Analysis
Mallet
Mallet is a Java based library and command line framework that provides statistical and machine learning tools for use with natural language processing.
For researchers who work with text
TAPoR catalogues concordancers, annotators, topic models, stylometry packages, and visualization environments. Every record notes the platform, the license, and what the tool is actually good for.
Filter by the type of analysis.
Analysis
Mallet is a Java based library and command line framework that provides statistical and machine learning tools for use with natural language processing.
Analysis
NLTK 2.0 (Natural Language Tooklt) is a free, open source collection of Python modules, linguistic data and documentation for research and development in natural language processing and text analytics, with distributions for Windows, Mac OS X and Linux. It offers a platform for building Python programs to work with human language data, and integrates a guide to programming fundamentals.
Analysis
NodeXL is a free, open source tool for generating and exploring network graphs from Microsoft Excel files. It is particularly suited to data from social media sources, and includes the ability to directly import data from Twitter, YouTube, Flickr and email, with additional plugins available for gathering data from Facebook, Microsoft Exchange, wikis and URLs. The tool generates visualizations that can be adjusted, zoomed and filtered, with additional features for vertex grouping, graphing metric calculations, and automating tasks. NodeXL can both import and export data in GraphML, Pajek, UCINet and matrix formats.
Analysis
Textalyser is a free web-based text analysis tool offered by the Bernhard Huber Internet Engineering Company. Users can paste text into the provided entry field, upload a file or provide a URL for analysis. Textalyser provides detailed statistics on the text to determine subject, analyse word groupings, determine keyword density and deterimine the most prominent phrase. The Textalyser website is no longer available as of late 2014. It has been captured by the Internet Archive, and can still be viewed there.
Analysis
TextArc is a free visualization tool that represents an entire text on a single page. It has elements of an index, concordance and summary all in one place, encouraging the viewer to use its juxtapositions to uncover meaning. The web-based applet is preloaded with thousands of text collected from Project Gutenberg. Note: TextArc was designed for browsers circa 2002 and requires Java SE 6 to run.
Analysis
Parses text tagged by the Stanford named entity recognizer in order to collect and analyze mentions of locations. Also incorporates the Google API in order to geocode those locations and, ultimately, mark them on a map. This code was written in an IPython Notebook, so the code below is actually a collection of scattered code snippets. Please see the repository on github for full details and documentation, or the Methods Common recipe ( http://methodi.ca/recipes/mapping-locations-corpus ) for a step-by-step guide. NOTE: Users will be required to acquire their own Google API key, store it in a text file, and then point the code to that text file. Instructions can be found in the IPython Notebook itself. Search for "api_key_file" to find the line in code that needs to be changed.
Week of 1 Nov – 7 Nov
Three tools from the catalogue, each rated at least 3 stars. A new set appears each Sunday.
Curated list created by experience authors in the fields.
Geoffrey Rockwell
Not all Voyant tools show up in the default view or skin. Here is a list of some of the other tools worth trying.
4 tools
View listHolly Pickering
Interested in audio production and editing? Here are a few programs that can help you get on your way. Some of them are free, some not, but all are helpful and useful.
3 tools
View list
Jason Bradshaw
This list compiles a suite of tools that make up Kynan Ly's Text Analysis for Twitter Research (TATR) Library. Recipes to these notebooks can be found on methodi.ca
6 tools
View list1321
Tools catalogued
15
Curated lists
22
Analysis types
671
Community reviews
Researchers, power users, and students will soon be able to contribute tools, share reviews, and curate lists around their own work.