110559 20240319080948.0 doi 10.3390/ijgi11020087 sideral 127489 ART-2022-127489 eng Lacasta, J. Approaches for the clustering of geographic metadata and the automatic detection of quasi-spatial dataset series 2022 Access copy available to the general public Unrestricted The discrete representation of resources in geospatial catalogues affects their information retrieval performance. The performance could be improved by using automatically generated clusters of related resources, which we name quasi-spatial dataset series. This work evaluates whether a clustering process can create quasi-spatial dataset series using only textual information from metadata elements. We assess the combination of different kinds of text cleaning approaches, word and sentence-embeddings representations (Word2Vec, GloVe, FastText, ELMo, Sentence BERT, and Universal Sentence Encoder), and clustering techniques (K-Means, DBSCAN, OPTICS, and agglomerative clustering) for the task. The results demonstrate that combining word-embeddings representations with an agglomerative-based clustering creates better quasi-spatial dataset series than the other approaches. In addition, we have found that the ELMo representation with agglomerative clustering produces good results without any preprocessing step for text cleaning. info:eu-repo/grantAgreement/ES/AEI/PID2020-113353RB-I00 info:eu-repo/grantAgreement/ES/DGA/T59-20R info:eu-repo/semantics/openAccess by http://creativecommons.org/licenses/by/3.0/es/ 3.4 2022 GEOGRAPHY, PHYSICAL 18 / 49 = 0.367 2022 Q2 T2 COMPUTER SCIENCE, INFORMATION SYSTEMS 88 / 158 = 0.557 2022 Q3 T2 REMOTE SENSING 21 / 34 = 0.618 2022 Q3 T2 0.738 2022 Earth and Planetary Sciences (miscellaneous) 2022 Q1 Geography, Planning and Development 2022 Q1 Computers in Earth Sciences 2022 Q2 6.2 2022 info:eu-repo/semantics/article info:eu-repo/semantics/publishedVersion López Pellicer, F. J. Zarazaga-Soria, J. Béjar, R. Nogueras-Iso, J. 11, 2 (2022), 87[19 pp.] ISPRS int. j. geo-inf. ISPRS International Journal of Geo-Information 2220-9964 543908 http://zaguan.unizar.es/record/110559/files/texto_completo.pdf Versión publicada 2860990 http://zaguan.unizar.es/record/110559/files/texto_completo.jpg?subformat=icon icon Versión publicada oai:zaguan.unizar.es:110559 articulos driver 2024-03-18-12:48:53 ARTICLE