Distilbert-cased-antisemitic-tweets Open-source Model - Free Detection of Antisemitic Tendencies in Tweets Containing 'jew'

Distilbert Cased Antisemitic Tweets

Developed by astarostap

This model is used to detect tweets containing the word 'jew' (Jewish people) and determine whether they exhibit anti-Semitic tendencies.

Text Classification

Transformers

Open Source License:MIT #Anti-Semitic speech screening #Social media text analysis #Manual annotation training

Downloads 22

Release Time : 3/2/2022

Model Overview

A preliminary screening tool for anti-Semitic content trained on 4,000 tweets, flagging potentially suspicious content that may require expert manual review.

Model Features

Preliminary screening tool

As a preliminary screening tool, it flags potentially suspicious content that may require expert manual review.

Annotation based on personal experience

Annotations were completed by the publisher based on personal experience and common anti-Semitic rhetorical features.

Requires manual review

The model is not intended for final determination of whether content is anti-Semitic; expert manual review is still required.

Model Capabilities

Text classification

Hate speech detection

Anti-Semitic content identification

Use Cases

Social media content moderation

Anti-Semitic tweet detection

Detect anti-Semitic content in tweets

Flag suspicious content for manual review

🚀 Antisemitic Tweet Detection Model

This model analyzes tweets containing the word "jew" to identify potential antisemitic content, serving as an initial screening tool for further human review.

🚀 Quick Start

This model takes a tweet with the word "jew" in it, and determines if it's antisemitic.

✨ Features

Analyze tweets with the word "jew" to detect potential antisemitism.
Serve as a first-pass screening tool for human experts.

📦 Installation

No installation steps are provided in the original document, so this section is skipped.

💻 Usage Examples

No code examples are provided in the original document, so this section is skipped.

📚 Documentation

Training Data

This model was trained on 4k tweets, where ~50% were labeled as antisemitic. The author labeled them based on personal experience and knowledge about common antisemitic tropes.

Note

The goal for this model is not to be used as a final say on what is or is not antisemitic, but rather as a first pass on what might be antisemitic and should be reviewed by human experts.
The author is not an expert on antisemitism or hatespeech.
Whether something is antisemitic or not depends on the context, as for any hate speech, and everyone has a different definition for what is hate speech.
If you would like to collaborate on antisemitism detection, please feel free to contact the author at starosta@alumni.stanford.edu.
This model is not ready for production, it needs more evaluation and more training data.

🔧 Technical Details

No technical implementation details are provided in the original document, so this section is skipped.

📄 License

This model is released under the MIT license.

📦 Information Table

Property	Details
Model Type	Antisemitic tweet detection model
Training Data	4k tweets, ~50% labeled as antisemitic

⚠️ Important Note

The goal for this model is not to be used as a final say on what is or is not antisemitic, but rather as a first pass on what might be antisemitic and should be reviewed by human experts. The author is not an expert on antisemitism or hatespeech, and the determination of antisemitism depends on context.

💡 Usage Tip

If you would like to collaborate on antisemitism detection, please feel free to contact the author at starosta@alumni.stanford.edu. Keep in mind that this model is not ready for production and needs more evaluation and training data.

Featured Recommended AI Models

Empowering the Future, Your AI Solution Knowledge Base

English 简体中文繁體中文にほんご