Generalized Term Semantics (GenTS)

GenTS is a Java API for measuring semantic relatedness between pairs of words using a large term-context matrix. Available for download here: GeneralizedTermSemantics, and also available through GitHub: https://github.com/alistairk/GeneralizedTermSemantics.

This software package is an implementation of the programs described in: Alistair Kennedy, Stan Szpakowicz (2012). "Supervised Distributional Semantic Relatedness". To appear in the Proceedings of the 15th International Conference on Text, Speech and Dialogue TSD 2012.
pdf bib

1911 Roget’s Thesaurus Electronic Lexical Knowledge Base

A Java API of the 1911 Roget’s Thesaurus, originally developed by Mario Jarmasz, called Open Roget's Thesaurus, is currently available here: open_rogets_1.4.1.tar.gz. This package comes with programs for measuring semantic relatedness between words, building lexical chains, and others.

This software package was first used in: Alistair Kennedy, Stan Szpakowicz (2008). "Evaluating Roget's Thesauri".
pdf bib

Sentiment and Product Reviews Data Set

The small data set of positive and negative product reviews from: Alistair Kennedy, Diana Inkpen (2005). "Sentiment Classification of Movie and Product Reviews Using Contextual Valence Shifters"
pdf bib data set