TXM is a free, open source text corpus analysis environment. Its features include concordance, collocate search, frequencies based on the CQP full text search engine and statistical functions based on R packages. It can export results in CSV, XML or SVG format, and runs as a standalone desktop application in Windows, OS X and Linux environments, or as a web portal (download the leaflet for more).

Mallet is a Java based library and command line framework that provides statistical and machine learning tools for use with natural language processing.

Overview is a free, web-based tool for document mining. Developed by and for journalists, Overview is also broadly applicable to other corpus-based research applications. Aside from providing advanced search features such as regular expressions and fuzzy matching, Overview automatically sorts documents according to topic and provides a fast visualization and reading interface. You can apply tags to search results, individual documents, or entire topics to track what you've found, then export the entire document set with its tags to perform further processing or create visualization. It’s been used for qualitative research, social media conversation analysis, legal document review, digital humanities, and more. 

PolyMeta is a metasearch engine that displays the search results in the form of clusters and images. The results are sorted according to source and category.

iBoogie is a clustering search engine that puts documents with similar content or with related topics into the same group. Each group is assigned a label based on the content of the documents. The results are presented to the user in a hierarchy of topics (clusters) for browsing.

Cluuz is a search engine that shows not only links to related pages, but also entities (people, companies, organizations) and images that are extracted from within the search results. In addition to the results, Cluuz displays a tag cloud of the most relevant entities extracted from returned results, as well as a semantic graph view of a cluster of terms.

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.