Methodology for identifying study sites in scientific corpus

TL;DR

This paper presents a methodology combining NLP and text mining to identify study sites, themes, and periods in scientific corpora, enabling spatial-temporal analysis of research activities.

Contribution

It introduces a novel approach integrating NLP and text mining for extracting geographical, thematic, and temporal information from heterogeneous scientific texts.

Findings

Successful identification of empirical study locations and periods

Effective thematic analysis of scientific publications

Development of a web-based geographical information retrieval tool

Abstract

The TERRE-ISTEX project aims at identifying the evolution of research working relation to study areas, disciplinary crossings and concrete research methods based on the heterogeneous digital content available in scientific corpora. The project is divided into three main actions: (1) to identify the periods and places which have been the subject of empirical studies, and which reflect the publications resulting from the corpus analyzed, (2) to identify the thematics addressed in these works and (3) to develop a web-based geographical information retrieval tool (GIR). The first two actions involve approaches combining Natural languages processing patterns with text mining methods. By crossing the three dimensions (spatial, thematic and temporal) in a GIR engine, it will be possible to understand what research has been carried out on which territories and at what time. In the project, the experiments are carried out on a heterogeneous corpus including electronic thesis and scientific articles from the ISTEX digital libraries and the CIRAD research center.