Gargantext is a collaborative web platform with the support of the Complex Systems Institute of Paris Ile-de-France  and its partners. It aims at the exploration of sets of unstructured documents. It combines tools from natural language processing, text-mining, complex networks analysis and interactive data visualization to pave the way toward new kinds of interactions with your digital corpora. In few minutes, you will be able to do knowledge maps, collaborative state-of-the-art, portfolio analysis and many other crazy things. Say good-bye to headaches in front of thousands of document to analyze and launch yourself into the Gargantext adventure.

This software is free software, developed by the CNRS Complex Systems Institute of Paris Île-de-France (ISC-PIF) and its partners.

Developers willing to join the Gargantext community are welcome.

History of Gargantext

Gargantext project is a continuation of the TINA project (Chavalarias D. 2009-2011, EU FP7 FET Open 245412) and a more confidential project called WordsEvolution (Chavalarias 2004-2008). The development of Gargantext has benefited from synergies with the whole ecosystem of open source softwares for text and network analytics, including Cortext, NLTK and SigmaJS.

Team, partners and supports

The core team at the origin of Gargantext is :

• David Chavalarias (CNRS/ISC-PIF), principal investigator
• Alexandre Delanoë (CNRS/ISC-PIF), project manager
• Simon Murail (CNRS/ISC-PIF), developer

Host institutions of this project

• CNRS labs ISC-PIF (Institut des Systèmes Complexes de Paris Île de France)
• CAMS (Centre d’Analyse et de Mathématiques Sociales)

This project has received the support from the following institutional partners:

• Ecole des Hautes Etudes en Science Sociales (EHESS)
• Ecole des Mines ParisTech, CSI
• Institut Pasteur
• Institut Mines Telecom

This project has received grant from the following programs

• IDEFI FORCCAST
• Programme CNRS MI Mastodons
• ADEME