About

This site collects some of the outputs presented in our DH2016 paper on visualizing Jeremy Bentham's manuscripts, besides additional work carried out within Pablo Ruiz's PhD thesis. The references are below:

Estelle Tieberghien¹, Frédérique Mélanie¹, Pablo Ruiz Fabo¹, Thierry Poibeau¹, Tim Causer² and Melissa Terras² (2016). Mapping the Bentham Corpus. In Digital Humanities Conference (DH 2016). Kraków, Poland.

Ruiz Fabo, Pablo¹. (2017). Concept-based and Relation-based Corpus Navigation: Applications of Natural Language Processing in Digital Humanities. PhD thesis. École Normale Supérieure, PSL Research University. Paris, France.

¹LATTICE Lab (CNRS, ENS, Paris 3, PSL, USPC)
²UCL Bentham Project, UCL Digital Humanities

Bentham's manuscripts are currently being transcribed within UCL's Transcribe Bentham project.

The work presented here was based on ca. 17,000 transcripts in English, to which it was possible to assign a date.

Help

• The Search menu provides full-text search to the corpus, and faceted search by date.
• The Lexical Extraction menu displays explanations how the terms used to create the different corpus maps were obtained.
• Under the Corpus Maps menu, the Introduction link describes the different types of corpus maps created, i.e. what we called Static maps, Dynamic maps and Heatmaps.
  The maps described in the thesis by Ruiz Fabo (2017) correspond to the Navigagle and Heatmap types described on the Introduction page just cited.
  Note that, on the Corpus Maps menu, maps which have the word terms in their name are based on Entity Linking, and maps with multiword in their name are based on keyphrase extraction. The number (150 or 250) refers to the approximate number of nodes.