Text Mining in the Domain of Plant Genetic Resources
Ivan P. Popchev, Daniela Orozova · 2020
Upcoming is the construction of informational and social spaces which integrate heterogeneous technologies and various approaches to the collection, storage and processing of information related to the plant genetic resources of Bulgaria. In the present paper a multistage algorithm for automatic analysis of documents from the area of plant genetic resources is proposed. Determination of the significant words in the document and the type of its content is carried out based on the object-oriented ontologies in the field. By applying software instruments for classification, testing and evaluation, the documents are classified into related and not related to the studied subject area - agriculture and plant genetic resources of Bulgaria.