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
Stanford Word Segmenter is a free, open source Java-based tokenization tool for Chinese and Arabic text that integrates token pre-processing, or segmentation. For Arabic, the tool processes text according to the Penn Arabic Treebank 3 standard. For Chinese, users can choose between the Chinese Penn Treebank or Peking University standards.
Analysis
The Stanford NLP Group's Sentiment Analysis tool is a free, web based live demo based on a sentiment analysis treebank, trained to predict the sentiment in movie reviews. Users can test out the sentiment analysis model with their own text in the box provided. The dataset and code is available for download, and the sentiment analysis model is now integrated into Stanford CoreNLP.
Analysis
Data Wrangler is free web-based tool for interactive data cleaning and transformation. It takes raw data and transforms it into data tables for further analysis and cleaning. The results can be exported in a variety of data table formats, including Excel, R, Tableau and Protovis.
Analysis
Protovis is a free, open source tool for composing custom views of data from simple elements such as bars or dots. Marks are defined through dynamic properties to allow inheritance, scales and layouts for simplified visualization construction. This tool uses JavaScript and SVG in order to ensure web-native visualizations. Protovis is no longer under active construction; many of the concepts used in its development have been implemented in its successor, D3.js.
Analysis
STAP (State Transition Network Analysis Procedure) was a program for parsing developed in the 1960s. It could determine correct parsing by following all possible branches until all possibilities permitted by its ruleset were exhausted.
Analysis
STASEL (Stylistic Treatment at the Sentence Level) is a historically important program designed to analyze text. It was intended for language and style instruction, but had research-based applications.
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 list
Holly 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.