slides

4 downloads 51766 Views 4MB Size Report
Oct 27, 2011 ... [Winoto & Tang, 2008] Winoto, P., Tang, T. 2008. If You Like the Devil Wears Prada the Book, Will You also Enjoy the Devil Wears. Prada the ...
A Generic Semantic-based Framework for Cross-domain Recommendation

Ignacio Fernández-Tobías1, Marius Kaminskas2, Iván Cantador1, Francesco Ricci2 1

Escuela Politécnica Superior, Universidad Autónoma de Madrid, Spain [email protected], [email protected]

2

Faculty of Computer Science, Free University of Bozen-Bolzano, Italy [email protected], [email protected]

Contents

1

• Cross-domain recommendation • Case study: adapting music recommendation to points of interest • A semantic-based framework for cross-domain recommendation • Semantic-based knowledge representation • Semantic graph-based recommendation algorithm

• Preliminary results • Future work

A Generic Semantic-based Framework for Cross-domain Recommendation 2nd Workshop on Information Heterogeneity and Fusion in Recommender Systems (HetRec 2011) 5th ACM Conference on Recommender Systems (RecSys 2011) - Chicago, IL, USA - October 23-27, 2011

Contents

2

• Cross-domain recommendation • Case study: adapting music recommendation to points of interest • A semantic-based framework for cross-domain recommendation • Semantic-based knowledge representation • Semantic graph-based recommendation algorithm

• Preliminary results • Future work

A Generic Semantic-based Framework for Cross-domain Recommendation 2nd Workshop on Information Heterogeneity and Fusion in Recommender Systems (HetRec 2011) 5th ACM Conference on Recommender Systems (RecSys 2011) - Chicago, IL, USA - October 23-27, 2011

Cross-domain recommendation • Recommender systems can help users to make choices, by proactively finding relevant items or services, taking into account or predicting the users’ tastes, priorities and goals • The vast majority of the currently available recommender systems predict the user’s relevance of items in a specific and limited domain

A Generic Semantic-based Framework for Cross-domain Recommendation 2nd Workshop on Information Heterogeneity and Fusion in Recommender Systems (HetRec 2011) 5th ACM Conference on Recommender Systems (RecSys 2011) - Chicago, IL, USA - October 23-27, 2011

3

Cross-domain recommendation

4

• In some applications, it could be useful to offer the user joint personalized recommendations of items belonging to multiple domains • In an e-commerce site, we may suggest movies or videogames based on a particular book bought by a costumer • In a travel application, we may suggest cultural events may interest a person who has booked a hotel in a particular place • In an e-learning system, we may suggest educational websites with topics related to a video documentary a student has seen

• Potential benefits • Offering diversity and serendipity • Addressing the user cold-start problem (on the target domain) • Mitigating the sparsity problem

A Generic Semantic-based Framework for Cross-domain Recommendation 2nd Workshop on Information Heterogeneity and Fusion in Recommender Systems (HetRec 2011) 5th ACM Conference on Recommender Systems (RecSys 2011) - Chicago, IL, USA - October 23-27, 2011

Cross-domain recommendation

5

• Some real applications do already recommend items from different domains, but • their recommendations rely on statistical analysis of popular items, without any personalization strategy, or • most of them only exploit information about the user preferences available in the target domain

A Generic Semantic-based Framework for Cross-domain Recommendation 2nd Workshop on Information Heterogeneity and Fusion in Recommender Systems (HetRec 2011) 5th ACM Conference on Recommender Systems (RecSys 2011) - Chicago, IL, USA - October 23-27, 2011

Cross-domain recommendation

6

• Research questions [Winoto & Tang, 2008] 1. At community level, are there correlations between user preferences for items belonging to the different domains of interest? 2. At individual level, can we build a recommendation model where each user’s preferences in source domains are used to predict/adapt her preferences in target domains? 3. How should we evaluate the effectiveness of cross-domain item recommendations?

[Winoto & Tang, 2008] Winoto, P., Tang, T. 2008. If You Like the Devil Wears Prada the Book, Will You also Enjoy the Devil Wears Prada the Movie? A Study of Cross-Domain Recommendations. New Generation Computing 26(3), 209-225. A Generic Semantic-based Framework for Cross-domain Recommendation 2nd Workshop on Information Heterogeneity and Fusion in Recommender Systems (HetRec 2011) 5th ACM Conference on Recommender Systems (RecSys 2011) - Chicago, IL, USA - October 23-27, 2011

Contents

7

• Cross-domain recommendation • Case study: adapting music recommendation to points of interest • A semantic-based framework for cross-domain recommendation • Semantic-based knowledge representation • Semantic graph-based recommendation algorithm

• Preliminary results • Future work

A Generic Semantic-based Framework for Cross-domain Recommendation 2nd Workshop on Information Heterogeneity and Fusion in Recommender Systems (HetRec 2011) 5th ACM Conference on Recommender Systems (RecSys 2011) - Chicago, IL, USA - October 23-27, 2011

Case study: adapting music recommendation to points of interest • Recommending music artists that suit places of interest (POIs) • Mobile city guide soundtrack • Adaptive music playlist in a car

[Braunhofer et al., 2011] Braunhofer, M., Kaminskas, M., Ricci, F. 2011. Recommending Music for Places of Interest in a Mobile Travel Guide. 5th ACM Conference on Recommender Systems. A Generic Semantic-based Framework for Cross-domain Recommendation 2nd Workshop on Information Heterogeneity and Fusion in Recommender Systems (HetRec 2011) 5th ACM Conference on Recommender Systems (RecSys 2011) - Chicago, IL, USA - October 23-27, 2011

8

Case study: adapting music recommendation to points of interest • In a previous work [Kaminskas & Ricci, 2011], emotional tags were used to manually annotate places and music • Emotional tags can be used to find matching between music and places of interest ‐ e.g. a monument and a music track may be described as ‘strong’ and ‘triumphant’

[Kaminskas & Ricci, 2011] Kaminskas, M., Ricci, F. 2011. Location-Adapted Music Recommendation Using Tags. 19th International Conference on User Modeling, Adaptation and Personalization, 183-194. A Generic Semantic-based Framework for Cross-domain Recommendation 2nd Workshop on Information Heterogeneity and Fusion in Recommender Systems (HetRec 2011) 5th ACM Conference on Recommender Systems (RecSys 2011) - Chicago, IL, USA - October 23-27, 2011

9

Case study: adapting music recommendation to points of interest 10 • In this work, we aim at automatically finding semantic relations between POIs and music artists • We propose to explore the Web of Data (Linked Data) to find such relations • Specifically, we propose to exploit DBpedia, the Linked Data version of Wikipedia • DBpedia can be considered as a core ontology in the Web of Data • Connected to many other ontologies • Describing and linking more than 3.5 million concepts from a large variety of knowledge domains

A Generic Semantic-based Framework for Cross-domain Recommendation 2nd Workshop on Information Heterogeneity and Fusion in Recommender Systems (HetRec 2011) 5th ACM Conference on Recommender Systems (RecSys 2011) - Chicago, IL, USA - October 23-27, 2011

Case study: adapting music recommendation to points of interest 11 • In this work, we aim at automatically finding semantic relations between POIs and music artists • We propose to explore the Web of Data (Linked Data) to find such relations • Specifically, we propose to exploit DBpedia, the Linked Data version of Wikipedia • DBpedia can be considered as a core ontology in the Web of Data • Connected to many other ontologies • Describing and linking more than 3.5 million concepts from a large variety of knowledge domains

A Generic Semantic-based Framework for Cross-domain Recommendation 2nd Workshop on Information Heterogeneity and Fusion in Recommender Systems (HetRec 2011) 5th ACM Conference on Recommender Systems (RecSys 2011) - Chicago, IL, USA - October 23-27, 2011

Case study: adapting music recommendation to points of interest 12

• Issues to investigate, identified in [Winoto & Tang, 2008] 1. Correlations between user preferences for items of the different domains  Correlations between POIs and music were established through tags in [Kaminskas & Ricci, 2011] 2. Recommendation model to predict/adapt user preferences across domains  This paper addresses this particular issue, presenting a semantic-based framework to support cross-domain recommendation 3. Evaluation of cross-domain recommendation effectiveness  Future work

A Generic Semantic-based Framework for Cross-domain Recommendation 2nd Workshop on Information Heterogeneity and Fusion in Recommender Systems (HetRec 2011) 5th ACM Conference on Recommender Systems (RecSys 2011) - Chicago, IL, USA - October 23-27, 2011

Contents

13

• Cross-domain recommendation • Case study: adapting music recommendation to points of interest • A semantic-based framework for cross-domain recommendation • Semantic-based knowledge representation • Semantic graph-based recommendation algorithm

• Preliminary results • Future work

A Generic Semantic-based Framework for Cross-domain Recommendation 2nd Workshop on Information Heterogeneity and Fusion in Recommender Systems (HetRec 2011) 5th ACM Conference on Recommender Systems (RecSys 2011) - Chicago, IL, USA - October 23-27, 2011

A Semantic-based framework for cross-domain recommendation • Goal: finding semantic relations between a given POI and music artists • Example: music artists related to the ‘Vienna State Opera’

Vienna State Opera

Wolfgang Amadeus Mozart

• Identified relations: • Geographical: artists who were born, died or lived in Vienna • Time-based: artists who were born, died or lived in the year (decade, century) the State Opera of Vienna was built • Category-based: artists who belong to music categories that are related through keywords to architecture structures/styles identified with the building of the Opera of Vienna • Tags: artists annotated with tags also assigned to the Opera of Vienna A Generic Semantic-based Framework for Cross-domain Recommendation 2nd Workshop on Information Heterogeneity and Fusion in Recommender Systems (HetRec 2011) 5th ACM Conference on Recommender Systems (RecSys 2011) - Chicago, IL, USA - October 23-27, 2011

14

A Semantic-based framework for cross-domain recommendation • A directed Acyclic Graph (DAG) representing semantic relations between concepts in two domains Vienna Austria

instance POI State Opera of Vienna

Arnold Schoenberg

MUSIC ARTIST

CITY Mozart

class 19th century

Brahms

Bizet

TIME

Opera houses

opera

Ballet venues

ballet

ARCHITECTURE CATEGORY

KEYWORD

Opera composers

A Generic Semantic-based Framework for Cross-domain Recommendation 2nd Workshop on Information Heterogeneity and Fusion in Recommender Systems (HetRec 2011) 5th ACM Conference on Recommender Systems (RecSys 2011) - Chicago, IL, USA - October 23-27, 2011

Ballet composers

MUSIC CATEGORY

15

A Semantic-based framework for cross-domain recommendation

16

• The previous graph can be considered as a particular instance of a semantic class/category network • The selection of classes and relations is guided by experts on the domains of interest and knowledge repositories CITY was born, died, lived in

located in

was built

POI

TIME

was born, died, lived in

belongs to ARCHITECTURE CATEGORY

has keyword

keyword of KEYWORD

subcategory of

MUSIC CATEGORY

subcategory of

A Generic Semantic-based Framework for Cross-domain Recommendation 2nd Workshop on Information Heterogeneity and Fusion in Recommender Systems (HetRec 2011) 5th ACM Conference on Recommender Systems (RecSys 2011) - Chicago, IL, USA - October 23-27, 2011

MUSIC ARTIST

A Semantic-based framework for cross-domain recommendation

17

• As a proof of concept, we have built our approach by exploiting DBpedia ontology in two stages: 1. 2.

Manually identifying DBpedia classes and relations belonging to the domains of interest to define the semantic-based knowledge representation Automatically obtaining related DBpedia instances according to the classes and relations identified in the first stage 1

Semantic framework

2

Semantic network Wolfgang Amadeus Mozart

Vienna State Opera POI

MUSIC ARTIST

A Generic Semantic-based Framework for Cross-domain Recommendation 2nd Workshop on Information Heterogeneity and Fusion in Recommender Systems (HetRec 2011) 5th ACM Conference on Recommender Systems (RecSys 2011) - Chicago, IL, USA - October 23-27, 2011

Contents

18

• Cross-domain recommendation • Case study: adapting music recommendation to points of interest • A semantic-based framework for cross-domain recommendation • Semantic-based knowledge representation • Semantic graph-based recommendation algorithm

• Preliminary results • Future work

A Generic Semantic-based Framework for Cross-domain Recommendation 2nd Workshop on Information Heterogeneity and Fusion in Recommender Systems (HetRec 2011) 5th ACM Conference on Recommender Systems (RecSys 2011) - Chicago, IL, USA - October 23-27, 2011

Semantic graph-based recommendation algorithm

19

• In the semantic network, a final score for each concept can be computed by weight spreading strategies • Initial weight values for concepts and relations must be established 1

Vienna Austria

Arnold Schoenberg

1

1

Mozart

0.3

1 State Opera of Vienna

0.3

19th century

0.3

Brahms

Bizet

0.6 0.6 0.6

0.5

0.5

0.6

Opera houses

0.4

Ballet venues

0.4

opera

ballet

0.4

Opera composers

0.4

A Generic Semantic-based Framework for Cross-domain Recommendation 2nd Workshop on Information Heterogeneity and Fusion in Recommender Systems (HetRec 2011) 5th ACM Conference on Recommender Systems (RecSys 2011) - Chicago, IL, USA - October 23-27, 2011

Ballet composers

Semantic graph-based recommendation algorithm

20

1·1=1 1

Vienna Austria

Arnold Schoenberg

1 Mozart

1 0.3

1

Bizet

1·0.3=0.3

State Opera of Vienna

0.3

0.3

19th century

0.6 Brahms

0.6 0.6

0.6 0.5

1·0.5=0.5

0.5

Opera houses

0.4

0.4

Opera composers

opera

1·0.5=0.5 Ballet venues

0.4

0.4 ballet

A Generic Semantic-based Framework for Cross-domain Recommendation 2nd Workshop on Information Heterogeneity and Fusion in Recommender Systems (HetRec 2011) 5th ACM Conference on Recommender Systems (RecSys 2011) - Chicago, IL, USA - October 23-27, 2011

Ballet composers

Semantic graph-based recommendation algorithm

21

1 1

Vienna Austria

Arnold Schoenberg

1 Mozart

1 0.3

1

Bizet

0.3

State Opera of Vienna

0.3

0.3

19th century

0.6 Brahms

0.6 0.6

0.6 0.5

0.5

0.5

Opera houses

0.5·0.4=0.2 0.4

Opera composers

0.5·0.4=0.2

0.5 Ballet venues

0.4 opera

0.4

0.4 ballet

A Generic Semantic-based Framework for Cross-domain Recommendation 2nd Workshop on Information Heterogeneity and Fusion in Recommender Systems (HetRec 2011) 5th ACM Conference on Recommender Systems (RecSys 2011) - Chicago, IL, USA - October 23-27, 2011

Ballet composers

Semantic graph-based recommendation algorithm

22

1 1

Vienna Austria

Arnold Schoenberg

1 Mozart

1 0.3

1

Bizet

0.3

State Opera of Vienna

0.3

0.3

19th century

0.6 Brahms

0.6 0.6

0.6 0.5

0.5

0.5

Opera houses

0.2 0.4

0.5 Ballet venues

0.4 opera

Opera composers

0.2

0.2·0.4=0.08

0.4

0.4 ballet

Ballet composers

0.2·0.4=0.08 A Generic Semantic-based Framework for Cross-domain Recommendation 2nd Workshop on Information Heterogeneity and Fusion in Recommender Systems (HetRec 2011) 5th ACM Conference on Recommender Systems (RecSys 2011) - Chicago, IL, USA - October 23-27, 2011

Semantic graph-based recommendation algorithm

23 1·1+0.08·0.6+0.08·0.6+0.3·0.3=1.186

1 1

Vienna Austria

Arnold Schoenberg

1·1+0.08·0.6=1.048 1 Mozart

1

0.08·0.6=0.048 0.3

1

Bizet

0.3

State Opera of Vienna

0.3

0.3·0.3=0.09 0.3

19th century

0.6 Brahms

0.6 0.6

0.6 0.5

0.5

0.5

Opera houses

0.2 0.4

0.5 Ballet venues

0.4 opera

Opera composers

0.2

0.08

0.4

0.4 ballet

Ballet composers

0.08 A Generic Semantic-based Framework for Cross-domain Recommendation 2nd Workshop on Information Heterogeneity and Fusion in Recommender Systems (HetRec 2011) 5th ACM Conference on Recommender Systems (RecSys 2011) - Chicago, IL, USA - October 23-27, 2011

Semantic graph-based recommendation algorithm

24 1·1+0.08·0.6+0.08·0.6+0.3·0.3=1.186

1 1

Vienna Austria

Arnold Schoenberg

1·1+0.08·0.6=1.048 1 Mozart

1 0.08·0.6=0.048 0.3

1

Bizet

0.3

State Opera of Vienna

0.3

0.3·0.3=0.09 0.3

19th century

0.6 Brahms

0.6 0.6

0.6 0.5

0.5

0.5

Opera houses

0.2 0.4

0.5 Ballet venues

0.4 opera

Opera composers

0.2

0.08

0.4

0.4 ballet

Ballet composers

0.08 A Generic Semantic-based Framework for Cross-domain Recommendation 2nd Workshop on Information Heterogeneity and Fusion in Recommender Systems (HetRec 2011) 5th ACM Conference on Recommender Systems (RecSys 2011) - Chicago, IL, USA - October 23-27, 2011

Semantic graph-based recommendation algorithm

25

• The initial weights of an edge in the graph can depend on the relevance of the linked instances and of the corresponding semantic classes

V ( I , I ' )  f rel r ( I , I ' ), rel r (CI , CI ' ) • These relevance values could be assigned in different ways Class relevance Domain expert e.g. a city is more informative to link a POI than a keyword

Relation relevance Entity semantic similarity e.g. co-occurrences of concepts ‘Mozart’ and ‘Vienna’ within a document collection

Instance relevance User profile e.g. an interest in Mozart’s compositions  the relevance for Mozart gets higher

A Generic Semantic-based Framework for Cross-domain Recommendation 2nd Workshop on Information Heterogeneity and Fusion in Recommender Systems (HetRec 2011) 5th ACM Conference on Recommender Systems (RecSys 2011) - Chicago, IL, USA - October 23-27, 2011

Semantic graph-based recommendation algorithm

26

• In general, the weight of an instance not only depends on its relevance value and that of its class, but also inductively on the weights of the predecessors in the network I1 ,, I k W ( I )  g rele ( I ), rel e (CI );W ( I1 ),,W ( I k );V ( I1 , I ),,V ( I k , I )

• To preliminarily test our approach we have implemented a simple retrieval algorithm computing weights by linear combination

V ( I , I ' )    rel r ( I , I ' )  (1   )  rel r (CI , CI ' ),  [0,1] k

W ( I )     W ( I p )  V ( I p , I )  (1   )  rele (C I ),   [0,1] p 1

A Generic Semantic-based Framework for Cross-domain Recommendation 2nd Workshop on Information Heterogeneity and Fusion in Recommender Systems (HetRec 2011) 5th ACM Conference on Recommender Systems (RecSys 2011) - Chicago, IL, USA - October 23-27, 2011

Contents

27

• Cross-domain recommendation • Case study: adapting music recommendation to points of interest • A semantic-based framework for cross-domain recommendation • Semantic-based knowledge representation • Semantic graph-based recommendation algorithm

• Preliminary results • Future work

A Generic Semantic-based Framework for Cross-domain Recommendation 2nd Workshop on Information Heterogeneity and Fusion in Recommender Systems (HetRec 2011) 5th ACM Conference on Recommender Systems (RecSys 2011) - Chicago, IL, USA - October 23-27, 2011

Preliminary results • Example: ‘Vienna State Opera’ (Vienna, Austria)

A Generic Semantic-based Framework for Cross-domain Recommendation 2nd Workshop on Information Heterogeneity and Fusion in Recommender Systems (HetRec 2011) 5th ACM Conference on Recommender Systems (RecSys 2011) - Chicago, IL, USA - October 23-27, 2011

28

Preliminary results

29

• Top 10 musicians for ‘Vienna State Opera’ Music artist Arnold Schoenberg Wolfgang Amadeus Mozart

Emil von Reznicek Alban Berg Ludwig van Beethoven Antonio Vivaldi Giovanni Felice Sances Fritz Kreisler Georg Christoph Wagenseil Antonio Salieri

Top music genres

Born/Death countries

Classical Avant-garde Classical Instrumental Classical Opera Classical Contemporary Classical Instrumental Classical Baroque Classical Baroque Classical Violin Classical Baroque Classical Italian

Austria USA Austria Austria Austria Germany Hungary Austria Germany Austria Italy Austria Italy Austria Austria USA Austria Austria Italy Austria

A Generic Semantic-based Framework for Cross-domain Recommendation 2nd Workshop on Information Heterogeneity and Fusion in Recommender Systems (HetRec 2011) 5th ACM Conference on Recommender Systems (RecSys 2011) - Chicago, IL, USA - October 23-27, 2011

Date 20th century 18th century

20th century 20th century 19th century 18th century 17th century 20th century 18th century 19th century

Preliminary results • Example: found relations between ‘Vienna State Opera’ and ‘Wolfgang Amadeus Mozart’ PLACE OF INTEREST: Vienna State Opera CITY: Vienna, Austria MUSIC ARTIST: Wolfgang Amadeus Mozart ARCHITECTURE CATEGORY: Opera houses KEYWORD: opera MUSIC CATEGORY: Opera composers MUSIC ARTIST: Wolfgang Amadeus Mozart TAG: energetic MUSIC CATEGORY: Opera composers MUSIC ARTIST: Wolfgang Amadeus Mozart TAG: sentimental MUSIC CATEGORY: Opera composers MUSIC ARTIST: Wolfgang Amadeus Mozart MUSIC GENRE: classical MUSIC ARTIST: Wolfgang Amadeus Mozart ARCHITECTURE CATEGORY: Theatres TAG: animated MUSIC GENRE: classical MUSIC ARTIST: Wolfgang Amadeus Mozart A Generic Semantic-based Framework for Cross-domain Recommendation 2nd Workshop on Information Heterogeneity and Fusion in Recommender Systems (HetRec 2011) 5th ACM Conference on Recommender Systems (RecSys 2011) - Chicago, IL, USA - October 23-27, 2011

30

Preliminary results • Example: ‘Wembley Stadium’ (London, UK)

A Generic Semantic-based Framework for Cross-domain Recommendation 2nd Workshop on Information Heterogeneity and Fusion in Recommender Systems (HetRec 2011) 5th ACM Conference on Recommender Systems (RecSys 2011) - Chicago, IL, USA - October 23-27, 2011

31

Preliminary results

32

• Top 10 musicians for ‘Wembley Stadium’ Music artist Beady Eye (Oasis band members) Operahouse The Woe Betides

Skunk Anansie The Fallen Leaves Ivyrise Plastic Ono Band (John Lennon & Yoko Ono) We Are Balboa Goldhawks Teddy Thompson

Top music genres

Born/Death Countries

Rock British Indie Rock British Rock Grunge Rock Female vocalist Garage Acoustic Rock Alternative Experimental Avant-garde Indie Rock Female vocalist Rock British Folk British

UK (origin) UK (origin) UK (origin) UK (origin) UK (origin) UK (origin) UK (origin) Spain-UK (origin) UK (origin) UK USA

A Generic Semantic-based Framework for Cross-domain Recommendation 2nd Workshop on Information Heterogeneity and Fusion in Recommender Systems (HetRec 2011) 5th ACM Conference on Recommender Systems (RecSys 2011) - Chicago, IL, USA - October 23-27, 2011

Date 2009 2006 2008

1994 2004 2007 1969 2003 2009 1976

Preliminary results • Example: found relations between ‘Wembley Stadium’ and ‘Beady Eye’

PLACE OF INTEREST: Wembley Stadium CITY: London, United Kingdom MUSIC ARTIST: Beady Eye TIME: 2007 MUSIC ARTIST: Beady Eye ARCHITECTURE CATEGORY: Music venues ARCHITECTURE CATEGORY: Rock music venues KEYWORD: rock MUSIC CATEGORY: Indie rock MUSIC ARTIST: Beady Eye MUSIC CATEGORY: Rock music MUSIC ARTIST: Beady Eye TAG: strong MUSIC CATEGORY: Rock music MUSIC ARTIST: Beady Eye

A Generic Semantic-based Framework for Cross-domain Recommendation 2nd Workshop on Information Heterogeneity and Fusion in Recommender Systems (HetRec 2011) 5th ACM Conference on Recommender Systems (RecSys 2011) - Chicago, IL, USA - October 23-27, 2011

33

Preliminary results • Automatic extraction of data from DBPedia for an input city • Modular and extensible implementation of the framework • Dataset • 3098 POIs located in 21 European cities ‐ 147.5 POIs/city

• 697 architecture categories ‐ 229 are directly linked to POIs ‐ Avg. 1.4 categories/POI

• 109 keywords describing 181 different architecture categories ‐ Avg. 1.1 keywords/category

• 1568 music artists • 1116 music categories ‐ 309 directly linked to artists (avg. 1.7 categories/artist) ‐ 511 related to keywords (avg. 1.2 keywords/category)

• Time data for 64.72% of the POIs A Generic Semantic-based Framework for Cross-domain Recommendation 2nd Workshop on Information Heterogeneity and Fusion in Recommender Systems (HetRec 2011) 5th ACM Conference on Recommender Systems (RecSys 2011) - Chicago, IL, USA - October 23-27, 2011

34

Contents

35

• Cross-domain recommendation • Case study: adapting music recommendation to points of interest • A semantic-based framework for cross-domain recommendation • Semantic-based knowledge representation • Semantic graph-based recommendation algorithm

• Preliminary results • Future work

A Generic Semantic-based Framework for Cross-domain Recommendation 2nd Workshop on Information Heterogeneity and Fusion in Recommender Systems (HetRec 2011) 5th ACM Conference on Recommender Systems (RecSys 2011) - Chicago, IL, USA - October 23-27, 2011

Future work

36

• Evaluation – user study • Are semantically relations between POIs and music artists really appreciated by users in a recommendation scenario? • Do users find cross-domain recommendations meaningful, and prefer them over nonadapted music suggestions?

• Providing personalized recommendations • Cascade strategy ‐ Obtaining semantically related artists to the input POI ‐ Ranking (adding, removing) artists with a recommender based on the user’s preferences

A Generic Semantic-based Framework for Cross-domain Recommendation 2nd Workshop on Information Heterogeneity and Fusion in Recommender Systems (HetRec 2011) 5th ACM Conference on Recommender Systems (RecSys 2011) - Chicago, IL, USA - October 23-27, 2011

Future work • Initializing entity and relation weights • Exploiting data statistics to estimate the popularity of the semantic entities and relations

• Exploring several weight spreading strategies • Constrained Spreading Activation ‐ Node in/out degrees ‐ Weight propagation thresholds ‐ Path length thresholds • Flow Networks ‐ Ford-Fulkerson’s algorithm to find maximum network flow

• Semi-automatic defining the semantic framework • Automatically exploring DBpedia to identify relevant entities and relations describing the domains of interest A Generic Semantic-based Framework for Cross-domain Recommendation 2nd Workshop on Information Heterogeneity and Fusion in Recommender Systems (HetRec 2011) 5th ACM Conference on Recommender Systems (RecSys 2011) - Chicago, IL, USA - October 23-27, 2011

37

A Generic Semantic-based Framework for Cross-domain Recommendation

Ignacio Fernández-Tobías1, Marius Kaminskas2, Iván Cantador1, Francesco Ricci2 1

Escuela Politécnica Superior, Universidad Autónoma de Madrid, Spain [email protected], [email protected]

2

Faculty of Computer Science, Free University of Bozen-Bolzano, Italy [email protected], [email protected]