Ebrahim Bagheri
Software Systems
Misinformation is becoming a prevalent phenomenon on the Web and especially on the social network. The objective of this capstone project will be to effectively classify a user-generated textual content into being either unreliable misinformation or reliable information through the use of text analytics, web mining and machine learning techniques.
To use Artificial Intelligence and Machine Learning techniques to label content into misinformation or otherwise.
* analyze literature fake news and misinformation detection
* work with existing gold standard datasets for misinformation
* perform extensive feature engineering for this task
* build machine learning classification models for misinformation detection
This work will build on state of the art literature on the topic of misinformation. The students will start by reading the following papers:
1. https://arxiv.org/abs/1812.00315
2. https://arxiv.org/abs/1904.11679
+ Work with gold standard datasets for misinformation and fake news
+ perform extensive feature engineering
+ implement integrated code in Python to automatically extract features
+ use CNN models to extract unsupervised features
+ train classification models for predicting fake news
+ systematically evaluate the work
+ Work with gold standard datasets for misinformation and fake news
+ perform extensive feature engineering
+ implement integrated code in Python to automatically extract features
+ Work with gold standard datasets for misinformation and fake news
+ use CNN models to extract unsupervised features
+ train classification models for predicting fake news
+ Work with gold standard datasets for misinformation and fake news
+ train classification models for predicting fake news
+ Work with gold standard datasets for misinformation and fake news
+ implement integrated code in Python to automatically extract features
+ train classification models for predicting fake news
+ systematically evaluate the work
EB01: Fake news prediction | Ebrahim Bagheri | Wednesday August 28th 2019 at 04:49 PM