Digitize analog text into manipulable web objects. Digitized objects can be annotated and analytics can be performed on the text data.
Textension
The Textension platform automatically adds visualizations and natural language processing applications to analog texts, using any web-based device with a camera. After taking a picture of a particular page or set of pages from a book or uploading an existing image, our system builds an interactive digital object that automatically inserts modular elements in a digital space. Leveraging the findings of previous studies, our framework augments the reading of analog texts with digital tools, making it possible to work with texts in both a digital and analog environments.
Citation Context Surfer
A tool aimed at giving users a in-depth look at citations and their surrounding context. Using customizable rulesets new trends can be found and explored.
Citation Context Surfer
Bibliometric experts use statistical analysis of natural language texts to provide a quantitative view of academic literature. Bibliometric techniques, such as citation analysis, are often used by funding agencies to understand and evaluate the publishing results of grant money distribution. While this field of scholarship in general, and citation analysis in particular, have been studied extensively, there still remains a lack of tools and techniques for evaluating the surrounding natural language context of individual citations on the network scale. The goal of this project is to aid in the identification of language patterns as they occur across a large corpus of academic texts, allow users to create and edit rule sets for evaluation, and then use vector space models to suggest expansions of the user defined natural language rules. Although originally developed for citation analysis, the tool can be customized for any number of categories and rules that apply to a given domain problem.
Synonymic Search
Perform OCR topic and text analysis using a visual interface. Documents for analysis are sourced from the Érudit database.
Synonymic Search
The synonymic search project is aimed at humanities researchers trying to ask more intelligent questions of document corpora. Our stakeholders identified to us that as document collections get larger, there is an inverse relationship to their ability to find what they are looking for. In the past this has been addressed with novel methods of query generation, but we wanted to offer a different method for building intelligent queries. The synonymic search uses a navigable visual thesaurus to allow for query extensions. Users can upload documents, which me model and then direct to similar matches, but can also input keywords and then navigate a hierarchy of English and French synonyms that are categorically related. The overall goal of this project was to allow for dynamic query generation especially when the user is not completely certain of what they are searching for. We imagine that through this interface humanities researchers can augment their search process to find more relevant results in large document corpora.
Erudit Collaboration Maps
Mapping the transfer of knowledge in the Érudit corpus. Allows for filtering by co-authorship in journals or by the institution, date, author or paper title.
Erudit Collaboration Maps
The collaboration maps project is a visualization framework that uses metadata from the Erudit corpus to show the collaborative worldwide academic networks that make up the document corpora. Users can filter based on multiple factors including author, date, academic institution, and journal. Several levels of granularity allows users the ability to investigate how and when the corpus was created. Used in concert with the rest of the corpus analysis suite, the collaboration maps give a full view of academic partnerships and their geography.
Erudit Journal Matcher
Perform OCR topic and text analysis using a visual interface. Newspapers for analysis are sourced from the Érudit database.
Erudit Journal Matcher
In partnership with Erudit, we were looking for a way to align researchers with the journals that they were most related to their work within the Erudit corpus. Users can upload a document in our document modeller and then they are directed to the journals that are most like their uploaded work. This project was designed as an alternative way for users to discover journals that will interest them can facilitate traffic at the journal level for erudit clients.