Mapping Heterogeneous Textual Data: a Multidimensional Approach based on Spatiality and Theme

Jacques Fize (1, 2) , Mathieu Roche (1, 2) , Maguelonne Teisseire (2)

1 Cirad-ES - Département Environnements et Sociétés
2 UMR TETIS - Territoires, Environnement, Télédétection et Information Spatiale

In this paper, we propose a multidimensional mapping approach for heterogeneous textual data that exploits firstly the spatial dimension and secondly the thematic dimension. Based on the Spatial Textual Representation (STR) as well as the Geodict geographic database, the contribution presented in this paper integrates the thematic dimension of documents. To support our proposal on mapping textual documents, we evaluate the different aspects of the process using two real corpora, including one corpus that is highly heterogeneous.

Mots clés: Spatial and Thematic Dimensions; Heterogeneous Data

Domaines: Intelligence artificielle [cs.AI]

Jacques Fize, Mathieu Roche, Maguelonne Teisseire. Mapping Heterogeneous Textual Data: a Multidimensional Approach based on Spatiality and Theme. Internet Science. 6th International Conference, INSCI 2019, Dec 2019, Perpignan, France. pp.310-317, ⟨10.1007/978-3-030-34770-3_25⟩. ⟨hal-03611104⟩