Fake News Detection by Learning Convolution Filters through Contextualized Attention

Fake News Detection on Liar dataset

fake new detection for liar and kaggle dataset using logistic regression, svm, cnn, lstm and bi-lstm

We propose a novel method of fine-tuning the model for a particular downstream task, which proves to be more efficient and generalizable. We show that in an example of a fake news detection task, utilizing three distinct datasets and outperforming the baseline model in both the same dataset and cross-dataset zero-shot test.

A comparative study for fake news detection using deep learning techniques.

Experiments with fake news detection using transformer models and classical baselines for multi-class political statement classification.

Fake News Detection by Learning Convolution Filters through Contextualized Attention

A machine learning project for fake news detection using the LIAR dataset. This repository includes Jupyter notebooks for data preprocessing, exploratory data analysis, training, and evaluation of classification models like Logistic Regression, SVM, and Random Forest.

Fake news detection

A deep learning-based fake news detection system leveraging BERT and metadata features. Built on the LIAR2 dataset, this project achieves ~65% accuracy in classifying news statements across six veracity categories from "pants-fire" to "true".