Stanford Classifier is a free, open source Java-based machine learning tool that takes data and applies probibalistic classification. It can also give probability distribution information related to class assignments.

WordStat is a commercial software package for content analysis and text mining on natural language text such as interview transcripts. It also includes features for automatic document tagging and classification.

Crawdad is a commercial software package for qualitative data analysis based on natural language processing. It generates a network model of a text and calculates word influence based on its position within the network. It also includes visualization, classification and comparator features. A trial version is available by request.

The Crawdad website is no longer maintained or available. It can still be viewed via the Internet Archive.

Prospéro (PROgramme de Sociologie Pragmatique, Expérimentale et Réflexive sur Ordinateur) is a free text analysis tool aimed at scholars in the Humanities capable of complex analysis on natural language. It permits users to classify and track records or thematic sets within a text or corpus for the purpose of exploration, analysis and comparison. It identifies places in a text that display uncertainty, controversy, criticism, and enables the user to establish rule and meta-rules to separate factual statements from views and interpretations. Prospéro is particularly designed for complex cases composed of large texts containing heterogenous discourse.

Weka provides machine learning algorithms in Java for data mining and predictive modeling tasks. These algorithms can either be incorporated into other Java code or called from the Weka Workbench, a GUI environment.