Generic knowledge-based analysis of social media for recommendations

V. de Graaff; Anne van de Venis; Maurice van Keulen; R.A. de By

Generic knowledge-based analysis of social media for recommendations

V. de Graaff, Anne van de Venis, Maurice van Keulen, R.A. de By

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Academic › peer-review

4 Citations (Scopus)

44 Downloads (Pure)

Abstract

Recommender systems have been around for decades to help people find the best matching item in a pre-defined item set. Knowledge-based recommender systems are used to match users based on information that links the two, but they often focus on a single, specific application, such as movies to watch or music to listen to. In this presentation, we present our Interest-Based Recommender System (IBRS). This knowledge-based recommender system provides recommendations that are generic in three dimensions: IBRS is (1) domain-independent, (2) language-independent, and (3) independent of the used social medium. To match user interests with items, the first are derived from the user's social media profile, enriched with a deeper semantic embedding obtained from the generic knowledge base DBpedia. These interests are used to extract personalized recommendations from a tagged item set from any domain, in any language. We also present the results of a validation of IBRS by a test user group of 44 people using two item sets from separate domains: greeting cards and holiday homes.

Original language	English
Title of host publication	CBRecSys 2015, New Trends on Content-Based Recommender Systems
Subtitle of host publication	Proceedings of the 2nd Workshop on New Trends on Content-Based Recommender Systems co-located with 9th ACM Conference on Recommender Systems (RecSys 2015)
Editors	Toine Bogers, Marijn Koolen
Place of Publication	New York
Publisher	CEUR
Pages	22-29
Number of pages	8
Publication status	Published - 20 Sept 2015
Event	2nd Workshop on New Trends in Content-Based Recommender Systems, CBRecSys 2015 - Vienna, Austria Duration: 16 Sept 2015 → 20 Sept 2015 Conference number: 2 http://ceur-ws.org/Vol-1448/

Publication series

Name	CEUR Workshop Proceedings
Volume	1448
ISSN (Electronic)	1613-0073

Workshop

Workshop	2nd Workshop on New Trends in Content-Based Recommender Systems, CBRecSys 2015
Abbreviated title	CBRecSys 2015
Country/Territory	Austria
City	Vienna
Period	16/09/15 → 20/09/15
Internet address	http://ceur-ws.org/Vol-1448/

Access to Document

ArticleFinal published version, 1.25 MB

http://ceur-ws.org/Vol-1448/

Cite this

de Graaff, V., van de Venis, A., van Keulen, M., & de By, R. A. (2015). Generic knowledge-based analysis of social media for recommendations. In T. Bogers, & M. Koolen (Eds.), CBRecSys 2015, New Trends on Content-Based Recommender Systems: Proceedings of the 2nd Workshop on New Trends on Content-Based Recommender Systems co-located with 9th ACM Conference on Recommender Systems (RecSys 2015) (pp. 22-29). (CEUR Workshop Proceedings; Vol. 1448). CEUR. http://ceur-ws.org/Vol-1448/

de Graaff, V. ; van de Venis, Anne ; van Keulen, Maurice et al. / Generic knowledge-based analysis of social media for recommendations. CBRecSys 2015, New Trends on Content-Based Recommender Systems: Proceedings of the 2nd Workshop on New Trends on Content-Based Recommender Systems co-located with 9th ACM Conference on Recommender Systems (RecSys 2015). editor / Toine Bogers ; Marijn Koolen. New York : CEUR, 2015. pp. 22-29 (CEUR Workshop Proceedings).

@inproceedings{3466da7f7f544d7ea10b62e8bb3fe6a7,

title = "Generic knowledge-based analysis of social media for recommendations",

abstract = "Recommender systems have been around for decades to help people find the best matching item in a pre-defined item set. Knowledge-based recommender systems are used to match users based on information that links the two, but they often focus on a single, specific application, such as movies to watch or music to listen to. In this presentation, we present our Interest-Based Recommender System (IBRS). This knowledge-based recommender system provides recommendations that are generic in three dimensions: IBRS is (1) domain-independent, (2) language-independent, and (3) independent of the used social medium. To match user interests with items, the first are derived from the user's social media profile, enriched with a deeper semantic embedding obtained from the generic knowledge base DBpedia. These interests are used to extract personalized recommendations from a tagged item set from any domain, in any language. We also present the results of a validation of IBRS by a test user group of 44 people using two item sets from separate domains: greeting cards and holiday homes.",

author = "{de Graaff}, V. and {van de Venis}, Anne and {van Keulen}, Maurice and {de By}, R.A.",

year = "2015",

month = sep,

day = "20",

language = "English",

series = "CEUR Workshop Proceedings",

publisher = "CEUR",

pages = "22--29",

editor = "Toine Bogers and Marijn Koolen",

booktitle = "CBRecSys 2015, New Trends on Content-Based Recommender Systems",

address = "Germany",

note = "2nd Workshop on New Trends in Content-Based Recommender Systems, CBRecSys 2015, CBRecSys 2015 ; Conference date: 16-09-2015 Through 20-09-2015",

url = "http://ceur-ws.org/Vol-1448/",

}

de Graaff, V, van de Venis, A, van Keulen, M & de By, RA 2015, Generic knowledge-based analysis of social media for recommendations. in T Bogers & M Koolen (eds), CBRecSys 2015, New Trends on Content-Based Recommender Systems: Proceedings of the 2nd Workshop on New Trends on Content-Based Recommender Systems co-located with 9th ACM Conference on Recommender Systems (RecSys 2015). CEUR Workshop Proceedings, vol. 1448, CEUR, New York, pp. 22-29, 2nd Workshop on New Trends in Content-Based Recommender Systems, CBRecSys 2015, Vienna, Austria, 16/09/15. <http://ceur-ws.org/Vol-1448/>

Generic knowledge-based analysis of social media for recommendations. / de Graaff, V.; van de Venis, Anne; van Keulen, Maurice et al.
CBRecSys 2015, New Trends on Content-Based Recommender Systems: Proceedings of the 2nd Workshop on New Trends on Content-Based Recommender Systems co-located with 9th ACM Conference on Recommender Systems (RecSys 2015). ed. / Toine Bogers; Marijn Koolen. New York: CEUR, 2015. p. 22-29 (CEUR Workshop Proceedings; Vol. 1448).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Academic › peer-review

TY - GEN

T1 - Generic knowledge-based analysis of social media for recommendations

AU - de Graaff, V.

AU - van de Venis, Anne

AU - van Keulen, Maurice

AU - de By, R.A.

N1 - Conference code: 2

PY - 2015/9/20

Y1 - 2015/9/20

N2 - Recommender systems have been around for decades to help people find the best matching item in a pre-defined item set. Knowledge-based recommender systems are used to match users based on information that links the two, but they often focus on a single, specific application, such as movies to watch or music to listen to. In this presentation, we present our Interest-Based Recommender System (IBRS). This knowledge-based recommender system provides recommendations that are generic in three dimensions: IBRS is (1) domain-independent, (2) language-independent, and (3) independent of the used social medium. To match user interests with items, the first are derived from the user's social media profile, enriched with a deeper semantic embedding obtained from the generic knowledge base DBpedia. These interests are used to extract personalized recommendations from a tagged item set from any domain, in any language. We also present the results of a validation of IBRS by a test user group of 44 people using two item sets from separate domains: greeting cards and holiday homes.

AB - Recommender systems have been around for decades to help people find the best matching item in a pre-defined item set. Knowledge-based recommender systems are used to match users based on information that links the two, but they often focus on a single, specific application, such as movies to watch or music to listen to. In this presentation, we present our Interest-Based Recommender System (IBRS). This knowledge-based recommender system provides recommendations that are generic in three dimensions: IBRS is (1) domain-independent, (2) language-independent, and (3) independent of the used social medium. To match user interests with items, the first are derived from the user's social media profile, enriched with a deeper semantic embedding obtained from the generic knowledge base DBpedia. These interests are used to extract personalized recommendations from a tagged item set from any domain, in any language. We also present the results of a validation of IBRS by a test user group of 44 people using two item sets from separate domains: greeting cards and holiday homes.

M3 - Conference contribution

T3 - CEUR Workshop Proceedings

SP - 22

EP - 29

BT - CBRecSys 2015, New Trends on Content-Based Recommender Systems

A2 - Bogers, Toine

A2 - Koolen, Marijn

PB - CEUR

CY - New York

T2 - 2nd Workshop on New Trends in Content-Based Recommender Systems, CBRecSys 2015

Y2 - 16 September 2015 through 20 September 2015

ER -

de Graaff V, van de Venis A, van Keulen M , de By RA. Generic knowledge-based analysis of social media for recommendations. In Bogers T, Koolen M, editors, CBRecSys 2015, New Trends on Content-Based Recommender Systems: Proceedings of the 2nd Workshop on New Trends on Content-Based Recommender Systems co-located with 9th ACM Conference on Recommender Systems (RecSys 2015). New York: CEUR. 2015. p. 22-29. (CEUR Workshop Proceedings).

Generic knowledge-based analysis of social media for recommendations

Abstract

Publication series

Workshop

Access to Document

Fingerprint

Cite this