Smart Email Notifier Using Supervised Learning
Keywords:
Supervised Learning, Naïve Bayes, Support Vector Machines, TF-IDF, python, .NET.Abstract
Communication via email is surely the most common and important aspect of a professional life and oftentimes our inbox is inundated with worthless emails. Various studies have shown that interruptions due to email usage have a negative impact on productivity thus there is a strong need of an intelligent system that could notify the user only when an important email arrives so This paper focuses on the applicability of machine learning to answer a simple question: is an incoming email worthy enough of user's time? To answer this question we have used two ML models namely, Multinominal Naive Bayes and Support Vector Machines. In addition, this project aims to use the learned models to build a real-time email notifier software that will estimate whether a received email is worth notifying the user.
References
- Chang, C.-C., and Lin, C.-J. LIB-SVM: A Library for Support Vector Machines. Department of Computer Science, National Taiwan University, 2001.
- Chaput, M. stemming 1.0. https://pypi.python.org/pypi/stemming/1.0Feb. 2010. Python implementation of theporter2 stemming algorithm.
- Hsu, C.-W., Chang, C.-C., and Lin, C.-J. A Practical Guide to Support Vector Classsification. Department of Computer Science, National Taiwan University, Taipei, Taiwan,2003.
- Wikipedia. F1 score. http://en.wikipedia.org/wiki/F1_score. Wikipedia page for the F1 score.
- Wikipedia. tf-idf. http://en.wikipedia.org/wiki/Tf%E2%80%93idf. Wikipedia page for the TF-IDF metric.
- https://www.kaggle.com/wcukierski/enron-email-dataset
- A cross-platform library for .NET http://imapx.org
- The IronPython package http://ironpython.net
Downloads
Published
Issue
Section
License
Copyright (c) IJSRCSEIT

This work is licensed under a Creative Commons Attribution 4.0 International License.