A brief textual analysis of a corpus on digital libraries and text mining - Archive ouverte HAL Access content directly
Preprints, Working Papers, ... Year : 2020

A brief textual analysis of a corpus on digital libraries and text mining

Abstract

Over 40 million books have been digitized by Google Books. Libraries around the world have participated in this movement to digitize print heritage. The digital corpora now available contain textual data which today is to be extracted using text mining. Specialised in digitization and digital libraries and with experience in text mining, we wanted to make a state of the art on the subject of text mining applied to digital libraries using text mining technologies themselves. We are indeed wondering about these technologies. Is it developing? Does it work? Are we making discoveries? We have assembled a corpus of metadata and summaries from Google Scholar which seems to be the most exhaustive source on the subject of scientific but also professional literature. We performed textual analyzes using CorTexT, a tool developed by research and higher education in France.
Fichier principal
Vignette du fichier
Digital libraries and text mining.pdf (565.83 Ko) Télécharger le fichier
Origin : Files produced by the author(s)
Loading...

Dates and versions

hal-02862896 , version 1 (09-06-2020)

Licence

Attribution

Identifiers

  • HAL Id : hal-02862896 , version 1

Cite

Mathieu Andro. A brief textual analysis of a corpus on digital libraries and text mining. 2020. ⟨hal-02862896⟩

Collections

INRAE
316 View
57 Download

Share

Gmail Facebook X LinkedIn More