Email Datasets can be found here

A Person Of Interest identifier based on ENRON CORPUS data.

The code and data for "Are Large Pre-Trained Language Models Leaking Your Personal Information?" (Findings of EMNLP '22)

Fraud Detection by finding the Person of Interest (POI)

The fraud identification models were build using Python Scikit-learn machine-learning module.

CEREC and Seed corpus for coreference resolution for email threads taken from the Enron Corpus

📩 Modeling the Enron dataset of emails using graphs

[Incomplete] A chrome extension that tells you if a mail you're currently drafting is going to be classified as spam or not.

A project on Extract-Transform-Load (ETL) operations performed on the emails from the infamous enron corpus database.

Natural Language Processing (NLP) and programmatic data extraction in large scale fraud investigations.

Enron Email Analysis

📧 A data engineering exercise

Spam and No Spam text classification with Convolutional Neuronal Network and Word Embedding

This repository contains code for normalizing the Enron dataset.

Identifying and cleaning the outliers of the Enron Dataset.

LT2212 V20 Assignment 3: Same-author-classification via feed-forward neural networks: Transformed email text (Enron) into a machine readable representation and built a classifier that determines whether two texts are authored by the same person or not.

Machine learning algorithms applied to explore Enron email dataset and figure out patterns about people involved in the scandal.

The final project for the University of Malta unit Web Intelligence (ICS2205). The 60% component involved an individual analysis on a twitter dataset using NetworkX. The 40% component involves half of group task where an analysis was performed on the enron email dataset using NetworkX.

Learning how to use machine learning and deep learning algorithms/tips/tricks to solve practical problems in Python.