A Comparison of Statistical and Data Mining Techniques for Enrichment Ontology with Instances

DOI

10.2991/icefs-17.2017.52How to use a DOI?

Keywords

Ontology Enrichment, Statistical Technique, Classification, Conditional Random Fields (CRFs), Feature-weighted k-Nearest Neighbor

Abstract

To enrich instances into an ontology is an important task. That is because the process does extend the knowledge in ontology to cover more the domain of interest, as a result, more benefits can be gained. There are many techniques to classify instances of concepts, however, two popular ones are the statistic and the data mining methods. This paper compares the use of these two methods to classify instances to enrich ontology having more domain knowledge. This paper selects conditional random field for the statistic method and feature-weight k-nearest neighbor classification for data mining method. The experiments were conducted on the tourism ontology. The results pointed out that conditional random fields methods provided more precision and recall value than the other, specifically, F1-measure is 74.09% for conditional random fields and 60.04% for feature-weight k-nearest neighbor classification.

Copyright

© 2017, the Authors. Published by Atlantis Press.

Open Access

This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).

Download article (PDF)

TY  - CONF
AU  - Aurawan Imsombut
AU  - Jesada Kajornrit
PY  - 2017/01
DA  - 2017/01
TI  - A Comparison of Statistical and Data Mining Techniques for Enrichment Ontology with Instances
BT  - Proceedings of the 2017 International Conference on Economics, Finance and Statistics (ICEFS 2017)
PB  - Atlantis Press
SP  - 408
EP  - 413
SN  - 2352-5428
UR  - https://doi.org/10.2991/icefs-17.2017.52
DO  - 10.2991/icefs-17.2017.52
ID  - Imsombut2017/01
ER  -