Identification of profiles belonging to same people at different social networks

Primož Kerin (2016) Identification of profiles belonging to same people at different social networks. EngD thesis.

Preview

Abstract

In my thesis I combined multiple duplicate person recognition techniques like rule-based methods to determine similar persons, pair classification, cluster building and machine learning. Extra comparison of profile pictures was used for recognizing person duplicates, because this comparison is the one of the first things that humans use when comparing profiles. I also used techniques for entity resolution on multiple databases. In the end I measured time complexity and success of the deduplication.

Item Type:

Thesis (EngD thesis)

Keywords:

deduplication, social network, merge, data cleaning, record linkage

Number of Pages:

Language of Content:

Slovenian

Mentor / Comentors:

Name and Surname	ID	Function
prof. dr. Marko Bajec	245	Mentor

Link to COBISS:

http://www.cobiss.si/scripts/cobiss?command=search&base=51012&select=(ID=1536875715)

Institution:

University of Ljubljana

Department:

Faculty of Computer and Information Science

Item ID:

3304

Date Deposited:

25 Mar 2016 08:37

Last Modified:

19 Apr 2016 11:11

URI:

http://eprints.fri.uni-lj.si/id/eprint/3304

Actions (login required)

View Item