Skip to content
TAPoR Text Analysis Portal for Research

Tools

Sort by Name Rating ↑ Date

Visualization

wordsimilarity (Word 2 Word)

wordsimilarity (Word 2 Word) is a free, open source tool for plotting and visualizing semantic spaces within a corpus. The tool's visualizations assign words to nodes, with similarities marked by edges between nodes of varying strength. The visualizations are designed to be easy to manipulate based on graph data, and the system includes a library of ready-to-use relationship models with an interface for training the models based on a variety of language sources.

Rated 0.0 out of 5.

Visualization

word tree

word tree is a free, web-based tool for generating dynamic word trees from user-supplied texts. Users can paste their text directly in the box provided, enter a URL or Twitter handle in the search bar, or install the bookmarklet into their browser's bookmarks bar to run the tool on their current page. Within the visualization, users can generate trees for any keyword based on search or from a click in the interface, and can reverse the direction of the tree (forward or back from the keyword within the text).

Rated 0.0 out of 5.

Search

WordWanderer

WordWanderer is a free, web-based tool for visualizing and exploring text. It combines search, concordance and word cloud attributes to enable users to explore their texts. Users can paste their own texts into the box provided, or choose from a list of preloaded texts. It includes the ability to include or hide words based on parts of speech, a stop list or a user-provided list, and can display the text based on relative frequency, context or comparison. To view specific words, users can search them or click on them in the visualization.

Rated 0.0 out of 5.

Visualization

Version Variation Visualization

Version Variation Visualization is an interrelated set of free, usable prototypes for visualizing and exploring culturally important works in relation to their world-wide translations. It allows users to explore either the inlcuded corpora or their own texts via time-maps, alignment maps, parallel views or a concordance view accommodating multiple translations in the same viewer. Version Variation Visualization is particularly valuable for its focus on translation and re-translation of text, and its capacity to accommodate and show multiple version of the same text or passage.

Rated 0.0 out of 5.

Search

DfR Browser

The DfR Browser is a free, open source visualization interface for exploring aggragates of articles from the JSTOR database. It uses topic modelling, co-occurrances and document metadata to provide multiple views on the corpus of interest based on topic searches, via several specialized views such as scaled, list and yearly subviews. Users can test the DfR browser via the provided web demo, which incudes a broad selection of pre-loaded topics, or download the source code to use the tool with their own data. The tool's output can be imported into Mallet for further analysis.

Rated 0.0 out of 5.

Search

jsLDA

jsLDA is a free, open source tool for corpus-based in browser topic modelling. Users can test the tool via the provided demo, or download the source code to run on their own system. Users can load any corpus accessible from a URL, and can train the tool on the topics within the corpus via the iteration function. Once jsLDA has been trained to the user's satisfaction, documents can be sorted according to topic and explored based on topic correlations.

Rated 0.0 out of 5.

Natural Language Processing

The Networked Corpus

The Networked Corpus is a free, open source tool for navigating a corpus of plain text files via topic modelling using MALLET. The tool consistes of a Python script, and generates a collection of HTML files that can be explored further via the user's web browser. To use The Networked Corpus, users must have a minimum of Python 2.7.x, NumPy, SciPy and MALLET 2.0.7 installed on their system.

Rated 0.0 out of 5.

Natural Language Processing

Topic Modelling Tool

Topic Modelling Tool is a free, open source tool for Latent Dirichlet Allocation topic modelling with a graphical user interface. The tool learns topics in a user-supplied corpus of plain text files, and outputs results as a CSV file for further analysis.

Rated 0.0 out of 5.

Search

BookLamp Labs: Stream Graph Viewer

BookLamp's Stream Graph Viewer is a tool for viewing where and how much of a story element ('StoryDNA') appears in a book. Books can be searched by title or author, and then graphed for one or several pieces of StoryDNA.

Rated 0.0 out of 5.

Search

BookLamp Labs: StoryDNA Viewer

BookLamp's StoryDNA Viewer is a corpus search tool designed to find all books sharing a user-selected set of characteristics ('StoryDNA'). From the resultant list, users can then view a book's entry in BookLamp to get more information about what characteristics it has, in what proportion, and in relation to other books in the database.

Rated 0.0 out of 5.