Need help with hate-speech-and-offensive-language?
Click the “chat” button below for chat support from the developer who created it, or find similar developers for support.
t-davidson

Description

Repository for the paper "Automated Hate Speech Detection and the Problem of Offensive Language", ICWSM 2017

491 Stars 180 Forks MIT License 3 Commits 3 Opened issues

Services available

Need anything else?

Automated Hate Speech Detection and the Problem of Offensive Language

Repository for Thomas Davidson, Dana Warmsley, Michael Macy, and Ingmar Weber. 2017. "Automated Hate Speech Detection and the Problem of Offensive Language." ICWSM. You read the paper here.

NOTE: This repository is no longer actively maintained. Please do not post issues regarding the compatibility of the existing code with new versions of Python or the packages used.

2019 NEWS

We have a new paper on racial bias in this dataset and others, you can read it here

WARNING: The data, lexicons, and notebooks all contain content that is racist, sexist, homophobic, and offensive in many other ways.

You can find our labeled data in the

data
directory. We have included them as a pickle file (Python 2.7) and as a CSV. You will also find a notebook in the
src
directory containing Python 2.7 code to replicate our analyses in the paper and a lexicon in the
lexicons
directory that we generated to try to more accurately classify hate speech. The
classifier
directory contains a script, instructions, and the necessary files to run our classifier on new data, a test case is provided.

Please cite our paper in any published work that uses any of these resources. ~~~ @inproceedings{hateoffensive, title = {Automated Hate Speech Detection and the Problem of Offensive Language}, author = {Davidson, Thomas and Warmsley, Dana and Macy, Michael and Weber, Ingmar}, booktitle = {Proceedings of the 11th International AAAI Conference on Web and Social Media}, series = {ICWSM '17}, year = {2017}, location = {Montreal, Canada}, pages = {512-515} } ~~~

Contact We would also appreciate it if you could fill out this short form if you are interested in using our data so we can keep track of how these data are used and get in contact with researchers working on similar problems.

If you have any questions please contact

trd54 at cornell dot edu
.

We use cookies. If you continue to browse the site, you agree to the use of cookies. For more information on our use of cookies please see our Privacy Policy.