@inproceedings{195faaf78fbf458eaa8bce252cdf549c,
title = "Modeling Generalization in Domain Taxonomies Using a Maximum Likelihood Criterion",
abstract = "We define a most specific generalization of a fuzzy set of topics assigned to leaves of the rooted tree of a domain taxonomy. This generalization lifts the set to its “head subject” node in the higher ranks of the taxonomy tree. The head subject is supposed to “tightly” cover the query set, possibly involving some errors referred to as “gaps” and “offshoots”. We develop a method to globally maximize the likelihood of a scenario involving gains and losses of the general concept manifested in a fuzzy cluster of leaf nodes of the taxonomy. Probabilities of the gain and loss events are derived from multiple runs of our earlier method of maximum parsimony starting with randomly generated values for the two parameters involved. Supplemented with fuzzy c-means clustering, this allows us to obtain meaningful generalizations for six fuzzy thematic clusters of Data Science topics using over 17000 abstracts from 17 research journals published by Springer.",
keywords = "Fuzzy thematic cluster, Generalization, Maximum likelihood, Research tendencies",
author = "Zhirayr Hayrapetyan and Susana Nascimento and Trevor Fenner and Dmitry Frolov and Boris Mirkin",
note = "info:eu-repo/grantAgreement/FCT/6817 - DCRRNI ID/UIDB%2F04516%2F2020/PT# Publisher Copyright: {\textcopyright} 2022, The Author(s), under exclusive license to Springer Nature Switzerland AG.; 10th World Conference on Information Systems and Technologies, WorldCIST 2022 ; Conference date: 12-04-2022 Through 14-04-2022",
year = "2022",
doi = "10.1007/978-3-031-04819-7_15",
language = "English",
isbn = "978-3-031-04818-0",
volume = "2",
series = "Lecture Notes in Networks and Systems",
publisher = "Springer",
pages = "141--147",
editor = "{\'A}lvaro Rocha and Hojjat Adeli and Gintautas Dzemyda and Fernando Moreira",
booktitle = "Information Systems and Technologies - WorldCIST 2022",
address = "Netherlands",
}