UZH-Logo

Maintenance Infos

Social network aggregation using face-recognition


Minder, Patrick; Bernstein, Abraham (2011). Social network aggregation using face-recognition. In: ISWC 2011 Workshop: Social Data on the Web, Bonn, Germany, 23 October 2011 - 23 October 2011.

Abstract

With the rapid growth of the social web an increasing num- ber of people started to replicate their off-line preferences and lives in an on-line environment. Consequently, the social web provides an enormous source for social network data, which can be used in both commercial and research applications. However, people often take part in multiple social network sites and, generally, they share only a selected amount of data to the audience of a specific platform. Consequently, the interlink- age of social graphs from different sources getting increasingly impor- tant for applications such as social network analysis, personalization, or recommender systems. This paper proposes a novel method to enhance available user re-identification systems for social network data aggrega- tion based on face-recognition algorithms. Furthermore, the method is combined with traditional text-based approaches in order to attempt a counter-balancing of the weaknesses of both methods. Using two sam- ples of real-world social networks (with 1610 and 1690 identities each) we show that even though a pure face-recognition based method gets out- performed by the traditional text-based method (area under the ROC curve 0.986 vs. 0.938) the combined method significantly outperforms both of these (0.998, p = 0.0001) suggesting that the face-based method indeed carries complimentary information to raw text attributes.

With the rapid growth of the social web an increasing num- ber of people started to replicate their off-line preferences and lives in an on-line environment. Consequently, the social web provides an enormous source for social network data, which can be used in both commercial and research applications. However, people often take part in multiple social network sites and, generally, they share only a selected amount of data to the audience of a specific platform. Consequently, the interlink- age of social graphs from different sources getting increasingly impor- tant for applications such as social network analysis, personalization, or recommender systems. This paper proposes a novel method to enhance available user re-identification systems for social network data aggrega- tion based on face-recognition algorithms. Furthermore, the method is combined with traditional text-based approaches in order to attempt a counter-balancing of the weaknesses of both methods. Using two sam- ples of real-world social networks (with 1610 and 1690 identities each) we show that even though a pure face-recognition based method gets out- performed by the traditional text-based method (area under the ROC curve 0.986 vs. 0.938) the combined method significantly outperforms both of these (0.998, p = 0.0001) suggesting that the face-based method indeed carries complimentary information to raw text attributes.

Citations

Downloads

32 downloads since deposited on 10 Aug 2012
4 downloads since 12 months
Detailed statistics

Additional indexing

Item Type:Conference or Workshop Item (Paper), refereed, original work
Communities & Collections:03 Faculty of Economics > Department of Informatics
Dewey Decimal Classification:000 Computer science, knowledge & systems
Language:English
Event End Date:23 October 2011
Deposited On:10 Aug 2012 13:01
Last Modified:05 Apr 2016 15:52
Publisher:RWTH Aachen
Series Name:CEUR Workshop Proceedings
Number:830
ISSN:1613-0073
Official URL:http://ceur-ws.org/Vol-830/sdow2011_paper_9.pdf
Related URLs:http://ceur-ws.org/Vol-830 (Publisher)
Other Identification Number:merlin-id:3881
Permanent URL: https://doi.org/10.5167/uzh-63244

Download

[img]
Content: Published Version
Filetype: PDF
Size: 269kB

TrendTerms

TrendTerms displays relevant terms of the abstract of this publication and related documents on a map. The terms and their relations were extracted from ZORA using word statistics. Their timelines are taken from ZORA as well. The bubble size of a term is proportional to the number of documents where the term occurs. Red, orange, yellow and green colors are used for terms that occur in the current document; red indicates high interlinkedness of a term with other terms, orange, yellow and green decreasing interlinkedness. Blue is used for terms that have a relation with the terms in this document, but occur in other documents.
You can navigate and zoom the map. Mouse-hovering a term displays its timeline, clicking it yields the associated documents.

Author Collaborations