A Machine Learning Approach to Vulnerability Detection Combining Software Metrics and Topic Modelling: Evidence from Smart Contracts

This repository contains the code and data associated with our submission entitled 'A Machine Learning Approach to Vulnerability Detection Combining Software Metrics and Topic Modelling: Evidence from Smart Contracts'. The replication package, provides the script for topic modelling, binary and multilabel classification, the code to run NMF and LDA analysis, and the dataset used for the analysis. The dataset also provides LDA and NMF models employed for the analysis, and provides plots and wordclouds for topics visualisation for both models.Further instructions are provided in the README.md.