OpenViSTAI · Agents · Blockchain · Crypto
Submit a project
Menu
AI Data & Analytics

Hate Speech And Offensive Language

A research repository for a 2017 ICWSM study of automated hate-speech detection and offensive language, containing labeled data, a lexicon, Python 2.7 analysis notebooks and files for applying a classifier to new text.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

Hate Speech And Offensive Language — OpenViST project profile in AI Data & Analytics.
OpenViST project illustration. See the linked sources for product details.
Understand the project

Practical overview

When it fits

Use it when a research project needs the study’s labeled data, analysis materials, lexicon or classifier example, and can account for the repository’s Python 2.7-era code and maintenance status.

Who it is for

  • Researchers studying hate-speech and offensive-language classification.
  • Readers seeking labeled text data, a lexicon or a historical classifier implementation for research.

Documented uses

  • Explore the labeled dataset in CSV or Python 2.7 pickle form.
  • Reproduce the study’s analyses with the included notebook.
  • Apply the supplied classifier to new text using its instructions and test case.
  • Examine the provided lexicon as a reference in classification research.
Before you choose

Requirements & limits

The repository is public and identified as MIT-licensed. The README says the project is no longer actively maintained.

  • The data is available as both CSV and a Python 2.7 pickle file.
  • The analysis notebook is written in Python 2.7.
  • The classifier directory includes instructions, supporting files and a test case, but the repository cautions that compatibility with newer Python and packages is not maintained.
  • The README asks users to cite the paper in published work using its resources and warns that the materials contain racist, sexist, homophobic and other offensive content.

Check current requirements in the official documentation. Source-based guidance does not mean OpenViST has run or independently tested this project.

Source-based practical guide

Use the supplied classifier test case

Follow the repository’s documented path for applying its classifier materials to new data, using the included test case as the provided example.

Before you start

  • The repository’s classifier script, instructions and necessary files.
  • Text data suitable for the classifier workflow.

Steps

  1. Review the classifier directory for its script, instructions and supporting files.

  2. Use the provided test case as the repository’s example for running the classifier on data.

Expected outcome

A documented example of applying the supplied classifier to text data.

Guide limitations

  • The repository is no longer actively maintained; its README warns that compatibility with newer Python and package versions is not supported.
  • The README does not specify dependency installation steps in the available documentation.
  • The data and related materials may contain racist, sexist, homophobic and other offensive content.
Documentation 1 ↗
Evidence and transparency

Sources & review

Official repository ↗
Source record details
Source availability
Active
Sources checked
16 October 2026
Original website title
t-davidson/hate-speech-and-offensive-language · Official homepage title · retained in its source language
How we review sourcesSuggest a correction