• Reduce text

    Reduce text
  • Restore text size

    Restore text size
  • Increase the text

    Increase the text
  • Print

ue GC IE - Picardie © Aline Waquet

CorTexT, a textual analysis platform

Updated on 03/22/2017
Published on 02/13/2013

The semantic and statistical analysis of textual data is a major stake of the Sociology contemporaneous development. SAE2 and SAD divisions develop and offer two types of tools at the searchers’ disposal in this field.


Context and stakes

Providing a still increasing number of resources on the network is a privileged field of studies for textual analysis. Tracking scientific activities and innovation in scientific databases, patent-bases and project bases gives detailed information to scientific production.

Facing these masses of more or less structured data, the scientific works in human and social sciences on research and innovation must, from now on, be confronted with the analysis of big heterogeneous corpus of data to both characterize and assess the extent of the phenomena that they study.

Answers given by the platform

Both these demands require the use of research and tools developed in the various scientific and technical fields to understand the mechanisms implied: automatic language process, information extraction, knowledge engineering, network sociology, scientometry, controversy analysis and semiotics.

To back up the work of analysis and interpretation of the problematic met within the Francilian Institute (Research, “Innovation and Society”), Ifris developed a technological platform called CorTexT focusing on the treatment of major textual corpus with intention of research, expertise and training. CorTexT is a project supported by the Lisis Inra, Ifris unit.

The objective is to provide Ifris partner teams with tools, treatment chains, procedures and methods to help searchers treat, characterize, analyse and quantify classified textual data.
Flagship project of the platform, CorTexT Manager allows users of the platform to manage their projects and analyze their data sets directly online. This application enables to upload data sets from disparate sources, and initiate treatments (scripts) to perform remote analyses/maps of primary data. A private space allows users to launch and test on their own chains of treatments before possibly making results public.


CorTexT Website

CorText Manager

CorText Manager is an online platform for data analysis specifically designed for research in digital humanities.

It is entirely open: https://managerv2.cortext.net and offers capacities for analyzing textual content, mapping medium-scale and large-scale corpora, unveiling dynamical patterns in a collaborative web interface. It can handle a large diversity of data sources (press database, scientific platforms, etc.) and formats (spreadsheet, isi/pubmed files, etc.) and offers a wide range of analytical tools to analyze them (NLP, network analysis, word embedding, etc.)

See the documentation website and video tutorials for more details.