@inproceedings{LueschowWartena2017, author = {Andreas L{\"u}schow and Christian Wartena}, title = {Classifying Medical Literature Using k-Nearest-Neighbours Algorithm}, series = {NKOS 2017: 17th European Networked Knowledge Organization Systems (NKOS) Workshop ; Proceedings of the 17th European Networked Knowledge Organization Systems Workshop co-located with the 21st International Conference on Theory and Practice of Digital Libraries 2017 (TPDL 2017), Thessaloniki, Greece, September 21st, 2017}, issn = {1613-0073}, doi = {10.25968/opus-1146}, url = {http://nbn-resolving.de/urn:nbn:de:bsz:960-opus4-11464}, pages = {26 -- 38}, year = {2017}, abstract = {The amount of papers published yearly increases since decades. Libraries need to make these resources accessible and available with classification being an important aspect and part of this process. This paper analyzes prerequisites and possibilities of automatic classification of medical literature. We explain the selection, preprocessing and analysis of data consisting of catalogue datasets from the library of the Hanover Medical School, Lower Saxony, Germany. In the present study, 19,348 documents, represented by notations of library classification systems such as e.g. the Dewey Decimal Classification (DDC), were classified into 514 different classes from the National Library of Medicine (NLM) classification system. The algorithm used was k-nearest-neighbours (kNN). A correct classification rate of 55.7\% could be achieved. To the best of our knowledge, this is not only the first research conducted towards the use of the NLM classification in automatic classification but also the first approach that exclusively considers already assigned notations from other classification systems for this purpose.}, language = {en} }