This document summarizes a presentation on generating personalized music playlists by leveraging social media sources. It discusses how the exponential growth of available online music has changed listening habits but created an information overload problem. It proposes personalized playlists as a solution and describes an approach that extracts a user's explicit music preferences from Facebook and generates new playlist recommendations by comparing the user's preferences to similar artists using distributional models. The system is called Play.me and generates personalized playlists by analyzing social media data, enriching explicit preferences, and recommending popular songs from resulting artists.
The Opposite of Transportation Livability is KillabilityAndy Boenau
Β
Livability is a concept that has enjoyed tremendous popularity in recent years. The Federal Highway Administration established a formal βLivability Initiativeβ and in 2010, published a guidebook to educate transportation planning and design professionals.
But even with the enormous amount of data showing direct and tangible connections between street design and public health and safety (i.e. livability), bad design continues to show itself on a regular basis on our street networks.
If good design promotes livability, then bad design must promote the opposite of livabilityβ¦killability.
City streets are intended for people of all ages and physical abilities. Let's design livable streets. Let's *reclaim* our streets!
This presentation was originally given in a Pecha Kucha (20x20) format during the 2013 American Planning Association national conference.
Leveraging Social Media To Raise Funds for Nonprofit OrganizationsAbila
Β
The third session in the Web-wise series, you will learn to understand the recent explosion of social media and its application to nonprofit organizations, presented by Dan Gonzalez, Web Manager, Sage Nonprofit Solutions.
Content Marketing presentation to UniSA Marketing by Will Fuller and Gavin Klose from FULLER Brand + Communication, Adelaide South Australia. What is content marketing? How many marketers are using content marketing? How much marketing budget is being allocated to content marketing in Australia? How is media consumed and how is it is changing? What type of media is consumed in digital especially on mobile devices? What is the content marketing sweet spot. A strategic framework for content marketing starting with strategy, channel creation, editorial planning, content creation, distribution and measurement. Content marketing cases studies for Xerox, Commonwealth Bank, Hahn Beer and Carnegie Mellon.
Presented at ACCU 2014 (accu.org)
Are estimates an essential part of project planning and delivery or a waste of everybody's time? As is so often the case the answer is neither and both. In this session we discover that there is more than one kind of estimate and examine how they are typically used in an agile context.
We look at what some of the great minds have said on the subject, from Steve McConnell to Demarco and Lister. We'll also consider the need for estimates from the viewpoint of the business people who have to decide whether a project proposal should receive budget. Picking up the 'No Estimates' discussion from Twitter, we'll see if there's a case to be made for always refusing to provide estimates or whether there are times that some sorts of estimation is valuable.
I may not change your mind, but I intend to widen your perspective.
Don't Leave Your Facilities Needs to Chance: From Game Plan to Master PlanSightlines
Β
This presentation explores what facilities leaders can do when rolling the dice doesn't work regarding the management of deferred maintenance. You'll also learn how to:
- Maximize the value of a deferred maintenance assessment
- Integrate deferred maintenance data with a master plan
- Optimize institutional resources to mitigate risk
- Be a partner in program success rather than a follower
Intelligenza Artificiale e Social Media - Monitoraggio della Farnesina e La M...Cataldo Musto
Β
Convegno a Porte Chiuse dell'Associazione Italiana per l'Intelligenza Artificiale insieme al Ministero per gli Affari Esteri e la Cooperazione Internazionale - 30 Giugno 2021
Exploring the Effects of Natural Language Justifications in Food Recommender ...Cataldo Musto
Β
Cataldo Musto, Alain D. Starke, Christoph Trattner, Amon Rapp, and Giovanni Semeraro. 2021. Exploring the Effects of Natural Language Justifications in Food Recommender Systems. In Proceedings of the 29th ACM
Conference on User Modeling, Adaptation and Personalization (UMAP β21), June 21β25, 2021, Utrecht, Netherlands. ACM, New York, NY, USA, 11 pages. https://doi.org/10.1145/3450613.3456827
The Opposite of Transportation Livability is KillabilityAndy Boenau
Β
Livability is a concept that has enjoyed tremendous popularity in recent years. The Federal Highway Administration established a formal βLivability Initiativeβ and in 2010, published a guidebook to educate transportation planning and design professionals.
But even with the enormous amount of data showing direct and tangible connections between street design and public health and safety (i.e. livability), bad design continues to show itself on a regular basis on our street networks.
If good design promotes livability, then bad design must promote the opposite of livabilityβ¦killability.
City streets are intended for people of all ages and physical abilities. Let's design livable streets. Let's *reclaim* our streets!
This presentation was originally given in a Pecha Kucha (20x20) format during the 2013 American Planning Association national conference.
Leveraging Social Media To Raise Funds for Nonprofit OrganizationsAbila
Β
The third session in the Web-wise series, you will learn to understand the recent explosion of social media and its application to nonprofit organizations, presented by Dan Gonzalez, Web Manager, Sage Nonprofit Solutions.
Content Marketing presentation to UniSA Marketing by Will Fuller and Gavin Klose from FULLER Brand + Communication, Adelaide South Australia. What is content marketing? How many marketers are using content marketing? How much marketing budget is being allocated to content marketing in Australia? How is media consumed and how is it is changing? What type of media is consumed in digital especially on mobile devices? What is the content marketing sweet spot. A strategic framework for content marketing starting with strategy, channel creation, editorial planning, content creation, distribution and measurement. Content marketing cases studies for Xerox, Commonwealth Bank, Hahn Beer and Carnegie Mellon.
Presented at ACCU 2014 (accu.org)
Are estimates an essential part of project planning and delivery or a waste of everybody's time? As is so often the case the answer is neither and both. In this session we discover that there is more than one kind of estimate and examine how they are typically used in an agile context.
We look at what some of the great minds have said on the subject, from Steve McConnell to Demarco and Lister. We'll also consider the need for estimates from the viewpoint of the business people who have to decide whether a project proposal should receive budget. Picking up the 'No Estimates' discussion from Twitter, we'll see if there's a case to be made for always refusing to provide estimates or whether there are times that some sorts of estimation is valuable.
I may not change your mind, but I intend to widen your perspective.
Don't Leave Your Facilities Needs to Chance: From Game Plan to Master PlanSightlines
Β
This presentation explores what facilities leaders can do when rolling the dice doesn't work regarding the management of deferred maintenance. You'll also learn how to:
- Maximize the value of a deferred maintenance assessment
- Integrate deferred maintenance data with a master plan
- Optimize institutional resources to mitigate risk
- Be a partner in program success rather than a follower
Intelligenza Artificiale e Social Media - Monitoraggio della Farnesina e La M...Cataldo Musto
Β
Convegno a Porte Chiuse dell'Associazione Italiana per l'Intelligenza Artificiale insieme al Ministero per gli Affari Esteri e la Cooperazione Internazionale - 30 Giugno 2021
Exploring the Effects of Natural Language Justifications in Food Recommender ...Cataldo Musto
Β
Cataldo Musto, Alain D. Starke, Christoph Trattner, Amon Rapp, and Giovanni Semeraro. 2021. Exploring the Effects of Natural Language Justifications in Food Recommender Systems. In Proceedings of the 29th ACM
Conference on User Modeling, Adaptation and Personalization (UMAP β21), June 21β25, 2021, Utrecht, Netherlands. ACM, New York, NY, USA, 11 pages. https://doi.org/10.1145/3450613.3456827
Natural Language Justifications for Recommender Systems Exploiting Text Summa...Cataldo Musto
Β
Natural Language Justifications for Recommender Systems Exploiting Text Summarization and Sentiment Analysis - AI*IA 2019 - Italian Conference on Artificial Intelligence
A Framework for Holistic User Modeling Merging Heterogeneous Digital FootprintsCataldo Musto
Β
A Framework for Holistic User Modeling Merging Heterogeneous Digital Footprints - HUM 2018 β Holistic User Modeling Workshop jointly held with
UMAP 2018 β 26th International
Conference on User Modeling,
Adaptation and Personalization
Singapore - July 8, 2018
The Art of the Pitch: WordPress Relationships and SalesLaura Byrne
Β
Clients donβt know what they donβt know. What web solutions are right for them? How does WordPress come into the picture? How do you make sure you understand scope and timeline? What do you do if sometime changes?
All these questions and more will be explored as we talk about matching clientsβ needs with what your agency offers without pulling teeth or pulling your hair out. Practical tips, and strategies for successful relationship building that leads to closing the deal.
Accelerate your Kubernetes clusters with Varnish CachingThijs Feryn
Β
A presentation about the usage and availability of Varnish on Kubernetes. This talk explores the capabilities of Varnish caching and shows how to use the Varnish Helm chart to deploy it to Kubernetes.
This presentation was delivered at K8SUG Singapore. See https://feryn.eu/presentations/accelerate-your-kubernetes-clusters-with-varnish-caching-k8sug-singapore-28-2024 for more details.
Epistemic Interaction - tuning interfaces to provide information for AI supportAlan Dix
Β
Paper presented at SYNERGY workshop at AVI 2024, Genoa, Italy. 3rd June 2024
https://alandix.com/academic/papers/synergy2024-epistemic/
As machine learning integrates deeper into human-computer interactions, the concept of epistemic interaction emerges, aiming to refine these interactions to enhance system adaptability. This approach encourages minor, intentional adjustments in user behaviour to enrich the data available for system learning. This paper introduces epistemic interaction within the context of human-system communication, illustrating how deliberate interaction design can improve system understanding and adaptation. Through concrete examples, we demonstrate the potential of epistemic interaction to significantly advance human-computer interaction by leveraging intuitive human communication strategies to inform system design and functionality, offering a novel pathway for enriching user-system engagements.
Key Trends Shaping the Future of Infrastructure.pdfCheryl Hung
Β
Keynote at DIGIT West Expo, Glasgow on 29 May 2024.
Cheryl Hung, ochery.com
Sr Director, Infrastructure Ecosystem, Arm.
The key trends across hardware, cloud and open-source; exploring how these areas are likely to mature and develop over the short and long-term, and then considering how organisations can position themselves to adapt and thrive.
UiPath Test Automation using UiPath Test Suite series, part 4DianaGray10
Β
Welcome to UiPath Test Automation using UiPath Test Suite series part 4. In this session, we will cover Test Manager overview along with SAP heatmap.
The UiPath Test Manager overview with SAP heatmap webinar offers a concise yet comprehensive exploration of the role of a Test Manager within SAP environments, coupled with the utilization of heatmaps for effective testing strategies.
Participants will gain insights into the responsibilities, challenges, and best practices associated with test management in SAP projects. Additionally, the webinar delves into the significance of heatmaps as a visual aid for identifying testing priorities, areas of risk, and resource allocation within SAP landscapes. Through this session, attendees can expect to enhance their understanding of test management principles while learning practical approaches to optimize testing processes in SAP environments using heatmap visualization techniques
What will you get from this session?
1. Insights into SAP testing best practices
2. Heatmap utilization for testing
3. Optimization of testing processes
4. Demo
Topics covered:
Execution from the test manager
Orchestrator execution result
Defect reporting
SAP heatmap example with demo
Speaker:
Deepak Rai, Automation Practice Lead, Boundaryless Group and UiPath MVP
Transcript: Selling digital books in 2024: Insights from industry leaders - T...BookNet Canada
Β
The publishing industry has been selling digital audiobooks and ebooks for over a decade and has found its groove. Whatβs changed? What has stayed the same? Where do we go from here? Join a group of leading sales peers from across the industry for a conversation about the lessons learned since the popularization of digital books, best practices, digital book supply chain management, and more.
Link to video recording: https://bnctechforum.ca/sessions/selling-digital-books-in-2024-insights-from-industry-leaders/
Presented by BookNet Canada on May 28, 2024, with support from the Department of Canadian Heritage.
Securing your Kubernetes cluster_ a step-by-step guide to success !KatiaHIMEUR1
Β
Today, after several years of existence, an extremely active community and an ultra-dynamic ecosystem, Kubernetes has established itself as the de facto standard in container orchestration. Thanks to a wide range of managed services, it has never been so easy to set up a ready-to-use Kubernetes cluster.
However, this ease of use means that the subject of security in Kubernetes is often left for later, or even neglected. This exposes companies to significant risks.
In this talk, I'll show you step-by-step how to secure your Kubernetes cluster for greater peace of mind and reliability.
FIDO Alliance Osaka Seminar: Passkeys and the Road Ahead.pdf
Β
Leveraging Social Media Sources to Generate Personalized Music Playlists
1. EC-Web 2012 - 13th International Conference on Electronic Commerce and Web Technologies
Vienna (Austria), 04.09.2012
Cataldo Musto, Giovanni Semeraro, Pasquale Lops, Marco de Gemmis, Fedelucio Narducci
Leveraging Social Media Sources to
Generate Personalized Music Playlists
2. Some stats
28,000,000 songs available on iTunes Store (*)
around 31,000 hours of music
a typical user spends 1.5 hours for day listening to music
=
56 years
to listen to the whole iTunes Library
(*) http://www.digitalmusicnews.com/permalink/2012/120425itunes
C. Musto, G. Semeraro, P. Lops, M. de Gemmis, F. Narducci.
Leveraging Social Media Sources to Generate Personalized Music Playlists - EC-WEB 2012 - 04.09.12
3. exponential growth
of the available music
C. Musto, G. Semeraro, P. Lops, M. de Gemmis, F. Narducci.
Leveraging Social Media Sources to Generate Personalized Music Playlists - EC-WEB 2012 - 04.09.12
4. online music libraries totally
changed our listening habits
C. Musto, G. Semeraro, P. Lops, M. de Gemmis, F. Narducci.
Leveraging Social Media Sources to Generate Personalized Music Playlists - EC-WEB 2012 - 04.09.12
5. Information Overload
C. Musto, G. Semeraro, P. Lops, M. de Gemmis, F. Narducci.
Leveraging Social Media Sources to Generate Personalized Music Playlists - EC-WEB 2012 - 04.09.12
6. paradox of choice
(Barry Schwartz, TED talk βWhy more is lessβ)
C. Musto, G. Semeraro, P. Lops, M. de Gemmis, F. Narducci.
Leveraging Social Media Sources to Generate Personalized Music Playlists - EC-WEB 2012 - 04.09.12
7. what music should I listen to?
C. Musto, G. Semeraro, P. Lops, M. de Gemmis, F. Narducci.
Leveraging Social Media Sources to Generate Personalized Music Playlists - EC-WEB 2012 - 04.09.12
8. solution
personalization.
C. Musto, G. Semeraro, P. Lops, M. de Gemmis, F. Narducci.
Leveraging Social Media Sources to Generate Personalized Music Playlists - EC-WEB 2012 - 04.09.12
9. solution
personalized music playlists
C. Musto, G. Semeraro, P. Lops, M. de Gemmis, F. Narducci.
Leveraging Social Media Sources to Generate Personalized Music Playlists - EC-WEB 2012 - 04.09.12
10. Is this something new?
No.
C. Musto, G. Semeraro, P. Lops, M. de Gemmis, F. Narducci.
Leveraging Social Media Sources to Generate Personalized Music Playlists - EC-WEB 2012 - 04.09.12
11. Amazon.com
Recommendations
C. Musto, G. Semeraro, P. Lops, M. de Gemmis, F. Narducci.
Leveraging Social Media Sources to Generate Personalized Music Playlists - EC-WEB 2012 - 04.09.12
12. Genius @iTunes
Recommendations
C. Musto, G. Semeraro, P. Lops, M. de Gemmis, F. Narducci.
Leveraging Social Media Sources to Generate Personalized Music Playlists - EC-WEB 2012 - 04.09.12
13. All the state of the art
platforms share an
important drawback.
C. Musto, G. Semeraro, P. Lops, M. de Gemmis, F. Narducci.
Leveraging Social Media Sources to Generate Personalized Music Playlists - EC-WEB 2012 - 04.09.12
14. need for
explicit
information
about
user interests.
C. Musto, G. Semeraro, P. Lops, M. de Gemmis, F. Narducci.
Leveraging Social Media Sources to Generate Personalized Music Playlists - EC-WEB 2012 - 04.09.12
15. training is a bottleneck.
C. Musto, G. Semeraro, P. Lops, M. de Gemmis, F. Narducci.
Leveraging Social Media Sources to Generate Personalized Music Playlists - EC-WEB 2012 - 04.09.12
16. social media
changed the rules for information
management and knowledge acquisition
C. Musto, G. Semeraro, P. Lops, M. de Gemmis, F. Narducci.
Leveraging Social Media Sources to Generate Personalized Music Playlists - EC-WEB 2012 - 04.09.12
17. social media
give new opportunities for modeling and
gathering information about user preferences
C. Musto, G. Semeraro, P. Lops, M. de Gemmis, F. Narducci.
Leveraging Social Media Sources to Generate Personalized Music Playlists - EC-WEB 2012 - 04.09.12
18. Facebook
user preferences in music.
C. Musto, G. Semeraro, P. Lops, M. de Gemmis, F. Narducci.
Leveraging Social Media Sources to Generate Personalized Music Playlists - EC-WEB 2012 - 04.09.12
19. Our contribution
Play.me
C. Musto, G. Semeraro, P. Lops, M. de Gemmis, F. Narducci.
Leveraging Social Media Sources to Generate Personalized Music Playlists - EC-WEB 2012 - 04.09.12
20. Play.me
personalized music playlists
β’ Goal
β’ To provide users with personalized music playlists
β’ Insights
β’ Extraction of explicit user preferences from Facebook
β’ Playlist creation by enriching explicit user preferences.
β’ New artists are added to those explicitly extracted from
Facebook
β’ Comparison of two enrichment techniques
C. Musto, G. Semeraro, P. Lops, M. de Gemmis, F. Narducci.
Leveraging Social Media Sources to Generate Personalized Music Playlists - EC-WEB 2012 - 04.09.12
21. Play.me
architecture
C. Musto, G. Semeraro, P. Lops, M. de Gemmis, F. Narducci.
Leveraging Social Media Sources to Generate Personalized Music Playlists - EC-WEB 2012 - 04.09.12
22. Play.me
architecture
C. Musto, G. Semeraro, P. Lops, M. de Gemmis, F. Narducci.
Leveraging Social Media Sources to Generate Personalized Music Playlists - EC-WEB 2012 - 04.09.12
23. Myusic
pre-processing
β’ Crawling from Last.fm
β’ Public API
β’ Content-based features
β’ Name of the artist + Social tags
β’ Noise processing
β’ Information locally stored
C. Musto, G. Semeraro, P. Lops, M. de Gemmis, F. Narducci.
Leveraging Social Media Sources to Generate Personalized Music Playlists - EC-WEB 2012 - 04.09.12
24. Myusic
pre-processing
Sigur RΓ²s tag cloud from Last.fm
C. Musto, G. Semeraro, P. Lops, M. de Gemmis, F. Narducci.
Leveraging Social Media Sources to Generate Personalized Music Playlists - EC-WEB 2012 - 04.09.12
25. Play.me
architecture
C. Musto, G. Semeraro, P. Lops, M. de Gemmis, F. Narducci.
Leveraging Social Media Sources to Generate Personalized Music Playlists - EC-WEB 2012 - 04.09.12
26. Myusic
data extraction from Facebook
C. Musto, G. Semeraro, P. Lops, M. de Gemmis, F. Narducci.
Leveraging Social Media Sources to Generate Personalized Music Playlists - EC-WEB 2012 - 04.09.12
27. Myusic
data extraction from Facebook
explicit preferences
C. Musto, G. Semeraro, P. Lops, M. de Gemmis, F. Narducci.
Leveraging Social Media Sources to Generate Personalized Music Playlists - EC-WEB 2012 - 04.09.12
28. Myusic
data extraction from Facebook
implicit preferences
C. Musto, G. Semeraro, P. Lops, M. de Gemmis, F. Narducci.
Leveraging Social Media Sources to Generate Personalized Music Playlists - EC-WEB 2012 - 04.09.12
29. Play.me
architecture
C. Musto, G. Semeraro, P. Lops, M. de Gemmis, F. Narducci.
Leveraging Social Media Sources to Generate Personalized Music Playlists - EC-WEB 2012 - 04.09.12
30. Play.fm
enrichment
β’ Rationale
β’ Given a set of explicit preferences extracted from
Facebook
β’ Play.me enrichs this set
β’ Extraction of artists similar to those the user
explicity likes
C. Musto, G. Semeraro, P. Lops, M. de Gemmis, F. Narducci.
Leveraging Social Media Sources to Generate Personalized Music Playlists - EC-WEB 2012 - 04.09.12
31. Play.fm
enrichment example
Coldplay extracted from Facebook
enrichment
radiohead red hot chili peppers kings of leon
C. Musto, G. Semeraro, P. Lops, M. de Gemmis, F. Narducci.
Leveraging Social Media Sources to Generate Personalized Music Playlists - EC-WEB 2012 - 04.09.12
32. Play.me
architecture
C. Musto, G. Semeraro, P. Lops, M. de Gemmis, F. Narducci.
Leveraging Social Media Sources to Generate Personalized Music Playlists - EC-WEB 2012 - 04.09.12
33. Play.me
playlist
Most popular songs of the artists extracted from Last.fm (as well as
those added through the enrichment) are proposed to the user.
C. Musto, G. Semeraro, P. Lops, M. de Gemmis, F. Narducci.
Leveraging Social Media Sources to Generate Personalized Music Playlists - EC-WEB 2012 - 04.09.12
34. letβs go
deeper
C. Musto, G. Semeraro, P. Lops, M. de Gemmis, F. Narducci.
Leveraging Social Media Sources to Generate Personalized Music Playlists - EC-WEB 2012 - 04.09.12
35. Play.fm
enrichment
β’ Comparison of two approaches
β’
Content-based strategy
β’ Distributional Models
β’ Linked Data
C. Musto, G. Semeraro, P. Lops, M. de Gemmis, F. Narducci.
Leveraging Social Media Sources to Generate Personalized Music Playlists - EC-WEB 2012 - 04.09.12
36. Play.fm
enrichment based on Distributional Models
β’ Content-based strategy
β’ Each artist is represented through a set of
tags
β’ Each artist is represented as a point in a
semantic geometrical space
β’ Distributional Models
β’ Similarity calculations to extract the most
similar artists.
C. Musto, G. Semeraro, P. Lops, M. de Gemmis, F. Narducci.
Leveraging Social Media Sources to Generate Personalized Music Playlists - EC-WEB 2012 - 04.09.12
37. distributional models
insight
by analyzing large corpus of textual data it is possible
to infer information about the usage (about the meaning)
of the terms.
C. Musto, G. Semeraro, P. Lops, M. de Gemmis, F. Narducci.
Leveraging Social Media Sources to Generate Personalized Music Playlists - EC-WEB 2012 - 04.09.12
38. distributional models
βmeaning
is its useβ
L.Wittgenstein
(Austrian philosopher)
C. Musto, G. Semeraro, P. Lops, M. de Gemmis, F. Narducci.
Leveraging Social Media Sources to Generate Personalized Music Playlists - EC-WEB 2012 - 04.09.12
39. distributional models
insight
by analyzing large corpus of textual data it is possible
to infer information about the usage (about the meaning)
of the terms.
example
C. Musto, G. Semeraro, P. Lops, M. de Gemmis, F. Narducci.
Leveraging Social Media Sources to Generate Personalized Music Playlists - EC-WEB 2012 - 04.09.12
40. distributional models
term/context matrix (WordSpace)
c1 c2 c3 c4 c5 c6 c7 c8 c9
t1 β β β β
t2 β β β β
t3 β β β
t4 β β β β
Cataldo Musto - Enhanced Vector Space Models for Content-based Recommender Systems - Ph.D. defense - University of Bari Aldo Moro, Italy - 08.06.12
41. distributional models
beer vs. glass: good overlap
c1 c2 c3 c4 c5 c6 c7 c8 c9
t1 β β β β
t2 β β β β
t3 β β β
t4 β β β β
Cataldo Musto - Enhanced Vector Space Models for Content-based Recommender Systems - Ph.D. defense - University of Bari Aldo Moro, Italy - 08.06.12
42. distributional models
beer vs. spoon: no overlap
c1 c2 c3 c4 c5 c6 c7 c8 c9
t1 β β β β
t2 β β β β
t3 β β β
t4 β β β β
Cataldo Musto - Enhanced Vector Space Models for Content-based Recommender Systems - Ph.D. defense - University of Bari Aldo Moro, Italy - 08.06.12
43. distributional models
rock vs. post rock = good overlap
a1 a2 a3 a4 a5 a6
rock β β β
post rock β β
jazz β
classical β β β
C. Musto, G. Semeraro, P. Lops, M. de Gemmis, F. Narducci.
Leveraging Social Media Sources to Generate Personalized Music Playlists - EC-WEB 2012 - 04.09.12
44. distributional models
rock vs. classical = no overlap
a1 a2 a3 a4 a5 a6
rock β β β
post rock β β
jazz β
classical β β β
C. Musto, G. Semeraro, P. Lops, M. de Gemmis, F. Narducci.
Leveraging Social Media Sources to Generate Personalized Music Playlists - EC-WEB 2012 - 04.09.12
45. WordSpace
example
rock
post-rock
jazz
classical
C. Musto, G. Semeraro, P. Lops, M. de Gemmis, F. Narducci.
Leveraging Social Media Sources to Generate Personalized Music Playlists - EC-WEB 2012 - 04.09.12
46. representation of documents (*)
can be inferred by combining the representation of
the terms (**) occurring in the document.
(*) documents = artists
(**) terms = tags
C. Musto, G. Semeraro, P. Lops, M. de Gemmis, F. Narducci.
Leveraging Social Media Sources to Generate Personalized Music Playlists - EC-WEB 2012 - 04.09.12
47. distributional models
term/context matrix (DocSpace)
c1 c2 c3 c4 c5 c6 c7 c8 c9
t2 β β β β
t3 β β β
d1 β β β β β
C. Musto, G. Semeraro, P. Lops, M. de Gemmis, F. Narducci.
Leveraging Social Media Sources to Generate Personalized Music Playlists - EC-WEB 2012 - 04.09.12
48. Play.fm
enrichment based on Distributional Models
Coldplay
Radiohead
Kings of Leon
Lady Gaga
C. Musto, G. Semeraro, P. Lops, M. de Gemmis, F. Narducci.
Leveraging Social Media Sources to Generate Personalized Music Playlists - EC-WEB 2012 - 04.09.12
49. Play.fm
enrichment based on Distributional Models
input: vector space representation
output: artists with the highest cosine similarity
radiohead the killers kings of leon
C. Musto, G. Semeraro, P. Lops, M. de Gemmis, F. Narducci.
Leveraging Social Media Sources to Generate Personalized Music Playlists - EC-WEB 2012 - 04.09.12
50. Linked Open Data Cloud
C. Musto, G. Semeraro, P. Lops, M. de Gemmis, F. Narducci.
Leveraging Social Media Sources to Generate Personalized Music Playlists - EC-WEB 2012 - 04.09.12
51. Linked Open Data Cloud
Structured
(RDF)
representation
of the information
stored in Wikipedia.
C. Musto, G. Semeraro, P. Lops, M. de Gemmis, F. Narducci.
Leveraging Social Media Sources to Generate Personalized Music Playlists - EC-WEB 2012 - 04.09.12
52. Play.fm
enrichment based on Linked Data
Coldplay play Alternative Rock
C. Musto, G. Semeraro, P. Lops, M. de Gemmis, F. Narducci.
Leveraging Social Media Sources to Generate Personalized Music Playlists - EC-WEB 2012 - 04.09.12
53. Play.me
RDF triple
Relationships are explictly encoded in RDF.
C. Musto, G. Semeraro, P. Lops, M. de Gemmis, F. Narducci.
Leveraging Social Media Sources to Generate Personalized Music Playlists - EC-WEB 2012 - 04.09.12
54. Play.fm
enrichment based on Linked Data
β’ Linked Open Data Cloud
β’ Each artist is mapped on a DBpedia node.
β’ univocal URI
β’ Relationship between artists (nodes) are explicitly
encoded
β’ e.g. genre, artist category, etc.
β’ Use of SPARQL to extract artists (nodes) that
share the same features
C. Musto, G. Semeraro, P. Lops, M. de Gemmis, F. Narducci.
Leveraging Social Media Sources to Generate Personalized Music Playlists - EC-WEB 2012 - 04.09.12
55. Play.fm
enrichment based on Linked Data
input: SPARQL query
output: artists sharing the same properties
radiohead the smiths the verve
C. Musto, G. Semeraro, P. Lops, M. de Gemmis, F. Narducci.
Leveraging Social Media Sources to Generate Personalized Music Playlists - EC-WEB 2012 - 04.09.12
56. recap
enrichment process
input: artist output: similar artists
coldplay the smiths
Linked Data
radiohead
the verve
kings of leon
Distributional Models
radiohead
C. Musto, G. Semeraro, P. Lops, M. de Gemmis, F. Narducci.
Leveraging Social Media Sources to Generate Personalized Music Playlists - EC-WEB 2012 - 04.09.12
57. experimental
evaluation.
C. Musto, G. Semeraro, P. Lops, M. de Gemmis, F. Narducci.
Leveraging Social Media Sources to Generate Personalized Music Playlists - EC-WEB 2012 - 04.09.12
58. experimental design
β’ Experiment
β’ Which one is the enrichment technique that
can provide users with the best playlists ?
C. Musto, G. Semeraro, P. Lops, M. de Gemmis, F. Narducci.
Leveraging Social Media Sources to Generate Personalized Music Playlists - EC-WEB 2012 - 04.09.12
59. experimental design
settings
β’ 30 users
β’ Heterogeneous musical knowledge
β’ Last.fm crawl: 228,878 artists
β’ Extraction & Recommendation step
β’ 325 artists extracted
β’ 11 per user, on average
C. Musto, G. Semeraro, P. Lops, M. de Gemmis, F. Narducci.
Leveraging Social Media Sources to Generate Personalized Music Playlists - EC-WEB 2012 - 04.09.12
60. experimental setup
Given a playlist, each user can freely express her own
feedback (like/dislike) on the proposed tracks.
C. Musto, G. Semeraro, P. Lops, M. de Gemmis, F. Narducci.
Leveraging Social Media Sources to Generate Personalized Music Playlists - EC-WEB 2012 - 04.09.12
61. experimental setup
Experiment repeated three times (one run with Linked Data enrichment,
another one with Distributional Models, one with a simple baseline based on
popularity).
C. Musto, G. Semeraro, P. Lops, M. de Gemmis, F. Narducci.
Leveraging Social Media Sources to Generate Personalized Music Playlists - EC-WEB 2012 - 04.09.12
62. experimental setup
Users were unaware of the adopted conο¬guration.
C. Musto, G. Semeraro, P. Lops, M. de Gemmis, F. Narducci.
Leveraging Social Media Sources to Generate Personalized Music Playlists - EC-WEB 2012 - 04.09.12
63. experimental design
results
76.3
80
75.2 Linked Data
Distributional Models
Baseline (Popularity)
73.75
69.7
67.5
65.9
64.6
61.25 63.2
58 58 58
55
n=1 n=2 n=3
n = number of artists added for each extracted artist
C. Musto, G. Semeraro, P. Lops, M. de Gemmis, F. Narducci.
Leveraging Social Media Sources to Generate Personalized Music Playlists - EC-WEB 2012 - 04.09.12
64. experimental design
results
76.3
80
75.2 Linked Data
Distributional Models
Baseline (Popularity)
73.75
69.7
67.5
65.9
64.6
61.25 63.2
58 58 58
55
n=1 n=2 n=3
distributional models overcome linked data
C. Musto, G. Semeraro, P. Lops, M. de Gemmis, F. Narducci.
Leveraging Social Media Sources to Generate Personalized Music Playlists - EC-WEB 2012 - 04.09.12
65. experimental design
results
76.3
80
75.2 Linked Data
Distributional Models
Baseline (Popularity)
73.75
69.7
67.5
65.9
64.6
61.25 63.2
58 58 58
55
n=1 n=2 n=3
precision in distributional models drops down more rapidly
C. Musto, G. Semeraro, P. Lops, M. de Gemmis, F. Narducci.
Leveraging Social Media Sources to Generate Personalized Music Playlists - EC-WEB 2012 - 04.09.12
66. experimental design
results
76.3
80
75.2 Linked Data
Distributional Models
Baseline (Popularity)
73.75
69.7
67.5
65.9
64.6
61.25 63.2
58 58 58
55
n=1 n=2 n=3
good results for baseline, as well (poor music knowledge?)
C. Musto, G. Semeraro, P. Lops, M. de Gemmis, F. Narducci.
Leveraging Social Media Sources to Generate Personalized Music Playlists - EC-WEB 2012 - 04.09.12
67. Play.me
recap of the experiment
β’ Play.me
β’ Platform for generating personalized music playlists
β’Extraction of favourite artists from Facebook
β’ Experiments
β’ Enrichment based on distributional models
overcomes linked data-based one in a signiο¬cant
way
C. Musto, G. Semeraro, P. Lops, M. de Gemmis, F. Narducci.
Leveraging Social Media Sources to Generate Personalized Music Playlists - EC-WEB 2012 - 04.09.12
68. conclusions.
C. Musto, G. Semeraro, P. Lops, M. de Gemmis, F. Narducci.
Leveraging Social Media Sources to Generate Personalized Music Playlists - EC-WEB 2012 - 04.09.12
69. both enrichment techniques
overcome the baseline
C. Musto, G. Semeraro, P. Lops, M. de Gemmis, F. Narducci.
Leveraging Social Media Sources to Generate Personalized Music Playlists - EC-WEB 2012 - 04.09.12
70. distributional models
overcome linked data
C. Musto, G. Semeraro, P. Lops, M. de Gemmis, F. Narducci.
Leveraging Social Media Sources to Generate Personalized Music Playlists - EC-WEB 2012 - 04.09.12
71. future research.
C. Musto, G. Semeraro, P. Lops, M. de Gemmis, F. Narducci.
Leveraging Social Media Sources to Generate Personalized Music Playlists - EC-WEB 2012 - 04.09.12
72. merging different
enrichment techniques
C. Musto, G. Semeraro, P. Lops, M. de Gemmis, F. Narducci.
Leveraging Social Media Sources to Generate Personalized Music Playlists - EC-WEB 2012 - 04.09.12
73. evaluation with user-based metrics
(serendipity, novelty, unexpectedness)
C. Musto, G. Semeraro, P. Lops, M. de Gemmis, F. Narducci.
Leveraging Social Media Sources to Generate Personalized Music Playlists - EC-WEB 2012 - 04.09.12
74. modeling context.
C. Musto, G. Semeraro, P. Lops, M. de Gemmis, F. Narducci.
Leveraging Social Media Sources to Generate Personalized Music Playlists - EC-WEB 2012 - 04.09.12
75. questions?
C. Musto, G. Semeraro, P. Lops, M. de Gemmis, F. Narducci.
Leveraging Social Media Sources to Generate Personalized Music Playlists - EC-WEB 2012 - 04.09.12