Home // SEMAPRO 2018, The Twelfth International Conference on Advances in Semantic Processing // View article

Estimating Semantic Similarity for Targeted Marketing based on Fuzzy Sets and the Odenet Ontology

Authors:
Tim vor der Brück

Keywords: Odenet; Fuzzy sets; Targeted marketing; Histogram equalization

Abstract:
Estimating the semantic similarity between texts is of vital importance for a wide range of application scenarios in natural language processing. With the increasing availability of large text corpora, data-driven approaches like Word2Vec became quite successful. In contrast, semantic methods, which employ manually designed knowledge bases like ontologies lost some of their former popularity. However, manually designed knowledge can still be a valuable resource, since it can be leveraged to boost the performance of data-driven approaches. We introduce in this paper a novel hybrid similarity estimate based on fuzzy sets that exploits both word embeddings and a lexical ontology. As ontology we use Odenet, a freely available resource recently developed by the Darmstadt University of Applied Sciences. Our application scenario is targeted marketing, in which we aim to match people to the best fitting marketing target group based on short German text snippets. The evaluation showed that the use of an ontology did indeed improve the overall result in comparison with a baseline data-driven estimate.

Pages: 48 to 52

Copyright: Copyright (c) IARIA, 2018

Publication date: November 18, 2018

Published in: conference

ISSN: 2308-4510

ISBN: 978-1-61208-678-1

Location: Athens, Greece

Dates: from November 18, 2018 to November 22, 2018