Deployment of the text-mining tool Bilbo on OpenEdition Books
Bilbo identifies the bibliographic references in the documents contained in a book (chapters, introductions, bibliography, etc.) and then semantizes the different elements contained in each reference. It then identifies DOIs (digital object identifiers) corresponding to these references, and, where these exist, adds them to the end of the reference as a hyperlink. This makes it possible to directly access the cited resource. Developed by OpenEdition Lab, Bilbo has now been launched on the platform.
How does Bilbo work?
Bilbo (Bibliographical Robot) is a piece of software that is able to detect, identify, analyze and code the bibliographic references contained in articles. Using text-mining and machine-learning techniques, Bilbo identifies the authors’ first and surnames, the title, the publisher, and the year and place of publication of each bibliographic reference.
The first version of Bilbo focuses on the general bibliography of documents. In the second stage of its development, Bilbo’s capacity to identify bibliographic references will be deployed in a document’s footnotes. Finally, in the third stage of its development, Bilbo should be able to identify the implicit references contained in the body of a text.
Bilbo will regularly analyze the same bibliographies as the algorithm becomes more advanced, but also because every day thousands of publications obtain a DOI.
Automatically identified references
Once Bilbo has identified the author and the title, it can consult the CrossRef search engine. CrossRef is the official DOI registry, whose database contains millions of academic references. Bilbo can also retrieve DOIs where they exist, and add them to the document’s bibliography.
Once it has identified the reference, Bilbo is able to enrich it with supplementary data and display it in different formats. Readers consulting a document from a library or institution that has subscribed to one of the OpenEdition Freemium programmes will be able to download the references for which Bilbo has found a DOI in APA, MLA and Chicago formats. The list of subscribing libraries and institutions can be found on this page: <http://cleo.openedition.org/pilotage/abonnes>
Who made Bilbo?
Developed by OpenEdition Lab, Bilbo is a R&D programme launched in 2011 which aims to develop reading, writing and browsing features as will a recommendations system. Two teams are working together closely on this project: the OpenEdition team and the CNRS-affiliated Information Science and Systems Laboratory (LSIS) at Aix-Marseille University. The initial funding has been provided by a Google Grant for Digital Humanities.
- Recommendations and information about Bilbo for editorial teams on the Maison des Revues (in French): <http://maisondesrevues.org/680>.
- The OpenEdition Lab research blog, which gives updates on how Bilbo has developed (in French): <http://lab.hypotheses.org/category/bilbo-bibliographical-robot>.
- A description of how DOIs: <http://maisondesrevues.org/253>.
Cite this blog post
Daša Radovič (2016, July 7). Deployment of the text-mining tool Bilbo on OpenEdition Books. Open Electronic Publishing. Retrieved March 1, 2024, from https://doi.org/10.58079/si8b