Cortext platform
At Cortext, our goal is to empower researchers in the social sciences and humanities by promoting advanced qualitative-quantitative mixed methods. Our primary focus is on studies about the dynamics of science, technology and innovation, and about the roles of knowledge and expertise in societies.
We understand the move towards digital humanities and computational methods not as addressing a technological gap for the social sciences, but rather as entailing entirely new assemblages between its disciplines and those of modern statistics and computer sciences. We work to tackle ever more complex research problems and deal with the profusion of new and diverse sources of information without losing sight of the situatedness and reflexivity required of studies of human societies.
Cortext is hosted by the LISIS research unit at Gustave Eiffel University, and was launched by French institutes IFRIS and INRAE, receiving their continued support.
Cortext Manager
Cortext Manager is our current main attraction, a publicly available web service providing data analysis methods curated and developed by our team of researchers and engineers.
You upload a textual corpus in order to analyse its discourse, names, categories, citations, places, dates etc, with methods for science/controversy/issue mapping, distant reading, document clustering, geo-spatial and network visualizations, and more.
You can jump straight to Cortext Manager and create an account, but we strongly suggest taking a look at the Documentation and Tutorials as you start your journey.
Latest journal articles employing our instruments
PhD Theses
2017
Ruiz, Pablo
PSL Research University, 2017, (HAL Id : tel-01575167 , version 2).
@phdthesis{Ruiz2017,
title = {Concept-based and relation-based corpus navigation : applications of natural language processing in digital humanities},
author = {Pablo Ruiz},
url = {https://tel.archives-ouvertes.fr/tel-01575167v2},
year = {2017},
date = {2017-06-23},
urldate = {2017-06-23},
school = {PSL Research University},
abstract = {Social sciences and Humanities research is often based on large textual corpora, that it would be unfeasible to read in detail. Natural Language Processing (NLP) can identify important concepts and actors mentioned in a corpus, as well as the relations between them. Such information can provide an overview of the corpus useful for domain-experts, and help identify corpus areas relevant for a given research question. To automatically annotate corpora relevant for Digital Humanities (DH), the NLP technologies we applied are, first, Entity Linking, to identify corpus actors and concepts. Second, the relations between actors and concepts were determined based on an NLP pipeline which provides semantic role labeling and syntactic dependencies among other information. Part I outlines the state of the art, paying attention to how the technologies have been applied in DH. Generic NLP tools were used. As the efficacy of NLP methods depends on the corpus, some technological development was undertaken, described in Part II, in order to better adapt to the corpora in our case studies. Part II also shows an intrinsic evaluation of the technology developed, with satisfactory results. The technologies were applied to three very different corpora, as described in Part III. First, the manuscripts of Jeremy Bentham. This is a 18th–19th century corpus in political philosophy. Second, the Poli Informatics corpus, with heterogeneous materials about the American financial crisis of 2007–2008. Finally, the Earth Negotiations Bulletin (ENB), which covers international climate summits since 1995, where treaties like the Kyoto Protocol or the Paris Agreements get negotiated. For each corpus, navigation interfaces were developed. These user interfaces (UI) combine networks, full-text search and structured search based on NLP annotations. As an example, in the ENB corpus interface, which covers climate policy negotiations, searches can be performed based on relational information identified in the corpus: The negotiation actors having discussed a given issue using verbs indicating supportor opposition can be searched, as well as all statements where a given actor has expressed support or opposition. Relation information is employed, beyond simple co-occurrence between corpus terms. The UIs were evaluated qualitatively with domain-experts, to assess their potential usefulness for research in the experts’ domains. First, we payed attention to whether the corpus representations we created correspond to experts’ knowledge of thecorpus, as an indication of the sanity of the outputs we produced. Second, we tried to determine whether experts could gain new insight on the corpus by using the applications, e.g. if they found evidence unknown to them or new research ideas. Examples of insight gain were attested with the ENB interface; this constitutes a good validation of the work carried out in the thesis. Overall, the applications’ strengths and weaknesses were pointed out, outlining possible improvements as future work.},
note = {HAL Id : tel-01575167 , version 2},
keywords = {},
pubstate = {published},
tppubtype = {phdthesis}
}
Kachani, Alexandra Struk
La construction des politiques de l'autisme : concurrence des acteurs et arbitrage de l'Etat PhD Thesis
Université de Bordeaux, 2017, (HAL Id : tel-01734867 , version 1).
@phdthesis{Kachani2017,
title = {La construction des politiques de l'autisme : concurrence des acteurs et arbitrage de l'Etat },
author = {Alexandra Struk Kachani},
url = {https://tel.archives-ouvertes.fr/tel-01734867/},
year = {2017},
date = {2017-01-01},
urldate = {2017-01-01},
school = {Université de Bordeaux},
abstract = {Cette thèse interroge les processus de construction de la réalité́ à l’oeuvre lors de l’émergence duproblème politique de l’autisme. Un mécanisme largement bottom-up s’est imposé, sousl’impulsion déterminante de « coalitions de causes » (notamment celle des associations deparents) qui ont opéré un véritable travail de capacitation et d’expertisation pour s’approprier destravaux de recherche, contester la légitimité du pouvoir médical, revendiquer des droits auprès despouvoirs publics en utilisant différentes armes, médiatiques, et judiciaires principalement.Expliquer pourquoi l’autisme est devenu un problème politique au milieu des années 1990 jusqu’àêtre reconnu « grande cause nationale » en 2012 suppose d’analyser, sur un temps long, lesprocessus qui changent le statut de l’autisme (d’un problème familial d’abord, social ensuite,politique enfin) et en définissent les traitements publics possibles. },
note = {HAL Id : tel-01734867 , version 1},
keywords = {},
pubstate = {published},
tppubtype = {phdthesis}
}
Technical Reports
2017
Bispo, Antonio; Gabrielle, Benoît; Makowski, David; Akkari, Monia El; Bamière, Laure; Barbottin, Aude; Bellassen, Valentin; Bessou, Cécile; Dumas, Patrice; Gaba, Sabrina; Wohlfahrt, Julie; Sandoval, Mélanie; Perchec, Sophie Le; Réchauchère, Olivier
Agence de l'Environnement et de la Maîtrise de l'Energie 2017.
@techreport{Bispo2017,
title = {Effets environnementaux des changements d'affectation des sols liés à des réorientations agricoles, forestières, ou d'échelle territoriales : une revue critique de la littérature scientifiques},
author = {Antonio Bispo and Benoît Gabrielle and David Makowski and Monia El Akkari and Laure Bamière and Aude Barbottin and Valentin Bellassen and Cécile Bessou and Patrice Dumas and Sabrina Gaba and Julie Wohlfahrt and Mélanie Sandoval and Sophie Le Perchec and Olivier Réchauchère},
url = {https://hal.archives-ouvertes.fr/hal-01562314/},
doi = {10.15454/5gxzv-a76},
year = {2017},
date = {2017-01-01},
urldate = {2017-01-01},
pages = {68},
institution = {Agence de l'Environnement et de la Maîtrise de l'Energie},
abstract = {Effets environnementaux des changements d'affectation des sols liés à des réorientations agricoles, forestières, ou d'échelle territoriales : une revue critique de la littérature scientifiques. Synthèse du rapport d'étude.},
keywords = {},
pubstate = {published},
tppubtype = {techreport}
}
Workshops
2017
Cointet, Jean-Philippe; Abdo, Alexandre Hannud
2017.
@workshop{cointet2017capturing,
title = {Capturing Oncology Dynamics from Textual Content of Conference Abstracts: Word Embedding and Stochastic Block Models},
author = {Jean-Philippe Cointet and Alexandre Hannud Abdo},
url = {http://www.ixxi.fr/agenda/seminaires/understanding-the-dynamics-of-science-an-interdisciplinary-workshop?searchterm=Understanding+the+dynamics+of+science},
year = {2017},
date = {2017-01-01},
urldate = {2017-01-01},
abstract = {The availability of social data drives many scientists from the formal sciences (computer science, physics…) into the quantitative analysis of social systems. One early example of this trend is « scientometrics », the study of science’s structure and evolutions using large bibliographic datasets. Recent topics of interest in the field include the development of new formal tools to provide insights on the nature, structure and dynamics of scientific communities « bottom-up », i.e. without using predetermined classification schemes. Many scientists develop also interactive visualization platforms, or compare the pictures obtained by quantitative and qualitative methods.},
keywords = {},
pubstate = {published},
tppubtype = {workshop}
}
NotesVIEW ALL
-
Long trends on twitter: intertemporal clusters combining hashtags and terms on Scientometrics, Altmetrics, Bibliometrics and Science Of Science
Long trends on twitter: inter-temporal clusters combining hashtags and terms, for all tweets on Scientometrics, Altmetrics, Bibliometrics and Science Of Science from Jan. 2017 to dec. 2021, on a semester base. Query used to extract tweets: lang:en (Scientometrics OR “ScienceOfScience” OR “Science Of Science” OR “Altmetrics” OR “altmetric” OR “bibliometrics” OR “bibliometric” OR “citation metrics” […]
-
Présenter CorTexT Manager en 2 minutes
Cortext Manager est une application web construite par des chercheurs et par des ingénieurs à destination de chercheurs en sciences humaines et sociales, au plus près des questions portées par les chercheurs qui nous entourent et par notre communauté d’utilisateurs. Cette application web peut produire un grand nombre d’analyses différentes qui ont trait aux champs […]
-
Analysis of the scientific production that mentioned the use of CorText Manager
There are two ways to understand what CorTexT Manager is. The first one is to look at what has been achieved in terms of methods, tools and therefore lines of code. The second one is studied below, by analyzing (here with CorTexT Manager) what academic users have published using… CorTexT Manager. Our study of the […]
-
10 years of CorText Manager v2
It took us more than 10 years to come with CorText Manager version 2 as it is now! Behind the scenes CorText Manager begun with a first version in 2009. More than thirty contributors has worked directly or indirectly on the two versions, year after year. All the ideas, inspirations, all this accumulation of pieces […]
-
RISIS Training: Thematic and spatial analysis of technologies using CorText Manager and RISIS patent database
One of the best CorText Manager training courses was organized and offered by the RISIS project. Here is the program of this training which lasted 3 days: Monday 08/11/21 14h-16h30: Session 1 Session 1a: Introduction on patent analysis (60’) Introductory lecture session • Welcoming introduction (Philippe Larédo) 5’ • Type of patents documents (Antoine Schoen) […]
-
Early 2021 CorText Manager training sessions
CorText organized a series of training workshops on CorText Manager and its methods in January 2021! These workshops were imagined as a staircase with three successive steps : Session 1: Introduction Session 2: Method comparisons Session 3: Research questions and work on user’s corpus For these sessions, the subject chosen for the demonstrations and exercises […]
-
Seminar and workshop during the Summer School of PPGCI IBICT UFRJ, Rio de Janeiro – 03/2020
In March 2020, the LabEx SITES post-doctoral researcher, Ale Abdo, traveled to Rio de Janeiro and São Paulo to organize two trainings on textual analysis and on a new method he developed and integrated at the CorText Infrastructure, as well as to participate in discussions on open and citizen science in Brazil, including the discussion […]
-
A CorText Manager distance training session in the framework of the nanocellulose project – Grenoble, June 2020
For complementing the RISIS access requested (to Leiden publications DB and RISIS patent DB) by the GAEL laboratory (UMR INRAE, CNRS, UGA, INPG), in the framework of a research project on nanocellulose, the CorText team has provided , in June and July 2020, an advanced training on the use of CorText. After setting up of […]
CorText Newsfeed
Want to stay up-to-date with the latest training sessions and developments in our methods and data? We invite you to subscribe to Cortext Newsfeed, our succint and researcher oriented quarterly newsletter.
Read the previous editions of our newsletter