Identity evaluation based entity cleansing for entities searched from linked open data cloud


  • Yonglak Sohn Seokyeong University





Semantic Web, Ontology, Knowledge Expansion, Identity Evaluation, Linked Open Data Cloud.


Linked open data (LOD) cloud is composed of LODs that assert facts on an entity with various viewpoints. Knowledge expansion, hence, has been an important goal of LOD cloud and achieved by identity links, specified with <owl: sameAs> predicates, among entities in differ-ent LODs. After searching the LODs in depth through the identity links, an entity searched from surface LOD would be expanded with various facts obtained from the other LODs. This paper suggests how to evaluate the searched entities as identical to the entity of the surface LOD and then to pick out the entities whose identity levels were sufficiently high compared to the criteria specified in a user query. For entity identity evaluation, LODs’ reputations and agreements on the identity assertions have been considered. Identity evaluation based enti-ty cleansing (IE2C) system and its surroundings have been implemented for experiments. Analysis on the experimental results presented that six or seven identity links would be necessary to an entity in order to achieve the goal of knowledge expansion. IE2C would provide in-depth searching results which were composed of trustworthy entities and their various descriptions to users.





[1] N. Konstantinou, D.E. Spanos, Materializing the Web of Linked Data, firstEd., Springer, USA, 2015.

[2] W3C, “Linked Dataâ€,, Revised June 2018, Accessed September 26, 2018.

[3] G. Antoniou, P. Groth, a Semantic Web Primer, third Ed., MIT Press, USA, 2012.

[4] T. Heath, C. Bizer, Linked Data: Evolving the Web into a Global Data Space, Morgan & Claypool, USA, 2011.

[5] T.B. Lee, “Semantic Web Road Mapâ€,, Revised October 1998, Accessed September 26, 2018.

[6] A. Abele and J. McCrae, “The Linked Open Data cloud diagramâ€, 2017,, Revised August 2018, Accessed September 26, 2018.

[7] D. Allemang, J, Hendler, Semantic Web for the Working Ontologist: Effective Modeling in RDFS and OWL, Elsevier, USA, 2011.

[8] J.Z. Pan, G. Vetere, J.M.G. Perez, H. Wu, Exploiting Linked Data and Knowledge Graphs in Large Organizations, Springer, Switzerland, 2017.

[9] A. Harsh, K. Hose, R. Schenkel, Linked Data Management, 1st Ed., CRC Press, NewYork, 2014.

[10] J. Volz, C. Bizer, M. Gaedke, G. Kobilrov, “Silk – A Link Discovery Framework for the Web of Dataâ€, Proc. of the second Workshop on Linked Data on the Web, pp. 238-247, 2009.

[11] A.N. Ngomo, S. Auer, “LIMES - A Time-Efficient Approach for Large-Scale Link Discovery on the Web of Dataâ€, Proc. of the 22nd IJCAIpp. pp. 2312-2317, 2011.

[12] J. Park and Y. Sohn, “A Syntax Added Link Evaluation Technique for Improving Trustworthiness of LOD’s Linkagesâ€, Journal of KIISE: Databases, 41:1, pp. 45-61, 2015.

[13] J. Park and Y. Sohn, “Trustworthiness Improving Link Evaluation Technique for LOD Linkages giving Considerations to the Syntactic Properties of RDFS, OWL, and OWL2â€, Journal of KIISE: Databases, 41:4, pp. 226-241, 2014.

[14] Y. Sohn, “Reliability Improving Identity Link Evaluation Technique for Linked Open Data Publicationâ€, INFORMATION, 19:9, pp. 4271-4279, 2016.

[15] P.F. Brown, P.V. deSouza, R.L. Mercer, “Class-based n-gram Model for Natural Languageâ€, Computational Linguistics, 18:3, pp. 467-479, 1992.

[16] C. Bizer, “Is the Semantic Web what we expectedâ€,, Revised November 2016, Accessed September 26, 2018.

[17] S. Brin, R. Motwani, T. Winograd., “The PageRank Citation Ranking-Bringing Order to the Webâ€, http:// Revised November 1998, Accessed September 26, 2018.

[18] B. Ducharme, Learning SPARQL, O’REILLY, USA, 2013.

View Full Article: