GSoC 2018: SpamBrainz - Fighting spam with machine learning

[Leo_Verto]

Notebooks, references and revised timeline

Notebooks:

• WIP Spam/nonspam editor comparison
• Editor statistics collection
• Dataviz playground

References

Papers/scientific articles

• Bhowmick, Hazarika (2016) Machine Learning for E-mail Spam Filtering: Review,
  Techniques and Trends
• Caruana, Li (2012) A survey of emerging approaches to spam filtering
• Arif, Li et al. (2017) Sentiment analysis and spam detection in short informal text using learning classifier systems
• Giyanani, Desai (2014) Spam Detection using Natural Language Processing
• Androutsopoulos, Paliouras et al. (2000) Learning to Filter Spam E-Mail: A Comparison of a Naive
  Bayesian and a Memory-Based Approach
• Santosh, Maity, Mukherjee (2017) ENWalk: Learning Network Features for Spam
  Detection in Twitter
• Miikkulainen, Liang et al. (2017) Evolving Deep Neural Networks
• Ren, Triantafillou et al. (2018) Meta-Learning for Semi-Supervised Few-Shot Classification
• Chen, Shah (2018) Explaining the Success of Nearest Neighbor Methods in Prediction

Blog posts

• Building a Spam Filter Using Machine Learning
• Spam detection using neural networks in Python
• How To Build a Simple Spam-Detecting Machine Learning Classifier
• Naive Bayes and Spam Detection
• A TensorFlow Tutorial: Email Classification
• Deceptive Spam Review Detection with CNN Using TensorFlow
• Implementing a CNN for Text Classification in TensorFlow
• Introduction to Natural Language Processing (NLP)
• The Mobile Neural Network Lottery: How to Find Your Winning Ticket

Repositories

• Tensorflow email spam detection
• Detecting Spam Emails using CNN
• Convolutional Neural Network for Text Classification in Tensorflow

Books

• Ng, Andrew (unpublished): Machine Learning Yearning

GDPR-Related

• GDPR and Data Processing Agreements
• Will GDPR Make Machine Learning Illegal?
• Specifically GDPR Article 6

Revised timeline

• Weeks 0-3: Researched existing projects, state-of-the-art of spam detection and machine learning.
• Week 1: Designed SpamBrainz’ project structure and started work on monitoring and management web interface.
• Week 3: Researched potential GDPR issues regarding SpamBrainz.
• Weeks 4-5: Received Spam data set, analyzed, compared and visualized spam/non-spam editor data.
• Week 6-7: Build the API and the SpamBrainz backend which the detection modules can plug into and a predictable dummy module to test it.
• Weeks 8-11: Create the machine learning module and tweak the hyperparameters to hopefully get it to a usable state.
• Week 12: Documentation, designing a simple website explaining SpamBrainz to our end users.
• Week 13: Buffer period.