temporal patterns of happiness and information in a global social network: Hedonometrics and Twitter. PLoS ONE, 6(12), e26752.

If you use any of the non-English lexicons, please cite the following paper.

Dodds, P. S., Clark, E. M., Desu, S., Frank, M. R., Reagan, A. J., Williams, J. R., Mitchell, L., Harris, K. D., Kloumann, I. M., Bagrow, J. P., Megerdoomian, K., McMahon, M. T., Tivnan, B. F., & Danforth, C. M. (2015). Human language reveals a universal positivity bias. Proceedings of the National Academy of Sciences, 112(8), 2389-2394.

Parameters:

Name Type Description Default

language

labMTLanguage

The language of the lexicon

required

Raises:

Type Description
LexiconDownloadError

If the lexicon could not be downloaded from HuggingFace

Source