Showing 47 tools matching filters

HuggingFace on Sheets

Media Country or Region United States of America Sourced From Hugging Face: The Essential AI Toolkit for Journalists and Content Creators

The Hugging Face on Sheets tool allows you or your newsroom to seamlessly integrate Hugging Face models with Google Sheets. It enables you to run machine learning models directly from a spreadsheet, providing functionalities such as text classification, sentiment analysis, and language translation right within a sheet. For example, you could use the tool to automatically analyze the sentiment of multiple social media posts in a dataset or translate articles into different languages, all within the convenience of Google Sheets.

Newsgathering and Fact-Checking Production

Language Checker

Media Country or Region Norway Sourced From JournalismAI

The Language Checker is a tool that uses deep learning to detect the language spoken in audio or video files. By uploading a file, the system identifies the language used, helping users verify content or provide translations. It’s designed for analyzing spoken language in various media formats.

Newsgathering and Fact-Checking

Mecodify by MeCoDEM

Media Country or Region Egypt Sourced From Partnership on AI: AI Tools for Local Newsrooms Database

Mecodify is an open-source tool developed by MeCoDEM (Media, Conflict, and Democratisation) to simplify the analysis and visualization of big data. It is particularly designed to analyze data collected from social media platforms, including X (formerly Twitter), allowing users to track trends and patterns. The tool provides intuitive data visualizations, helping to uncover insights about social media conversations and their potential impact on media, conflict, and democracy.

Newsgathering and Fact-Checking

Minutes

Media Country or Region United States of America Sourced From JournalismAI

The Minutes application scrapes, transcribes, and summarizes city council meetings from various video sources. It provides a searchable database of meeting content, allowing users to easily access and navigate important public discussions, thereby enhancing transparency and civic engagement.

Newsgathering and Fact-Checking Production

olmOCR

Media Country or Region United States of America Sourced From Hugging Face: The Essential AI Toolkit for Journalists and Content Creators

olmOCR converts PDFs and other documents into plain text while preserving natural reading order. It supports complex elements like tables, equations, and handwriting, making it ideal for processing academic papers and technical documents. Users can run olmOCR on their own GPUs, enabling high-throughput document conversion at scale. This allows for cost-effective processing, estimated at just $190 per million pages, making it suitable for large-scale academic and technical archives.

Newsgathering and Fact-Checking

OmniParser

Media Country or Region United States of America Sourced From Hugging Face: The Essential AI Toolkit for Journalists and Content Creators

OmniParser is a tool designed to convert graphical user interface (GUI) screens (the layout and elements you see on an app or website) into structured elements, making it easier for newsrooms to extract and analyze data from visual sources. Journalists can use it to turn app screenshots (images of the app's interface) into structured data, extracting specific information for reporting or research. This tool helps transform visual data into formats that can be processed and analyzed, streamlining the work with complex user interfaces (the interactive part of apps or websites). Examples for newsroom use include analyzing news apps and converting visual information into usable structured data for investigations.

Newsgathering and Fact-Checking Workflow and Other General Operations

Originality.ai

Media Country or Region Canada Sourced From Journalists Toolbox

Originality.ai is a comprehensive tool that can help, among others, journalists ensure the authenticity of written content. It detects AI-generated text, helping journalists and editors maintain transparency and credibility in their reporting. The tool also checks for plagiarism, ensuring that sourced material complies with copyright and originality standards. With readability analysis and fact-checking capabilities, it helps refine content for clarity and accuracy, streamlining editorial workflows. Ideal for media outlets, it integrates seamlessly into existing systems via API, making it a reliable solution for producing high-quality, trustworthy content.

Newsgathering and Fact-Checking Production

Phi-4-mini Playground

Media Country or Region United States of America Sourced From Hugging Face: The Essential AI Toolkit for Journalists and Content Creators

phi-4-mini is an advanced AI model for generating and understanding natural language. It can assist journalists by helping them draft articles, summarize complex topics, or brainstorm ideas with minimal input. With a deep understanding of language, the tool can provide relevant content suggestions, making it ideal for content creation and ideation. It streamlines the writing process and boosts productivity by offering quick insights and detailed explanations.

Distribution and Audience Engagement Newsgathering and Fact-Checking Production Workflow and Other General Operations

Quispe Chequea by Ojo Publico

Media Country or Region Peru Sourced From JournalismAI

Quispe Chequea verifies content in Spanish and Peruvian indigenous languages like Quechua, Aymara, and Awajún. It converts fact-checked information into audio for radio dissemination across nine regions. The platform leverages large language models for analysis and Tacotron 2 for voice synthesis, allowing indigenous interpreters to create voices that deliver credible news in local languages. It's used by trained regional broadcasters to ensure factual communication for Andean and Amazonian communities.

Newsgathering and Fact-Checking

Qwen2-VL

Media Country or Region China Sourced From Hugging Face: The Essential AI Toolkit for Journalists and Content Creators

Qwen2-VL is a multimodal AI model that processes both text and images to generate responses. It can analyze visual inputs, interpret text within images, and provide detailed descriptions or answers based on the combined context of text and visuals.

Newsgathering and Fact-Checking
With the support of

User Guide

© IRCAI and UNESCO

The designations used and the presentation of materials throughout this repository do not imply the expression of any opinion on the part of UNESCO and IRCAI concerning the legal status of any country, territory, city or area, or of its authorities, or concerning the delimitation of its frontiers or boundaries. The ideas, opinions, and content presented in this repository are those of the authors; they do not necessarily represent the views of UNESCO and IRCAI and do not commit the Organizations.