A fast, robust library to check for offensive language in strings. This version of "profanity-check" is used by Bleepy.
Project description
bleepy-profanity-check
pip install bleepy-profanity-check
profanity-check
version used for Bleepy
A fast, robust Python library to check for profanity or offensive language in strings. Read more about how and why profanity-check
was built in this blog post. You can also test out profanity-check
in your browser.
Notice: We created a library for this project, see: https://pypi.org/project/alt-profanity-check/ and https://gitlab.com/dimitrios/alt-profanity-check/
Disclaimer
Profanity-check is originally created by Victor Zhou, and updated by other contributors. This version of profanity-check is used by Bleepy to detect and bleep tagalog and english profanity from videos. Therefore this version is called bleepy-profanity-check.
How It Works
profanity-check
uses a linear SVM model trained on 200k human-labeled samples of clean and profane text strings. Its model is simple but surprisingly effective, meaning profanity-check
is both robust and extremely performant.
Why Use profanity-check?
No Explicit Blacklist
Many profanity detection libraries use a hard-coded list of bad words to detect and filter profanity. For example, profanity uses this wordlist, and even better-profanity still uses a wordlist. There are obviously glaring issues with this approach, and, while they might be performant, these libraries are not accurate at all.
A simple example for which profanity-check
is better is the phrase "You cocksucker" - profanity
thinks this is clean because it doesn't have "cocksucker" in its wordlist.
Performance
Other libraries like profanity-filter use more sophisticated methods that are much more accurate but at the cost of performance. A benchmark (performed December 2018 on a new 2018 Macbook Pro) using a Kaggle dataset of Wikipedia comments yielded roughly the following results:
Package | 1 Prediction (ms) | 10 Predictions (ms) | 100 Predictions (ms) |
---|---|---|---|
profanity-check | 0.2 | 0.5 | 3.5 |
profanity-filter | 60 | 1200 | 13000 |
profanity | 0.3 | 1.2 | 24 |
profanity-check
is anywhere from 300 - 4000 times faster than profanity-filter
in this benchmark!
Accuracy
This table speaks for itself:
Package | Test Accuracy | Balanced Test Accuracy | Precision | Recall | F1 Score |
---|---|---|---|---|---|
profanity-check | 95.0% | 93.0% | 86.1% | 89.6% | 0.88 |
profanity-filter | 91.8% | 83.6% | 85.4% | 70.2% | 0.77 |
profanity | 85.6% | 65.1% | 91.7% | 30.8% | 0.46 |
See the How section below for more details on the dataset used for these results.
Installation
$ pip install profanity-check
Usage
from profanity_check import predict, predict_prob
predict(['predict() takes an array and returns a 1 for each string if it is offensive, else 0.'])
# [0]
predict(['fuck you'])
# [1]
predict_prob(['predict_prob() takes an array and returns the probability each string is offensive'])
# [0.08686173]
predict_prob(['go to hell, you scum'])
# [0.7618861]
Note that both predict()
and predict_prob
return numpy
arrays.
More on How/Why It Works
How
Special thanks to the authors of the datasets used in this project. profanity-check
was trained on a combined dataset from 2 sources:
- t-davidson/hate-speech-and-offensive-language, used in their paper Automated Hate Speech Detection and the Problem of Offensive Language
- the Toxic Comment Classification Challenge on Kaggle.
profanity-check
relies heavily on the excellent scikit-learn
library. It's mostly powered by scikit-learn
classes CountVectorizer
, LinearSVC
, and CalibratedClassifierCV
. It uses a Bag-of-words model to vectorize input strings before feeding them to a linear classifier.
Why
One simplified way you could think about why profanity-check
works is this: during the training process, the model learns which words are "bad" and how "bad" they are because those words will appear more often in offensive texts. Thus, it's as if the training process is picking out the "bad" words out of all possible words and using those to make future predictions. This is better than just relying on arbitrary word blacklists chosen by humans!
Caveats
This library is far from perfect. For example, it has a hard time picking up on less common variants of swear words like "f4ck you" or "you b1tch" because they don't appear often enough in the training corpus. Never treat any prediction from this library as unquestionable truth, because it does and will make mistakes. Instead, use this library as a heuristic.
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
Built Distribution
File details
Details for the file bleepy-profanity-check-0.1.9.tar.gz
.
File metadata
- Download URL: bleepy-profanity-check-0.1.9.tar.gz
- Upload date:
- Size: 1.9 MB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/4.0.2 CPython/3.9.16
File hashes
Algorithm | Hash digest | |
---|---|---|
SHA256 | 155443fb2f0e8ec8e02ff2a8fba1f04d7c78b7b3b8141137e2b6cc6b4f81fc7b |
|
MD5 | c781fa3a84d75a6a6fd9fd361238c771 |
|
BLAKE2b-256 | c722180ee174255d8fcb02a7956b126a65bbc841994f8fd100b21919ae317823 |
File details
Details for the file bleepy_profanity_check-0.1.9-py3-none-any.whl
.
File metadata
- Download URL: bleepy_profanity_check-0.1.9-py3-none-any.whl
- Upload date:
- Size: 1.9 MB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/4.0.2 CPython/3.9.16
File hashes
Algorithm | Hash digest | |
---|---|---|
SHA256 | fad371fb4710da518b90fa41bcc0915eaef1399480cd7de25e75cf8bd7788661 |
|
MD5 | 00b06b3530d1de1e9547063e7f4b8aea |
|
BLAKE2b-256 | 39231a567880ae90b42d52c2938885828b8c2cda281a60c27b584f4540516925 |