This web page is a companion to our Journal of Software: Evolution and Process (JSEP) submission [pdf].
Eduardo C. Campos
Lucas B. L. de Souza
Marcelo de A. Maia
We make publicly available the source code for the regular expressions used for code term detection in Java and C++ programming languages.
Moreover, you can also download the class that contains the reserved words for programming languages (Java, C# and C++) and LINQ API.
You can download the dataset used for training and testing the "How-to" classifier as an ARFF file (Attribute-Relation File Format) . This file can be loaded into Weka Interface.