Fake news prediction

2019 COE Engineering Design Project (EB01)

---

Faculty Lab Coordinator

Ebrahim Bagheri

Topic Category

Software Systems

Preamble

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.

Objective

To use Artificial Intelligence and Machine Learning techniques to label content into misinformation or otherwise.

Partial Specifications

* 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

Suggested Approach

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

Group Responsibilities

+ 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

Student A Responsibilities

+ Work with gold standard datasets for misinformation and fake news
+ perform extensive feature engineering
+ implement integrated code in Python to automatically extract features

Student B Responsibilities

+ Work with gold standard datasets for misinformation and fake news
+ use CNN models to extract unsupervised features
+ train classification models for predicting fake news

Student C Responsibilities

+ Work with gold standard datasets for misinformation and fake news
+ train classification models for predicting fake news

Student D Responsibilities

+ 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

Course Co-requisites