Skip to content
TAPoR Text Analysis Portal for Research

Tools

Sort by Name Rating Date ↑

Search

AntConc

AntConc is free concordance software. It is multi-platform and easy to deploy and use. AntConc is part of a suite of related tools for text processing and analysis, including applications for parallel corpus analysis, word profiling, PDF to text conversion, text structure analysis, detecting and converting character encodings, Japanese and Chinese segmenter and tokenizer, wordclass tagger, and spelling variant anaysis. The developer is currently drafting a more explicit licence for the use of the software.

Rated 0.0 out of 5.

Search

Laurence Anthony: AntWordProfiler

AntWordProfiler is a free tool for word profiling. For each word in a document, it will generate the base form and a list of possible related words, provide statistics and frequency data and list word types. It can also process files separately or as a batch.

Rated 0.0 out of 5.

Natural Language Processing

CLAWS Part-of-Speech Tagger

CLAWS (Constituent Likelihood Automatic Word-tagging System) is a free parts-of-speech tagging tool from Lancaster University. It has been continuously developed since the 1980s, has consistently achieved 96-97% accuracy, and has been applied to the over 100 million word British National Corpus. This tool is available for download in addition to an on-line 'trial' version.

Rated 0.0 out of 5.

Visualization

CHNM: Timeline Builder (Beta)

Timeline Builder is a free tool for creating and maintaining interactive, Flash-based timelines for viewing on the web. Basic text formatting and links to other resources can be added through basic HTML. This tool requires registration through the web page.

Rated 0.0 out of 5.

Visualization

IBM: Many Eyes

Many Eyes is a free collection of data visualization tools enabling exploration and discussion of the data. Users who post comments on a visualization may also save their view for others to see in conjunction with their comment. Visualizations can be created from the data sets loaded into the site, or one can upload a new dataset for use. Note : Uploaded datasets are shared with the site.

Rated 0.0 out of 5.

Visualization

INKE: Dynamic Table of Contexts

Dynamic Table of Contexts is a free tool for supplementing a traditional table of contents for a text. It allows users to add or subtract index items based on XML encoding. This tool requires the creation of an account.

Rated 0.0 out of 5.

Visualization

Mandala Browser

Mandala Browser is a rich-prospect browsing interface for exploring a data set in .txt, .rft, .pdf, .csv or .xml format. Searches can be constrained by columns or fields. A version of this tool is also available in the Voyant toolset.

Rated 0.0 out of 5.

Uncategorized

Voyant Skin Builder

Voyant Skin Builder is a function within the larger Voyant toolset that enables users to create a customized selection and arrangement of tools with which to analyze a text. These custom skins can be saved or exported for future use.

Rated 1.0 out of 5.

Search

Visualizing Literature: Words in Context

Words in Context, from the Visualizing Literature toolset, allows users to select a text from Visualizing Literature's list of grade school curriculum exemplar creative commons texts and perform a keyword search. The results of the search show all instances of the word, with all surrounding text found on the same line for context. All texts are searchable, and can be sorted by writer, title, publication year, grade level, availability for analysis and availablility of a direct link to the text. Please note that, as this toolset is still in beta, the selection of texts is currently limited, though over 300 texts are forthcoming. As of 2014, this toolset is no longer available as the website has been taken down. It may still be viewed via the Internet Archive.

Rated 0.0 out of 5.

Visualization

Visualizing Literature: Sentiment

Sentiment, from the Visualizing Literature toolset, allows users to select a text from Visualizing Literature's list of grade school curriculum exemplar creative commons texts and graph it for keywords suggestive of sentiment. All texts are searchable, and can be sorted by writer, title, publication year, grade level, availability for analysis and availablility of a direct link to the text. Please note that, as this toolset is still in beta, the selection of texts is currently limited, though over 300 texts are forthcoming. As of 2014, this toolset is no longer available as the website has been taken down. It may still be viewed via the Internet Archive.

Rated 0.0 out of 5.