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
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
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
Algorithm | Hash digest | |
---|---|---|
SHA256 | 251c6ed97998f67852627170925a8f1059d5d5e0553682a165934b1d036e139d |
|
MD5 | 973b6900dc59a9193b092bd705cde609 |
|
BLAKE2b-256 | a8da0b8feb5187f95a076f237e01f777c9238afafb6f2e2748779dd522c32809 |