Renaissance Knowledge Network - Textual Analysis

TextDNA

djpowell — Thu, 15 Jan 2015 17:00:48 +0000

TextDNA is a free tool designed to facilitate large-scale analysis projects of linguistic data. Using the Sequence Surveyor system, "TextDNA supports the comparison of ordered sets of linguistic data by visualizing the sequences as colored rows and elements within the set as colored blocks within each row". TextDNA identifies pattens within a dataset and enables users to compare across corpora. TextDNA is compatible with the data stored in Google N-Grams.

Category:

Visualization

Textual Analysis

URL:

http://graphics.cs.wisc.edu/Vis/SequenceSurveyor/TextDNA.html

MONK (Metadata Offer New Knowledge)

djpowell — Thu, 15 Jan 2015 16:48:46 +0000

MONK (Metadata Offer New Knowledge) is a digital environment for humanities scholars. It is desgined to assist with the discovery and analysis of patterns within texts, incorporating full text content from corpora such as ECCO, EEBO and Early American Fiction directly into the tool. The MONK Workbench is the primary environment, permitting users to create worksets, perform analytics and save their results. In addition, the MONK workbench can be used in conjunction with the Flameco faceted browser and Zotero. [Credit to TAPoR for this exceptional annotation]

Category:

Visualization

Textual Analysis

URL:

http://quest.library.illinois.edu/monk/project/downloads/

PDF Extract

ReKN Admin — Thu, 18 Dec 2014 20:01:53 +0000

PDF Extract is an open source set of tools that "allow you to identify and extract the individual references from a scholarly journal article". PDF Extract utilizes the visual clues present in an academic article via formatting to "identify semantically important areas of a PDF" and facilitate appropriate extraction of material. PDF Extract was created to assist "small and medium-sized publishers to meet CrossRef’s linking requirements and to participate in CrossRef’s Cited-by service".

Category:

Textual Analysis

URL:

http://labs.crossref.org/pdfextract/

Tesseract

ReKN Admin — Thu, 18 Dec 2014 19:46:36 +0000

Tesseract is a free raw OCR engine originally developed by HP Labs and now maintained by Google. It works with the Leptonica Image Processing Library, and is capable of reading a variety of image formats. It can convert images to text in over 40 languages. [Credit to TAPoR for this exceptional annotation]

Category:

Textual Analysis

URL:

http://code.google.com/p/tesseract-ocr/

PhiloLogic

ReKN Admin — Thu, 18 Dec 2014 19:45:24 +0000

PhiloLogic is a "primary full-text search, retrieval and analysis tool" developed by the University of Chicago. PhiloLogic leverages the "wide array of XML data specifications and the recent deployment of basic XML processing tools provides an important opportunity for the collaborative development of higher-level, interoperable tools for Humanities Computing applications". Recognizing that the TEI community does not suit a one-size-fits-all approach, PhiloLogic focuses on the development of "specialized, interoperable tools" that can be implemented for end-user applications in a cost-effective manner. PhiloLogic is committed to the open source development of these applications: drawing on a wide range of technical abilities and expertise that is "not well supported by the commercial sector".

Category:

Textual Analysis

URL:

https://sites.google.com/site/philologic3/

Lexomics

ReKN Admin — Thu, 18 Dec 2014 19:41:35 +0000

Lexomics is a text mining software that leverages computational techniques and statistical analysis to answer literary questions. Lexomics searches through texts for word patterns and determines how different parts of a work relate to one another. The web-based Lexomics tools "enables you to "scrub" (clean) your unicode text(s), cut a text(s) into various size chunks, manage chunks and chunk sets, tokenize with character- or word- Ngrams or TF-IDF weighting, and choose from a suite of analysis tools for investigating those texts". The program uses dendrograms - a visual representation of word frequency in text - to analyze to relationship between a text and its author, source, other similar texts. Other visual representations include word clouds and bible visualizations that also represent word frequencies and ratios in a text or set of texts.

Category:

Textual Analysis

URL:

http://wheatoncollege.edu/lexomics/

Brat Rapid Annotation Tool

ReKN Admin — Thu, 18 Dec 2014 19:41:04 +0000

"Brat is a web-based tool for text annotation". Brat is particularly designed for structured annotation where the textual notes are fixed and can be easily categorized in order to aid automated computer processing and interpretation. Brat facilitates four types of fixed annotations: text span annotations, suitable for creating categorical annotations for entities; relation annotations, suitable for drawing simple relationships between entities; n-ary associations, that link annotation to specific roles; and finally normalization annotations, that associate internal annotations with external resources. All annotations can be further explained and categorized using attributes that describe the base annotation - similar to how adjectives modify a noun. Brat's user-friendly and intuitive features include comprehensive visualization, editing, integration with resources, annotating in any language, and easy export in multiple formats.

Category:

Textual Analysis

URL:

http://brat.nlplab.org/

GeoNames

ReKN Admin — Thu, 18 Dec 2014 19:39:07 +0000

GeoNames is massive geographical database that contains "over 10 million geographical names and consists of over 9 million unique features". GeoNames integrates geographical data with place names in various languages, physical features (area, elevation, longitude/latitude), and social statistics (population, currency, postal codes, national flag). GeoNames is a collaborative project that encourages user participation by allowing users to "manually edit, correct and add new names using a user friendly wiki interface". GeoNames is a worldwide initiative that is managed and maintained by ambassadors around the globe who lend their help and expertise to the project's development.

Category:

Textual Analysis

URL:

http://www.geonames.org/

CATMA: Computer Aided Textual Markup & Analysis

ReKN Admin — Thu, 18 Dec 2014 19:37:29 +0000

CATMA is a "practical and intuitive tool for literary scholars, students and other parties with an interest in text analysis and literary research". CATMA facilitates efficient literary analysis by "helping perform many of the procedures [...] that normally have to be carried out entirely manually". CATMA's key features include advanced search in the text, visualization of the distribution items of interest, the possibility of analysis a whole corpora of texts in one step, easy toggling between modules, and freely producible Tagsets. "CATMA integrates three functional, interactive modules: the Tagger, the Analyzer and the Visualizer": the Tagger implements of graphic interface for textual mark-up, the Analyzer has Query Builder that executes complex and powerful data inquires, and the Visualizer offers a wide range of charting possibilities that cater to the user's needs and preferences.

Category:

Textual Analysis

URL:

http://www.catma.de

Scrapy

ReKN Admin — Thu, 18 Dec 2014 19:36:55 +0000

Scrapy is "an open source and collaborative framework for extracting the data you need from websites. In a fast, simple, yet extensible way". Scrapy is a site crawling application that is structured to retrieve structured and useful data from websites for the purposes of data mining, information processing or historical archiving. Scrapy facilitates the data extraction from nearly any website by allowing user to write their own Spiders - directions for locating and retrieving website data. Scrapy is fast, powerful, easily extensible, and yet entirely simple. Scrapy is a free, multi-platform program that is compatible with Windows, Mac, and Linux.

Category:

Textual Analysis

URL:

http://scrapy.org/