journalism
BERT_Journalism_SentimentBERT Model Sentiment Analysis
Project Overview
This repository contains scripts and resources for performing sentiment analysis on news articles referring to Russinan-Ukrainian 2022 War using a pre-trained BERT model. The goal is to classify the sentiment of each article as either Pro-Russian or Pro-Ukrainian and calculate a sentiment score.
The scripts were used for my MA thesis
Steps to use the model:
Scraping Journal ariticles from site archives and create a large dataset… See the full description on the dataset page: https://huggingface.co/datasets/Giannis79/BERT_Journalism_Sentiment.investigative-journalism-training
Investigative Journalism Training
Instruction-tuning dataset for investigative-journalism and OSINT assistant workflows: tool selection, investigation methodology, verification, financial investigation, digital security/OPSEC, sourcing and evidence, media law, editing, and ethics.
This dataset was used to fine-tune the Buried Signals "journalist" model family (Gemma 4 and Qwen3.5/3.6 LoRA adapters and merges). See the model cards under tomvaillant for trained checkpoints.… See the full description on the dataset page: https://huggingface.co/datasets/tomvaillant/investigative-journalism-training.journalism
Domain Dataset Grower
This dataset was generated by distilabel as a domain specific dataset for the domain of farming. The dataset used this seed data to generate the samples. The seed data was define by a domain expert and the generated data can be reviewed in this Argilla space here: Argilla
If you want to define a domain specific seed dataset for your own domain, you can use the distilabel tool to generate the dataset, and seed your dataset here
journalism… See the full description on the dataset page: https://huggingface.co/datasets/fdaudens/journalism.