Music Recommendation and Discovery in the Long Tail Òscar Celma Doctoral Thesis Defense (Music Technology Group ~ Universitat Pompeu Fabra)
Music Recommendation and Discovery in the Long Tail
Jan 16, 2015
Music consumption is biased towards a few popular artists. For instance, in 2007 only 1% of all digital tracks accounted for 80% of all sales. Similarly, 1,000 albums accounted for 50% of all album sales, and 80% of all albums sold were purchased less than 100 times. There is a need to assist people to filter, discover, personalise and recommend from the huge amount of music content available along the Long Tail.
Current music recommendation algorithms try to accurately predict what people demand to listen to. However, quite often these algorithms tend to recommend popular -or well-known to the user- music, decreasing the effectiveness of the recommendations. These approaches focus on improving the accuracy of the recommendations. That is, try to make accurate predictions about what a user could listen to, or buy next, independently of how useful to the user could be the provided recommendations.
In this Thesis we stress the importance of the user's perceived quality of the recommendations. We model the Long Tail curve of artist popularity to predict -potentially- interesting and unknown music, hidden in the tail of the popularity curve. Effective recommendation systems should promote novel and relevant material (non-obvious recommendations), taken primarily from the tail of a popularity distribution.
The main contributions of this Thesis are: (i) a novel network-based approach for recommender systems, based on the analysis of the item (or user) similarity graph, and the popularity of the items, (ii) a user-centric evaluation that measures the user's relevance and novelty of the recommendations, and (iii) two prototype systems that implement the ideas derived from the theoretical work. Our findings have significant implications for recommender systems that assist users to explore the Long Tail, digging for content they might like.
Current music recommendation algorithms try to accurately predict what people demand to listen to. However, quite often these algorithms tend to recommend popular -or well-known to the user- music, decreasing the effectiveness of the recommendations. These approaches focus on improving the accuracy of the recommendations. That is, try to make accurate predictions about what a user could listen to, or buy next, independently of how useful to the user could be the provided recommendations.
In this Thesis we stress the importance of the user's perceived quality of the recommendations. We model the Long Tail curve of artist popularity to predict -potentially- interesting and unknown music, hidden in the tail of the popularity curve. Effective recommendation systems should promote novel and relevant material (non-obvious recommendations), taken primarily from the tail of a popularity distribution.
The main contributions of this Thesis are: (i) a novel network-based approach for recommender systems, based on the analysis of the item (or user) similarity graph, and the popularity of the items, (ii) a user-centric evaluation that measures the user's relevance and novelty of the recommendations, and (iii) two prototype systems that implement the ideas derived from the theoretical work. Our findings have significant implications for recommender systems that assist users to explore the Long Tail, digging for content they might like.
Welcome message from author
This document is posted to help you gain knowledge. Please leave a comment to let me know what you think about it! Share it to your friends and learn new things together.
Transcript
Music Recommendation and Discovery in the Long Tail
Òscar CelmaDoctoral Thesis Defense
(Music Technology Group ~ Universitat Pompeu Fabra)
PhD defense // UPF // Feb 16th 2009
Music
Recommendation(personalized)
and Discovery(explore large music collections)
in the Long Tail(non-obvious, novel, relevant music)
PhD defense // UPF // Feb 16th 2009
Paradox of choice“The Paradox of Choice: Why More Is Less”, Barry Schwartz (2004)
The problem
PhD defense // UPF // Feb 16th 2009
music overload
• Today(August, 2007)
iTunes: 6M tracks P2P: 15B tracks 53% buy music on line
• Finding unknown, relevant music is hard! Awareness vs. access to content
PhD defense // UPF // Feb 16th 2009
music overload?● Digital Tracks – Sales data for 2007
●
● Nearly 1 billion sold in 2007 ●
● 1% of tracks account for 80% of sales●
● 3.6 million tracks sold less than 100 copies, and ● 1 million tracks sold exactly 1 copy
•
•
•Data from Nielsen Soundscan 'State of the (US) industry' 2007 report
PhD defense // UPF // Feb 16th 2009
the Long Tail of popularity
• Help me find it! [Anderson, 2006]
PhD defense // UPF // Feb 16th 2009
research questions
• 1) How can we evaluate/compare different music recommendation approaches?
• 2) How far into the Long Tail do music recommenders reach?
• 3) How do users perceive novel (unknown to them), non-obvious recommendations?
PhD defense // UPF // Feb 16th 2009
If you like The Beatles you might like ...
PhD defense // UPF // Feb 16th 2009
PhD defense // UPF // Feb 16th 2009
PhD defense // UPF // Feb 16th 2009
PhD defense // UPF // Feb 16th 2009
• popularity bias
• low novelty ratio
PhD defense // UPF // Feb 16th 2009
FACTORS AFFECTING RECOMMENDATIONS:
NoveltyRelevanceDiversityCold startCoverageExplainabilityTemporal effects
PhD defense // UPF // Feb 16th 2009
FACTORS AFFECTING RECOMMENDATIONS:
NoveltyRelevanceDiversityCold startCoverageExplainabilityTemporal effects
PhD defense // UPF // Feb 16th 2009
novelty vs. relevance
PhD defense // UPF // Feb 16th 2009
how can we measure novelty?
• predictive accuracy vs. perceived quality
• metrics MAE, RMSE, P/R/F-measure, ...
Can't measure novelty
Train
Test
PhD defense // UPF // Feb 16th 2009
how can we measure novelty?
• predictive accuracy vs. perceived quality
• metrics MAE, RMSE, P/R/F-measure, ...
Can measure novelty
PhD defense // UPF // Feb 16th 2009
how can we measure relevance?
"The key utility measure is user happiness. It seems reasonable to assume that relevance of the results is the most important factor: blindingly fast, useless answers do not make a user happy."
"Introduction to Information Retrieval" (Manning, Raghavan, and Schutze, 2008)
PhD defense // UPF // Feb 16th 2009
PhD defense // UPF // Feb 16th 2009
research in music recommendation
• Google Scholar
Papers that contain “music recommendation” or “music recommender”
in the title (Accessed October 1st, 2008)
PhD defense // UPF // Feb 16th 2009
research in music recommendation
• ISMIR community
PhD defense // UPF // Feb 16th 2009
music recommendation approaches
• Expert-based
• Collaborative filtering
• Context-based
• Content-based
• Hybrid (combination)
PhD defense // UPF // Feb 16th 2009
music recommendation approaches
• Expert-based AllMusicGuide Pandora
• Collaborative filtering
• Context-based
• Content-based
• Hybrid (combination)
PhD defense // UPF // Feb 16th 2009
music recommendation approaches
• Expert-based
• Collaborative filtering User-Item matrix [Resnick, 1994], [Shardanand, 1995], [Sarwar, 2001]
• Context-based
• Content-based
• Hybrid (combination)
PhD defense // UPF // Feb 16th 2009
music recommendation approaches
• Expert-based
• Collaborative filtering User-Item matrix [Resnick, 1994], [Shardanand, 1995], [Sarwar, 2001]
Similarity Cosine
Adj. cosine
Pearson
SVD / NMF: matrix factorization
• Context-based
• Content-based
• Hybrid (combination)
PhD defense // UPF // Feb 16th 2009
music recommendation approaches
• Expert-based
• Collaborative filtering User-Item matrix [Resnick, 1994], [Shardanand, 1995], [Sarwar, 2001]
Similarity Cosine
Adj. cosine
Pearson
SVD / NMF: matrix factorization Prediction (user-based)
Avg. weighted
PhD defense // UPF // Feb 16th 2009
rock
Edgyheavy metal
90s
Weird
concert
Loud
ContentReviews Lyrics Blogs Social Tags Bios Playlists
music recommendation approaches
• Expert-based
• Collaborative filtering
• Context-based WebMIR [Schedl, 2008]
[Hu&Downie, 2006] [Celma et al., 2006] [Levy&Sandler, 2007] [Baccigalupo, 2008]
[Symeonidis, 2008]
• Content-based
• Hybrid (combination)
thrash
PhD defense // UPF // Feb 16th 2009
music recommendation approaches
• Expert-based
• Collaborative filtering
• Context-based
• Content-based Audio features
Bag-of-frames (MFCC) [Aucouturier, 2004], Rhythm [Gouyon,
2005], Harmony [Gomez, 2006], ... Similarity
KL-divergence: GMM [Aucouturier, 2002]
EMD [Logan, 2001]
Euclidean: PCA [Cano, 2005]
Cosine: mean/var (feature vectors) Ad-hoc
• Hybrid (combination)
PhD defense // UPF // Feb 16th 2009
music recommendation approaches
• Expert-based
• Collaborative filtering
• Context-based
• Content-based
• Hybrid (combination)
Weighted Cascade Switching
PhD defense // UPF // Feb 16th 2009
Work done
PhD defense // UPF // Feb 16th 2009
contributions
PhD defense // UPF // Feb 16th 2009
contributions
1) Network-based evaluationItem Popularity + Complex networks
PhD defense // UPF // Feb 16th 2009
contributions
1) Network-based evaluationItem Popularity + Complex networks
2) User-based evaluation
PhD defense // UPF // Feb 16th 2009
contributions
1) Network-based evaluationItem Popularity + Complex networks
2) User-based evaluation3) Systems
PhD defense // UPF // Feb 16th 2009
contributions
PhD defense // UPF // Feb 16th 2009
contributions
PhD defense // UPF // Feb 16th 2009
complex network analysis :: artists
• 3 Artist similarity (directed) networks CF*: Social-based, incl. item-based CF (Last.fm)
“people who listen to X also listen to Y” CB: Content-based Audio similarity
“X and Y sound similar” EX: Human expert-based (AllMusicGuide)
“X similar to (or influenced by) Y”
PhD defense // UPF // Feb 16th 2009
complex network analysis :: artists
• 3 Artist similarity (directed) networks CF*: Social-based, incl. item-based CF (Last.fm)
“people who listen to X also listen to Y” CB: Content-based Audio similarity
“X and Y sound similar” EX: Human expert-based (AllMusicGuide)
“X similar to (or influenced by) Y”
PhD defense // UPF // Feb 16th 2009
complex network analysis :: artists
• Small-world networks [Watts & Strogatz, 1998]
Network traverse in a few clicks
PhD defense // UPF // Feb 16th 2009
• Indegree – avg. neighbor indegree correlation r = Pearson correlation [Newman, 2002]
complex network analysis :: artists
PhD defense // UPF // Feb 16th 2009
complex network analysis :: artists
• Indegree – avg. neighbor indegree correlation
PhD defense // UPF // Feb 16th 2009
complex network analysis :: artists
• Indegree – avg. neighbor indegree correlation
PhD defense // UPF // Feb 16th 2009
complex network analysis :: artists
• Indegree – avg. neighbor indegree correlation
Kin(Bruce Springsteen)=534=>avg(Kin(sim(Bruce Springsteen)))=463
PhD defense // UPF // Feb 16th 2009
complex network analysis :: artists
• Indegree – avg. neighbor indegree correlation
Kin(Bruce Springsteen)=534=>avg(Kin(sim(Bruce Springsteen)))=463
Kin(Mike Shupp)=14=>avg(Kin(sim(Mike Shupp)))=15
PhD defense // UPF // Feb 16th 2009
complex network analysis :: artists
• Indegree – avg. neighbor indegree correlation
Kin(Bruce Springsteen)=534=>avg(Kin(sim(Bruce Springsteen)))=463
Kin(Mike Shupp)=14=>avg(Kin(sim(Mike Shupp)))=15
Homophily effect!
PhD defense // UPF // Feb 16th 2009
• Indegree – avg. neighbor indegree correlation Last.fm presents assortative mixing (homophily)
Artists with high indegree are connected together, and similarly for low indegree artists
complex network analysis :: artists
PhD defense // UPF // Feb 16th 2009
complex network analysis :: artists
• Last.fm is a scale-free network [Barabasi, 2000]
power law exponent for the cumulative indegree distribution [Clauset, 2007]
A few artists (hubs) control the network
PhD defense // UPF // Feb 16th 2009
complex network analysis :: artists
|------------|---------|-----|-----------|
| | Last.fm | CB | Exp (AMG) |
|------------|---------|-----|-----------|
|Small World | yes | yes | yes |
| | | | |
|Ass. mixing | yes | No | No |
| | | | |
| Scale-free | yes | No | No |
|------------|---------|-----|-----------|
• Summary: artist similarity networks
Last.fm artist similarity network resembles to a social network (e.g. facebook)
PhD defense // UPF // Feb 16th 2009
complex network analysis :: artists
• But, still some remaining questions...
Are the hubs the most popular artists?
How can we navigate along the Long Tail, using the artist similarity network?
PhD defense // UPF // Feb 16th 2009
contributions
Long Tail analysis
PhD defense // UPF // Feb 16th 2009
the Long Tail in music
• last.fm dataset (~260K artists)
PhD defense // UPF // Feb 16th 2009
the Long Tail in music
• last.fm dataset (~260K artists)
radiohead (40,762,895)
red hot chili peppers (37,564,100)
muse (30,548,064)
the beatles (50,422,827)
death cab for cutie (29,335,085)pink floyd (28,081,366)coldplay (27,120,352)
metallica (25,749,442)
PhD defense // UPF // Feb 16th 2009
the Long Tail model [Kilkki, 2007]
• F(x) = Cumulative distribution up to x
PhD defense // UPF // Feb 16th 2009
the Long Tail model [Kilkki, 2007]
• Top-8 artists: F(8)~ 3.5% of total plays
50,422,827 the beatles40,762,895 radiohead37,564,100 red hot chili peppers30,548,064 muse29,335,085 death cab for cutie28,081,366 pink floyd27,120,352 coldplay25,749,442 metallica
PhD defense // UPF // Feb 16th 2009
the Long Tail model [Kilkki, 2007]
• Split the curve in three parts
(82 artists) (6,573 artists) (~254K artists)
PhD defense // UPF // Feb 16th 2009
contributions
Long Tail analysis +
PhD defense // UPF // Feb 16th 2009
artist indegree vs. artist popularity
• Are the network hubs the most popular artists?
???
PhD defense // UPF // Feb 16th 2009
artist indegree vs. artist popularity Last.fm: correlation between Kin and playcounts
r = 0.621
PhD defense // UPF // Feb 16th 2009
artist indegree vs. artist popularity Audio CB similarity: no correlation
r = 0.032
PhD defense // UPF // Feb 16th 2009
artist indegree vs. artist popularity Expert: correlation between Kin and playcounts
r = 0.475
PhD defense // UPF // Feb 16th 2009
navigation along the Long Tail
• “From Hits to Niches” # clicks to reach a Tail artist, starting in the Head
how many clicks?
PhD defense // UPF // Feb 16th 2009
navigation along the Long Tail
• “From Hits to Niches” Audio CB similarity example (VIDEO)
PhD defense // UPF // Feb 16th 2009
navigation along the Long Tail
• “From Hits to Niches” Audio CB similarity example
Bruce Springsteen (14,433,411 plays)
PhD defense // UPF // Feb 16th 2009
navigation along the Long Tail
• “From Hits to Niches” Audio CB similarity example
Bruce Springsteen (14,433,411 plays) The Rolling Stones (27,720,169 plays)
PhD defense // UPF // Feb 16th 2009
navigation along the Long Tail
• “From Hits to Niches” Audio CB similarity example
Bruce Springsteen (14,433,411 plays) The Rolling Stones (27,720,169 plays) Mike Shupp (577 plays)
PhD defense // UPF // Feb 16th 2009
artist similarity vs. artist popularity
• navigation in the Long Tail Similar artists, given an artist in the HEAD part:
Also, it can be seen as a Markovian Stochastic process...
54,68%
(0%)
45,32%64,74%
28,80%6,46%
60,92%33,26%
5,82%
CF CB EXP
Head Mid Tail Head Mid Tail Head Mid Tail
PhD defense // UPF // Feb 16th 2009
artist similarity vs. artist popularity
• navigation in the Long Tail Markov transition matrix
PhD defense // UPF // Feb 16th 2009
artist similarity vs. artist popularity
• navigation in the Long Tail Markov transition matrix
PhD defense // UPF // Feb 16th 2009
artist similarity vs. artist popularity
• navigation in the Long Tail Last.fm Markov transition matrix
PhD defense // UPF // Feb 16th 2009
artist similarity vs. artist popularity
• navigation in the Long Tail From Head to Tail, with P(T|H) > 0.4 Number of clicks needed
CF : 5 CB : 2 EXP: 2 HEAD
TAIL
#clicks?
PhD defense // UPF // Feb 16th 2009
artist popularity
|-----------------------|---------|-----|-----------|
| | Last.fm | CB | Exp (AMG) |
|-----------------------|---------|-----|-----------|
| Indegree / popularity| yes | no | yes |
| | | | |
|Similarity / popularity| yes | no | no |
|-----------------------|---------|-----|-----------|
Summary
PhD defense // UPF // Feb 16th 2009
summary: complex networks+popularity|-----------------------|---------|-----|-----------|
| | Last.fm | CB | Exp (AMG) |
|-----------------------|---------|-----|-----------|
| Small World | yes | yes | yes |
| | | | |
| Scale-free | yes | no | no |
| | | | |
| Ass. mixing | yes | no | no |
|-----------------------|---------|-----|-----------|
| Indegree / popularity| yes | no | yes |
| | | | |
|Similarity / popularity| yes | no | no |
|-----------------------|---------|-----|-----------|
| POPULARITY BIAS | YES | NO | FAIRLY |
|-----------------------|---------|-----|-----------|
PhD defense // UPF // Feb 16th 2009
contributions
1) Network-based evaluationItem Popularity + Complex networks
2) User-based evaluation3) Systems
PhD defense // UPF // Feb 16th 2009
contribution #2: User-based evaluation
• How do users perceive novel, non-obvious recommendations? Survey
288 participants Method: blind music recommendation
no metadata (artist name, song title) only 30 sec. audio excerpt
PhD defense // UPF // Feb 16th 2009
music recommendation survey
• 3 approaches: CF: Social-based Last.fm similar tracks CB: Pure audio content-based similarity HYbrid: AMG experts + audio CB to rerank songs
(Not a combination of the two previous approaches)
• User profile: last.fm, top-10 artists
• Procedure Do you recognize the song?
Yes, Only Artist, Both Artist and Song title Do you like the song?
Rating: [1..5]
PhD defense // UPF // Feb 16th 2009
PhD defense // UPF // Feb 16th 2009
music recommendation survey: results
• Overall results
PhD defense // UPF // Feb 16th 2009
music recommendation survey: results
• Overall results
PhD defense // UPF // Feb 16th 2009
music recommendation survey: results
• Familiar recommendations (Artist & Song)
PhD defense // UPF // Feb 16th 2009
music recommendation survey: results
• Ratings for novel recommendations
PhD defense // UPF // Feb 16th 2009
music recommendation survey: results
• Ratings for novel recommendations
one-way ANOVA within subjects (F=29.13, p<0.05) Tukey's test (pairwise comparison)
PhD defense // UPF // Feb 16th 2009
music recommendation survey: results
• % of novel recommendations
PhD defense // UPF // Feb 16th 2009
music recommendation survey: results
• % of novel recommendations
one-way ANOVA within subjects (F=7,57, p<0.05) Tukey's test (pairwise comparison)
PhD defense // UPF // Feb 16th 2009
music recommendation survey: results
• Novel recommendations
Last.fm provides less % of novel songs, but of higher quality
PhD defense // UPF // Feb 16th 2009
contributions
1) Network-based evaluationItem Popularity + Complex networks
2) User-based evaluation3) Systems
PhD defense // UPF // Feb 16th 2009
Why?besides better understanding of music recommendation...
Open questions in the State of the Art in music discovery & recommendation:
Is it possible to create a music discovery engine exploiting the music content in the WWW? How to build it? How can we describe the available music content?
=> SearchSounds
Is it possible to recommend, filter and personalize music content available on the WWW? How to describe a user profile? What can we recommend beyond similar artists?
=> FOAFing the Music
PhD defense // UPF // Feb 16th 2009
contribution #3: two complete systems
• Searchsounds Music search engine
keyword based search “More like this” (audio CB)
PhD defense // UPF // Feb 16th 2009
contribution #3: two complete systems
• Searchsounds
Crawl MP3 blogs > 400K songs analyzed
PhD defense // UPF // Feb 16th 2009
contribution #3: two complete systems
• Searchsounds Further work: improve song descriptions using
Auto-tagging [Lamere, 2008] [Turnbull, 2007]
audio CB similarity [Sordo et al., 2007]
tags from the text (music dictionary)
Feedback from the usersthumbs-up/downtag audio content
PhD defense // UPF // Feb 16th 2009
contribution #3: two complete systems
• FOAFing the music Music recommendation
constantly gathering music related info via RSS feeds It offers:
artist recommendationnew music releases (iTunes, Amazon, eMusic, Rhapsody, Yahoo! Shopping)
album reviewsconcerts close to user's locationsrelated mp3 blogs and podcasts
PhD defense // UPF // Feb 16th 2009
contribution #3: two complete systems
• FOAFing the music Integrates different user accounts (circa 2005!)
Semantic Web (FOAF, OWL/RDF) + Web 2.0 2nd prize Semantic Web Challenge (ISWC 2006)
PhD defense // UPF // Feb 16th 2009
contribution #3: two complete systems
• FOAFing the music Further work:
Follow Linking Open Data best practices Link our music recommendation ontology with
Music Ontology [Raimond et al., 2007]
(Automatically) add external information from:MyspaceJamendoGarageband...
PhD defense // UPF // Feb 16th 2009
summary of contributions :: research questions
• 1) How can we evaluate/compare different music recommendation approaches?
• 2) How far into the Long Tail do music recommenders reach?
• 3) How do users perceive novel (unknown to them), non-obvious recommendations?
PhD defense // UPF // Feb 16th 2009
summary of contributions :: research questions
• 1) How can we evaluate/compare different music recommendation approaches? Objective framework comparing music rec.
approaches (CF, CB, EX) using Complex Network analysis
Highlights fundamental differences among the approaches
• 2) How far into the Long Tail do music recommenders reach?
• 3) How do users perceive novel (unknown to them), non-obvious recommendations?
PhD defense // UPF // Feb 16th 2009
summary of contributions :: research questions
• 1) How can we evaluate/compare different music recommendation approaches?
• 2) How far into the Long Tail do music recommenders reach? Combine 1) with the Long Tail model, and Markov
model theory Highlights differences in terms of discovery and
navigation
• 3) How do users perceive novel (unknown to them), non-obvious recommendations?
PhD defense // UPF // Feb 16th 2009
summary of contributions :: research questions
• 1) How can we evaluate/compare different music recommendation approaches?
• 2) How far into the Long Tail do music recommenders reach?
• 3) How do users perceive novel (unknown to them), non-obvious recommendations? Survey with 288 participants Still room to improve novelty (3/5 or less...)
To appreciate novelty users need to understand the recommendations
PhD defense // UPF // Feb 16th 2009
summary of contributions :: research questions
• 1) How can we evaluate/compare different music recommendation approaches?
• 2) How far into the Long Tail do music recommenders reach?
• 3) How do users perceive novel (unknown to them), non-obvious recommendations?
=> Systems that perform best (CF) do not exploit the
Long Tail, and Systems that can ease Long Tail navigation (CB) do
not perform good enough Combine (hybrid) different approaches!
PhD defense // UPF // Feb 16th 2009
Systems that perform best (CF) do not exploit the Long Tail, and
Systems that can ease Long Tail navigation (CB) do not perform good enough
Combine different approaches!
PhD defense // UPF // Feb 16th 2009
summary of contributions :: systems
• Furthermore... 2 web systems that improved existing State of the
Art work in music discovery and recommendation Searchsounds: music search engine exploiting music
related content in the WWW FOAFing the Music: music recommender based on a
FOAF user profile, also offering a number of extra features to complement the recommendations
PhD defense // UPF // Feb 16th 2009
further work :: limitations
• 1) How can we evaluate/compare different recommendations approaches? Dynamic networks [Leskovec, 2008]
track item similarity over time track user's taste over time trend and hype detection
PhD defense // UPF // Feb 16th 2009
further work :: limitations
• 2) How far into the Long Tail do recommendation algorithms reach? Intercollections
how to detect bad quality music in the tail?
PhD defense // UPF // Feb 16th 2009
further work :: limitations
• 3) How do users perceive novel, non-obvious recommendations? User understanding [Jennings, 2007]
savant, enthusiast, casual, indifferent Transparent, steerable recommendations [Lamere &
Maillet, 2008]
Why? as important as What?
PhD defense // UPF // Feb 16th 2009
summary: articles
• #1) Network-based evaluation for RS O. Celma and P. Cano. “From hits to niches? or how
popular artists can bias music recommendation and discovery”. ACM KDD, 2008.
J. Park, O. Celma, M. Koppenberger, P. Cano, and J. M. Buldu. “The social network of contemporary popular musicians”. Journal of Bifurcation and Chaos (IJBC), 17:2281–2288, 2007.
M. Zanin, P. Cano, J. M. Buldu, and O. Celma. “Complex networks in recommendation systems”. WSEAS, 2008
P. Cano, O. Celma, M. Koppenberger, and J. M. Buldu “Topology of music recommendation networks”. Journal Chaos (16), 2006.
• #2) User-based evaluation for RS O. Celma and P. Herrera. “A new approach to
evaluating novel recommendations”. ACM RecSys, 2008.
PhD defense // UPF // Feb 16th 2009
summary: articles
• #3) Prototypes FOAFing the Music
O. Celma and X. Serra. “FOAFing the music: Bridging the semantic gap in music recommendation”. Journal of Web Semantics, 6(4):250–256, 2008.
O. Celma. “FOAFing the music”. 2nd Prize Semantic Web Challenge ISWC, 2006.
O. Celma, M. Ramirez, and P. Herrera. “FOAFing the music: A music recommendation system based on rss feeds and user preferences”. ISMIR, 2005.
O. Celma, M. Ramirez, and P. Herrera. “Getting music recommendations and filtering newsfeeds from foaf descriptions”. Scripting for the Semantic Web, ESWC, 2005.
PhD defense // UPF // Feb 16th 2009
summary: articles
• #3) Prototypes Searchsounds
O. Celma, P. Cano, and P. Herrera. “Search sounds: An audio crawler focused on weblogs”. ISMIR, 2006.
V. Sandvold, T. Aussenac, O. Celma, and P. Herrera. “Good vibrations: Music discovery through personal musical concepts”. ISMIR, 2006.
M. Sordo, C. Laurier, and O. Celma. “Annotating music collections: how content-based similarity helps to propagate labels”. ISMIR, 2007.
PhD defense // UPF // Feb 16th 2009
summary: articles
• Misc. (mainly MM semantics) R. Garcia C. Tsinaraki, O. Celma, and S. Christodoulakis.
“Multimedia Content Description using Semantic Web Languages” book, Chapter 2. Springer–Verlag, 2008.
O. Celma and Y. Raimond. “Zempod: A semantic web approach to podcasting”. Journal of Web Semantics, 6(2):162–169, 2008.
S. Boll, T. Burger, O. Celma, C. Halaschek-Wiener, E. Mannens. “Multimedia vocabularies on the Semantic Web”. W3C Technical report, 2007.
O. Celma, P. Herrera, and X. Serra. “Bridging the music semantic gap”. SAMT, 2006.
R. Garcia and O. Celma. “Semantic integration and retrieval of multimedia metadata”. ESWC, 2005
PhD defense // UPF // Feb 16th 2009
summary: articles R. Troncy, O. Celma, S. Little, R. Garcia and C. Tsinaraki.
“MPEG-7 based multimedia ontologies: Interoperability support or interoperability issue?” MARESO, 2007.
M. Sordo, O. Celma, M. Blech, and E. Guaus. “The quest for musical genres: Do the experts and the wisdom of crowds agree?”. ISMIR, 2008.
• Music Recommendation Tutorials -- with Paul Lamere
ACM MM, 2008 (Vancouver, Canada) ISMIR, 2007 (Vienna, Austria) MICAI, 2007 (Aguascalientes, Mexico)
PhD defense // UPF // Feb 16th 2009
summary: dissemination
• PhD Webpage http://mtg.upf.edu/~ocelma/PhD
PDF Source code
Long Tail Model in R
ReferencesCiteulike
Related linksdelicious
PhD defense // UPF // Feb 16th 2009
acknowledgments
NB: The complete list of acknowledgments can be found in the document
Music Recommendation and Discovery in the Long Tail
Òscar CelmaDoctoral Thesis Defense
(Music Technology Group ~ Universitat Pompeu Fabra)
PICA-PICAUPF-Tanger, 3rd floor
Related Documents
![[HetRec2011@RecSys]Experience Discovery: Hybrid Recommendation of Student Activities using Social Network Data](https://static.cupdf.com/doc/110x72/555a3e70d8b42ae1398b4cf3/hetrec2011recsysexperience-discovery-hybrid-recommendation-of-student-activities-using-social-network-data.jpg)
