Automatic Identification of Research Fields in Scientific Papers

Automatic Identification of Research Fields in Scientific Papers Eric Kergosien1, Amin Farvardin5, Maguelonne Teisseire3, Marie-No¨elle Bessagnet2, Joachim Sch¨opfel1,6, St´ephane Chaudiron1, Bernard Jacquemin1, Annig Lacayrelle2, Mathieu Roche3,4, Christian Sallaberry2, Jean Philippe Tonneau3,4 1 Univ. Lille, EA 4073 – GERiiCO, F-59000 Lille, France prenom.nom@univ-lille.fr 2 LIUPPA, Universit´e de Pau et des Pays de l’Adour, Pau, France prenom.nom@univ-pau.fr 3 TETIS, Univ. Montpellier, APT, Cirad, CNRS, Irstea, Montpellier, France prenom.nom@teledetection.fr 4 Cirad, Montpellier, France prenom.nom@cirad.fr 5 LAMSADE, Universit´e Paris-Dauphine, Paris, France MohammadAmin.Farvardin@dauphine.eu 6 ANRT, Lille, France Joachim.Schopfel@univ-lille3.fr Abstract The TERRE-ISTEX project aims to identify scientific research dealing with specific geographical territories areas based on hetero- geneous digital content available in scientific papers. The project is divided into three main work packages: (1) identification of the periods and places of empirical studies, and which reflect the publications resulting from the analyzed text samples, (2) identification of the themes which appear in these documents, and (3) development of a web-based geographical information retrieval tool (GIR). The first two actions combine Natural Language Processing patterns with text mining methods. The integration of the spatial, thematic and temporal dimensions in a GIR contributes to a better understanding of what kind of research has been carried out, of its topics and its geographical and historical coverage. Another originality of the TERRE-ISTEX project is the heterogeneous character of the corpus, including PhD theses and scientific articles from the ISTEX digital libraries and the CIRAD research center. Keywords: text mining, natural language processing, geographical information retrieval, scientometrics, document analysis 1. Introduction Widespread access to digital resources, via academic plat- forms – for example, the Gallica project (BnF)1, the IS- TEX2 platform, electronic theses and dissertation reposito- ries (TEL), content federation services (Isidore), or elec- tronic publishing platforms (OpenEdition) – offers nu- merous possibilities for users. The ISTEX initiative was launched to create innovative information retrieval services and provide access to digital resources through different search processes. The increasing adoption of information and communication technologies by researchers in different academic disciplines, especially in the social sciences and humanities, is changing the conditions of knowledge appro- priation. Digital humanities have made it possible to de- velop platforms, providing researchers with large volumes of academic papers and with support services to add value and make use of them (e.g., the TELMA3 application). The TERRE-ISTEX project was developed in this research context and proposes (1) to identify the covered territories and areas from scientific papers available in digital versions within and outside the ISTEX library, and (2) to evaluate the academic disciplines involved (e.g. history, geography, information sciences, etc.) as well as the evolution of dis- ciplinary and multi-disciplinary research paradigms in se- lected topics. The results of this project will help scientists 1http://gallica.bnf.fr/ 2http://www.istex.fr/ 3http://www.cn-telma.fr/ Figure 1: Generic Approach to Multidimensional Analysis of Scientific Corpus working on a given territory (areas at different scales, such as township, region, country, or continent) to retrieve pa- pers on the same territory. 2. The TERRE-ISTEX Project The generic approach used in the TERRE-ISTEX project is described in …

Content truncated to 500 words