Skip to main content

A sentiment analysis library for detecting absolutist language.

Project description

A sentiment analysis library for detecting absolutist language.

Quickstart

Installation:

$ pip install absolang
$ python -m spacy download en_core_web_sm

Determining absolutist index for text:

>>> from absolang import absolutist, absolutist_index
>>> absolutist_index("The bigger dog is running.")
0.0
>>> absolutist("The bigger dog is running.")
False
>>> absolutist_index("He was completely bowled over.")
0.2
>>> absolutist("He was completely bowled over.")
True

Algorithm

  • Parse text into tokens using Spacy’s en_core_web_sm language model.

  • Count the number of word tokens (a token is considered a word if it consists solely of characters from the alphabet).

  • Count the number of absolutist word tokens (a token is considered absolutist if its stem word is in the dictionary of absolutist words and it is not preceded by a negation, modifier or interjection).

  • The absolutist index is the number of absolutist words divided by the total number of words.

  • Text is considered absolutist if the index is greater than 1.1 percent.

Caveats

  • The frequency of absolutist words in control texts (ones written by people presumed not to suffer from anxiety or depression more than the average person) is about 1%, so one needs a few hundred words of texts before results start becoming meaningful.

References

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

absolang-0.0.2.tar.gz (4.0 kB view details)

Uploaded Source

File details

Details for the file absolang-0.0.2.tar.gz.

File metadata

  • Download URL: absolang-0.0.2.tar.gz
  • Upload date:
  • Size: 4.0 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No

File hashes

Hashes for absolang-0.0.2.tar.gz
Algorithm Hash digest
SHA256 251c6ed97998f67852627170925a8f1059d5d5e0553682a165934b1d036e139d
MD5 973b6900dc59a9193b092bd705cde609
BLAKE2b-256 a8da0b8feb5187f95a076f237e01f777c9238afafb6f2e2748779dd522c32809

See more details on using hashes here.

Provenance

Supported by

AWS AWS Cloud computing and Security Sponsor Datadog Datadog Monitoring Fastly Fastly CDN Google Google Download Analytics Microsoft Microsoft PSF Sponsor Pingdom Pingdom Monitoring Sentry Sentry Error logging StatusPage StatusPage Status page