Back To Projects
Fake News Classification
Roshni K. | Summer 2022

As fake news becomes more of a problem across the US, its consequences are becoming more and more damaging. This project aims to combat this disinformation through an artificial intelligence algorithm that can classify real articles versus fake ones.


As fake news becomes more of a problem across the US, its consequences are becoming more and more damaging. Many viewers who interact with information online are unable to distinguish the difference between fake information and real information, especially with social media worsening the spread of fake articles. This project aims to combat this disinformation through an artificial intelligence algorithm that can classify real articles versus fake ones. The model utilizes a BERT model and is tested on two different datasets, the Kaggle dataset and the LIAR dataset. The results are also presented through an app where readers can input any article and immediately find out whether it contains false information or not.

Explore More!

Roshni K.
Philip Bell
Computer Science MS from Georgia Tech, Harvard and Oxford alum, AI Engineer at Cognino

Related Projects

Biased News Detection Using Artificial Intelligence

Biased news has become especially problematic in modern times. In this paper, we investigate the abilities of various machine learning models to correctly identify biased news. Our results indicate that artificial intelligence is very capable of doing this detection. In particular, both logistic regression and K-nearest neighbor classifier performed rather well in cross validation.
Arianna H. | Summer 2022
Mentored by Matteo Santamaria
The Effect of the News on the Stock Market

I remember opening my investing account one day and looking at my stocks, noticing that the majority of them were declining pretty severely. Ever since the Russia and Ukraine war, this had been the case. I saw many news headlines talking about the market, and how it was affected from this war. It was then I realized, why isn’t there a way for us to predict these changes in the market given sufficient news headlines?
Pranav B. | Summer 2022
Mentored by Eric Bradford
Generating Instagram Captions with ViT-GPT2 and GPT3

This paper presents a novel approach for generating Instagram captions based on visual features and language models. Our caption generator combines Vision Transformer-GPT2 and GPT3 to generate descriptive and engaging captions in the style of an Instagram post.
Ariel M. | Summer 2022
Mentored by Roger Jin