Skip to content
TAPoR Text Analysis Portal for Research

Tools

Sort by Name ↓ Rating Date

Annotating

UVic Image Markup Tool

The UVic Image Markup Tool is a free tool for annotating images and storing the annotations in XML files from the University of Victoria's Humanities Computing and Media Centre. Its interface is designed for users without prior XML experience with additional functions for users familiar with XML, and supports multiple languages. The Image Markup Tool is available for Windows, and will also run in Linux with Wine.

Rated 0.0 out of 5.

Natural Language Processing

Using Regular Expressions to Clean Up Web Pages

A beginner's notebook on using Regex to strip website content of tags.

Rated 0.0 out of 5.

Natural Language Processing

Using Regular Expressions to Clean a Text

Techniques on using regular expressions to clean up a text for textual analysis.

Rated 0.0 out of 5.

Collaboration

Ushahidi Platform

Ushahidi is a software for information collection, visualization and interactive mapping, to build tools for democratizing information, increasing transparency and lowering the barriers for individuals to share their stories. It has been used for election monitoring, crisis and emergency response, civil society, city/community building, arts and even where to find the best burger. Specific tools: Crowdmap: A simple map-making tool, built on an open API, that allows for collaborative mapping Swiftriver: Curate real-time data and analysis from a variety of sources, including social media streams CrisisNET: A consolidated source of global crisis data Ping: Two-way multichannel group alert during an emergency SMSSync: Create a two way gateway with an Android phone and local SIM anywhere in the world BRCK: Supports connectivity in remote locations, self-powered, mobile WiFi device

Rated 0.0 out of 5.

Analysis

URICA! II

URICA! II (User Response Interactive Collation Assistant) was an interactive collation program for the Macintosh. It semi-automated text collation, and assisted text comparison by 'tagging' variants or automatically reconciling small differences. URICA! II built upon the foundation of URICA!, the first iteration of the program.

Rated 0.0 out of 5.

Content Analysis

Unlock Text

Unlock Text is a powerful geoparser that can search text hosted on the web in txt or html format for references to locations. These locations are then returned ready for use in your results page, web map or any other application. The Unlock Text API provides access to two parsers, the Edinburgh Geoparser from the Edinburgh Language Technology Group and the CLAVIN parser.

Rated 0.0 out of 5.

Visualization

University of Maryland HCI Group: FeatureLens

FeatureLens is a free tool for visualizing and exploring patterns in text collections. This tool integrates the results of text-mining algorithms, and can assist in finding frequent words or ngrams, enabling the discovery of fuzzy repetition patterns. In addition, the tool will recommend features based on particular pattern types identified in the text.

Rated 0.0 out of 5.

Analysis

UNICORN

UNICORN was a concording system developed in the 1970s. It was developed in FORTRAN IV to replace more restricted programs at at the University of Colorado at Boulder, and could process most machine-readable texts.

Rated 0.0 out of 5.

Analysis

UNICON

UNICON was a concordance generator written in FORTRAN IV and available in the 1960s. It was available first for the IBM 7094, and for IBM 1410/7090 computers after 1970.

Rated 0.0 out of 5.

Natural Language Processing

Umigon

Umigon is a tool used for the sentiment analysis of texts. It is one of the tools of the Nocode app which is a suite of text analysis tools. Results can be exported in Excel or CSV format for further analysis. It was formerly a stand alone web-based and open-source tool for the sentiment analysis of tweets. From a person's Twitter handle, Umigon retrieved that account's tweets and processed them for sentiment while accounting for factual statements (ex: "I hate war" will be classified has negative, and "war in Syria" will be classified as neutral). Tweets could also be pasted manually in the entry box provided. Beyond sentiment analysis, Umigon could identify characteristics such as whether the tweet contains a question, whether it contains possible promotional/commercial subject matter, or temporal indicators based on tense. The developer of this application can be reached on Twitter. As of April 2022, Umigon has been archived after a long period without new developments.

Rated 0.0 out of 5.