Vol 3 - Digital Contextualization

 .: Call for Papers :.

Special Issue on

Digital Contextualization 

Scope of the special issue

Sociologists like Pierre Bourdieu advocated the need of a relational type of analysis on data: Statistics, scores and answers to a questionnaire should be considered to relate individuals and highlight hidden complex factors.Data collected about individuals need to be contextualized relatively to other individuals, implicit social environment and culture at large.  

Correspondence Analysis based on Singular value decomposition (SVD) has been successful in contextualizing individual data to other individuals. Latent Semantic Analysis also based on SVD was successful in contextualizing words based on their usage context. These methods have been expanded in several directions. Partial Least Squares path modelling (PLS­pm) analysis allows the analysts to test hypotheses against data by integrating a simulation process. Latent Dirichlet Allocation has provided a  probabilistic alternative to vector LSA.  

Along with these efficient numerical approaches, discrete approaches relying on the increasing computer power have explored non­frequentist approaches. These Formal Concept Analysis based on Galois Lattices allow highlighting and relate complex underlying concepts. More specifically,  Information Visualisation based on graph algorithms like PathFinder and Social Network indicators  have allowed domain and topic mapping from raw text. Further on, automatic summarization approaches combined with Information Retrieval approaches led to methods that can highlight the implicit context of a short message giving a large and reliable encyclopedic resource like the WikiPedia.

Recently, Deep Learning based on Word Embedding approaches handle contextualization based on very large data sources.

Pierre Bourdieu was limited by two obstacles: the power of computers that at the time did not allow  him to explore all correlations and the cost of data digitization and the contextualization by correlation analysis could only be done at the initiative of the analyst and according to the choice made. However the digital world of the 21st century reversed this paradigm. Automatic contextualisation of our every action is sustained. Finally the removal of these two technical bottlenecks raises questions, data rights and other ethical issues.

The special issue would include state of the art, automatic contextualization methods and would put into perspective representative case studies of these approaches. Each article would be reviewed by a multidisciplinary committee and will include thorough reviews by both sociologists and computer scientists or statisticians. 

Topics of the special issue

For the applicative side​, all domains related to the representation or study of social relationships and interactions are concerned:

  • anthropology
  • artificial intelligence
  • communication
  • data science
  • economics
  • geomatics
  • history
  • information processing
  • information retrieval
  • law
  • linguistics
  • natural language processing
  • political science
  • sociology
  • and others. 

The​ methodological aspects​ of interest include: 

  • Multiple Correspondence Analysis 
  • Factor analysis
  • Formal Concept Analysis
  • Information Visualisation
  • PLS­-pm
  • LSA and LDA 
  • Text Summarization 
  • Word Embedding 
  • Deep Learning 
  • Open Link Data 
  • Micro­blog analysis
  • Opinion and Sentiment Analysis
  • and others. 

About the journal

Since January 2016, JIMIS is an international open-access peer-reviewed journal covering cross-disciplinary topics. It uses the Creative Commons license and is free for both authors and readers. Each issue is handled by guest editors and dedicated to a specific topic. The strongly interdisciplinary nature of the journal is enforced by gathering in one issue articles from Humanities and Social Sciences, and articles from Exact and Experimental Sciences. Papers co-signed by authors from different disciplines are very much welcome, but not mandatory.

Located off the beaten track, JIMIS has a wide and original scope. The goal of each issue is to emphasize a variety of points of view on a common cross-disciplinary topic. JIMIS aims at publishing high quality papers that would not find their place in traditional disciplinary journals, due to their strong connection with other scientific fields. For instance: tackling a problem which is multidisciplinary in nature, exposing alternative points of views coming from other fields, or transposing methods from one field to another.

Along with several other international journals, JIMIS is published under the aegis of Épisciences (http://episciences.org/), an offspring of the CNRS (French national center for scientific research http://www.cnrs.fr/). The steering committee of JIMIS is constituted of recognized international scientists representing a number of domains (http://jimis.episciences.org/page/comites). Each paper is reviewed by three reviewers in a single blind process. 

Submission Notes

Submissions can be in English or French. For the abstract and paper submission, authors must send a PDF file by email to:

eric.sanjuan@univ-avignon.fr (or alternatively to  eric.sanjuan@talne.eu)

For accepted papers, authors will have to follow the publication process and guidelines of the journal  (​http://jimis.episciences.org/page/auteurs​). Most significantly, authors must take into account that the publication process involves uploading the article on HAL (​https://hal.archives­ouvertes.fr/​) or arXiv (​http://arxiv.org/​). LaTeX, MS Word and OpenOffice templates are provided on the journal website.

Submitted articles ​must not have been previously published nor currently submitted for conference/journal publication elsewhere​. If the article is an extension of a previous paper, please cite it in the submitted article, explicitly describing the new contributions and explain how they are significant.

Authors having submitted an abstract could benefit from an access to CLEF Microblog Cultural Contextualization lab data and server resources.

Important Dates

Abstract submission (optional): ​from October 15​th​ to October 31th 2016 (Extended)

Abstract feedback: ​November 1​st​ 2016

Paper submission deadline all tracks: December 1​st​ 2016

Fast track publication (papers accepted without revision): December 30th​ 2016

First round of reviews for minor and major revisions: January 1​st​ 2017

Intended publication date for revised papers: March 2017 

Editors

Guest editors:

  • Pr. Frédéric Lebaron, Department of Humanities, ENS Paris­Saclay 
  • Dr. Brigitte Le Roux, MAP5 ­ University Paris Descartes and CEVIPOF ­ Sciences­Po Paris 
  • Pr. Fionn Murtagh, Big Data Lab, University of Derby and Goldsmiths University of London 
  • Pr. Evelyn Ruppert, Department of Sociology, Goldsmiths University of London

Associate editor:

Dr. Eric SanJuan­, Computer Science Lab of Avignon (LIA), University of Avignon