(SoWeMine Workshop) "#nowplaying on #Spotify: Leveraging Spotify Information on Twitter for Artist Recommendations" - Martin Pichl, Eva Zangerle and Günther SpechtPresentation
The document summarizes research on developing a music recommendation system using data from Twitter posts that share songs users are listening to on Spotify. Key points:
1) Researchers collected over 500,000 tweets sharing Spotify listening events to create a dataset of users, artists, and tracks.
2) They used collaborative filtering on the dataset to recommend artists similar to those in a user's listening history.
3) Evaluation of the initial recommendation system showed moderate precision and recall, with performance decreasing for more recommendations, likely due to data sparsity.
4) Next steps discussed include improving data matching of Twitter and Spotify profiles and extracting additional context like playlists to develop a more specialized recommendation approach.
Crowsourcing for Social Multimedia Task: Crowsorting Timed Comments about Musicmultimediaeval
This paper provides an overview of the Crowdsorting Timed Comments about Music Task, a new task in the area of crowdsourcing for social media offered by the MediaEval 2014 Multimedia Benchmark. Data for this task is a set of Electronic Dance Music (EDM) tracks, collected from online music sharing platform Soundcloud. Given a set of noisy labels for segments of Electronic Dance Music (EDM) that were collected on Amazon Mechanical Turk, the task is to predict a single `correct' label. The labels indicate whether or not a `drop' occurs in the particular music segment. The larger aim of this task is to contribute to the development of hybrid human/conventional computation techniques to generate accurate labels for social multimedia content. For this reason, participants are also encouraged to predict labels by combining input from the crowd (i.e., human computation) with automatic computation (i.e., processing techniques applied to textual metadata and/or audio signal analysis).
http://ceur-ws.org/Vol-1263/mediaeval2014_submission_78.pdf
Presented at the Machine Learning class at Chalmers, Gothenburg.
http://www.cse.chalmers.se/research/lab/courses.php?coid=9
Trying to connect their theoretical machine learning class with industry examples.
The current revolution in the music industry represents great opportunities and challenges for music recommendation systems. Recommendation systems are now central to music streaming platforms, which are rapidly increasing in listenership and becoming the top source of revenue for the music industry. It is increasingly more common for a music listener to simply access music than to purchase and own it in a personal collection. In this scenario, recommendation calls no longer for a one-shot recommendation for the purpose of a track or album purchase, but for a recommendation of a listening experience, comprising a very wide range of challenges, such as sequential recommendation, or conversational and contextual recommendations. Recommendation technologies now impact all actors in the rich and complex music industry ecosystem (listeners, labels, music makers and producers, concert halls, advertisers, etc.).
The purpose of this presentation is to understand how analytics is used in the Media and Entertainment Industry. Examples of Netflix, Spotify and BookMyShow have been considered to look at the same
Machine Learning and Big Data for Music Discovery at SpotifyChing-Wei Chen
Spotify is the world’s largest on-demand music streaming company, with over 100 million active users who generate around 2TB of interaction data every day. With over 30 million songs to choose from, discovery and personalization play an essential role in helping users discover the best music for them. In this talk, given at the newly opened Galvanize space in NYC in March 2017, we’ll explain how Spotify uses Latent Space Models and Deep Learning to power features such as Discover Weekly and Release Radar.
Crowsourcing for Social Multimedia Task: Crowsorting Timed Comments about Musicmultimediaeval
This paper provides an overview of the Crowdsorting Timed Comments about Music Task, a new task in the area of crowdsourcing for social media offered by the MediaEval 2014 Multimedia Benchmark. Data for this task is a set of Electronic Dance Music (EDM) tracks, collected from online music sharing platform Soundcloud. Given a set of noisy labels for segments of Electronic Dance Music (EDM) that were collected on Amazon Mechanical Turk, the task is to predict a single `correct' label. The labels indicate whether or not a `drop' occurs in the particular music segment. The larger aim of this task is to contribute to the development of hybrid human/conventional computation techniques to generate accurate labels for social multimedia content. For this reason, participants are also encouraged to predict labels by combining input from the crowd (i.e., human computation) with automatic computation (i.e., processing techniques applied to textual metadata and/or audio signal analysis).
http://ceur-ws.org/Vol-1263/mediaeval2014_submission_78.pdf
Presented at the Machine Learning class at Chalmers, Gothenburg.
http://www.cse.chalmers.se/research/lab/courses.php?coid=9
Trying to connect their theoretical machine learning class with industry examples.
The current revolution in the music industry represents great opportunities and challenges for music recommendation systems. Recommendation systems are now central to music streaming platforms, which are rapidly increasing in listenership and becoming the top source of revenue for the music industry. It is increasingly more common for a music listener to simply access music than to purchase and own it in a personal collection. In this scenario, recommendation calls no longer for a one-shot recommendation for the purpose of a track or album purchase, but for a recommendation of a listening experience, comprising a very wide range of challenges, such as sequential recommendation, or conversational and contextual recommendations. Recommendation technologies now impact all actors in the rich and complex music industry ecosystem (listeners, labels, music makers and producers, concert halls, advertisers, etc.).
The purpose of this presentation is to understand how analytics is used in the Media and Entertainment Industry. Examples of Netflix, Spotify and BookMyShow have been considered to look at the same
Machine Learning and Big Data for Music Discovery at SpotifyChing-Wei Chen
Spotify is the world’s largest on-demand music streaming company, with over 100 million active users who generate around 2TB of interaction data every day. With over 30 million songs to choose from, discovery and personalization play an essential role in helping users discover the best music for them. In this talk, given at the newly opened Galvanize space in NYC in March 2017, we’ll explain how Spotify uses Latent Space Models and Deep Learning to power features such as Discover Weekly and Release Radar.
Luis Aguiar: Platforms, Promotion, and Product Discovery: Evidence from Spoti...Marius Miron
Luis Aguiar's keynote presentation at the 1st Workshop on Designing Human-Centric MIR Systems, ISMIR 2019
Luis Aguiar is Assistant Professor in Management of the Digital Transformation at the University of Zurich, Switzerland. His main research interests are in the economics of digitization, with a particular focus on the effects of technological change on firms, consumers, markets, and welfare. A large part of his research has focused on the music industry, analyzing the effects of digitization on the supply of recorded music, the interaction between distinct music consumption channels, and the welfare effects of music trade. He has also studied how music streaming platforms affect content availability, production, and music consumption patterns.
Deezer - Big data as a streaming serviceJulie Knibbe
40 million songs, albums and artists available - how nice? Streaming allows you to get a grasp at the biggest music collections in the world. The only thing is that you would need centuries to listen to all of it.
Getting access doesn’t mean knowing what to do with it. How are we making music discovery more & more efficient at Deezer?
Algorithmic Music Recommendations at SpotifyChris Johnson
In this presentation I introduce various Machine Learning methods that we utilize for music recommendations and discovery at Spotify. Specifically, I focus on Implicit Matrix Factorization for Collaborative Filtering, how to implement a small scale version using python, numpy, and scipy, as well as how to scale up to 20 Million users and 24 Million songs using Hadoop and Spark.
Building Data Pipelines for Music Recommendations at SpotifyVidhya Murali
In this talk, we will get into the architectural and functional details as to how we build scalable and robust data pipelines for music recommendations at Spotify. We will also discuss some of the challenges and an overview of work to address these challenges.
Designing recommender system for your application孜羲 顏
The Goal and The Role of Recommender System
The General Recommending Flow: Sourcing/Ranking
Sourcing Paths of Different Application/Industry
The Methods of Presenting Recommendation Results and Interacting with Users
A Recommender System in Real World: Pinterest Related Pins
Gather Feedback and Building a Feedback Loop
What You Need is More Than Modeling and Designing: The Data System
The Ultimate Goal of a Recommender System
Online Recommender System for Radio Station Hosting: Experimental Results Rev...Dmitrii Ignatov
We present a new recommender system developed for the Russian interactive radio network FMhost based on a previously proposed model. The underlying model combines a collaborative user-based approach with information from tags of listened tracks in order to match user and radio station profiles.
It follows an adaptive online learning strategy based on the user history. We compare the proposed algorithms and an industry standard technique based on singular value decomposition (SVD)
in terms of precision, recall, and NDCG measures; experiments show that in our case the fusion-based approach shows the best results.
This presentation was provided by Kira Sobers of The Smithsonian Institution, during the NISO event "Preservation and Archiving of Digital Media," held on September 11, 2019.
Big data is data sets that are so voluminous and complex that traditional data processing application software are inadequate to deal with them. Big data challenges include capturing data, data storage, data analysis, search, sharing, transfer, visualization, querying, updating and information privacy
Hadoop Training in Chennai from BigDataTraining.IN is a leading Global Talent Development Corporation, building skilled manpower pool for global industry requirements. BigData Training.in has today grown to be amongst worlds leading talent development companies offering learning solutions to Individuals, Institutions & Corporate Clients.
(Web User Interfaces track) "Getting the Query Right: User Interface Design o...icwe2015
-
More Related Content
Similar to (SoWeMine Workshop) "#nowplaying on #Spotify: Leveraging Spotify Information on Twitter for Artist Recommendations" - Martin Pichl, Eva Zangerle and Günther SpechtPresentation
Luis Aguiar: Platforms, Promotion, and Product Discovery: Evidence from Spoti...Marius Miron
Luis Aguiar's keynote presentation at the 1st Workshop on Designing Human-Centric MIR Systems, ISMIR 2019
Luis Aguiar is Assistant Professor in Management of the Digital Transformation at the University of Zurich, Switzerland. His main research interests are in the economics of digitization, with a particular focus on the effects of technological change on firms, consumers, markets, and welfare. A large part of his research has focused on the music industry, analyzing the effects of digitization on the supply of recorded music, the interaction between distinct music consumption channels, and the welfare effects of music trade. He has also studied how music streaming platforms affect content availability, production, and music consumption patterns.
Deezer - Big data as a streaming serviceJulie Knibbe
40 million songs, albums and artists available - how nice? Streaming allows you to get a grasp at the biggest music collections in the world. The only thing is that you would need centuries to listen to all of it.
Getting access doesn’t mean knowing what to do with it. How are we making music discovery more & more efficient at Deezer?
Algorithmic Music Recommendations at SpotifyChris Johnson
In this presentation I introduce various Machine Learning methods that we utilize for music recommendations and discovery at Spotify. Specifically, I focus on Implicit Matrix Factorization for Collaborative Filtering, how to implement a small scale version using python, numpy, and scipy, as well as how to scale up to 20 Million users and 24 Million songs using Hadoop and Spark.
Building Data Pipelines for Music Recommendations at SpotifyVidhya Murali
In this talk, we will get into the architectural and functional details as to how we build scalable and robust data pipelines for music recommendations at Spotify. We will also discuss some of the challenges and an overview of work to address these challenges.
Designing recommender system for your application孜羲 顏
The Goal and The Role of Recommender System
The General Recommending Flow: Sourcing/Ranking
Sourcing Paths of Different Application/Industry
The Methods of Presenting Recommendation Results and Interacting with Users
A Recommender System in Real World: Pinterest Related Pins
Gather Feedback and Building a Feedback Loop
What You Need is More Than Modeling and Designing: The Data System
The Ultimate Goal of a Recommender System
Online Recommender System for Radio Station Hosting: Experimental Results Rev...Dmitrii Ignatov
We present a new recommender system developed for the Russian interactive radio network FMhost based on a previously proposed model. The underlying model combines a collaborative user-based approach with information from tags of listened tracks in order to match user and radio station profiles.
It follows an adaptive online learning strategy based on the user history. We compare the proposed algorithms and an industry standard technique based on singular value decomposition (SVD)
in terms of precision, recall, and NDCG measures; experiments show that in our case the fusion-based approach shows the best results.
This presentation was provided by Kira Sobers of The Smithsonian Institution, during the NISO event "Preservation and Archiving of Digital Media," held on September 11, 2019.
Big data is data sets that are so voluminous and complex that traditional data processing application software are inadequate to deal with them. Big data challenges include capturing data, data storage, data analysis, search, sharing, transfer, visualization, querying, updating and information privacy
Hadoop Training in Chennai from BigDataTraining.IN is a leading Global Talent Development Corporation, building skilled manpower pool for global industry requirements. BigData Training.in has today grown to be amongst worlds leading talent development companies offering learning solutions to Individuals, Institutions & Corporate Clients.
Similar to (SoWeMine Workshop) "#nowplaying on #Spotify: Leveraging Spotify Information on Twitter for Artist Recommendations" - Martin Pichl, Eva Zangerle and Günther SpechtPresentation (20)
1.Wireless Communication System_Wireless communication is a broad term that i...JeyaPerumal1
Wireless communication involves the transmission of information over a distance without the help of wires, cables or any other forms of electrical conductors.
Wireless communication is a broad term that incorporates all procedures and forms of connecting and communicating between two or more devices using a wireless signal through wireless communication technologies and devices.
Features of Wireless Communication
The evolution of wireless technology has brought many advancements with its effective features.
The transmitted distance can be anywhere between a few meters (for example, a television's remote control) and thousands of kilometers (for example, radio communication).
Wireless communication can be used for cellular telephony, wireless access to the internet, wireless home networking, and so on.
Multi-cluster Kubernetes Networking- Patterns, Projects and GuidelinesSanjeev Rampal
Talk presented at Kubernetes Community Day, New York, May 2024.
Technical summary of Multi-Cluster Kubernetes Networking architectures with focus on 4 key topics.
1) Key patterns for Multi-cluster architectures
2) Architectural comparison of several OSS/ CNCF projects to address these patterns
3) Evolution trends for the APIs of these projects
4) Some design recommendations & guidelines for adopting/ deploying these solutions.
ER(Entity Relationship) Diagram for online shopping - TAEHimani415946
https://bit.ly/3KACoyV
The ER diagram for the project is the foundation for the building of the database of the project. The properties, datatypes, and attributes are defined by the ER diagram.
This 7-second Brain Wave Ritual Attracts Money To You.!nirahealhty
Discover the power of a simple 7-second brain wave ritual that can attract wealth and abundance into your life. By tapping into specific brain frequencies, this technique helps you manifest financial success effortlessly. Ready to transform your financial future? Try this powerful ritual and start attracting money today!
This 7-second Brain Wave Ritual Attracts Money To You.!
(SoWeMine Workshop) "#nowplaying on #Spotify: Leveraging Spotify Information on Twitter for Artist Recommendations" - Martin Pichl, Eva Zangerle and Günther SpechtPresentation
1. Seite 1
Page 1
The University of Innsbruck was founded in 1669 and is one of Austria’s oldest universities. Today, with over 28.000 students and 4.000 staff, it is
western Austria’s largest institution of higher education and research. For further information visit: www.uibk.ac.at.
#nowplaying on #Spotify: Leveraging Spotify
Information on Twitter for Artist Recommendations
Martin Pichl, Eva Zangerle and Günther Specht
2. Seite 2
Page 2
Agenda
• Why Music Recommendations?
• Dataset Creation & Recommendation Approach
• Discussion and Future Work
3. Seite 3
Page 3
Recent Trends
• Rise of the web enabled new distribution channels
• Online Stores
• Music Streaming Platforms
• …
• These new distribution channels
– Exploit a word-wide market
– Virtually no inventory costs
→ More and more dives music is available
4. Seite 4
Page 4
Why (Music) Recommender Systems?
• The user is confronted with more and more diverse music
– on streaming platforms
– in online stores
– on mobile devices
• and has a free choice
• Users often do not know what to listen to
→ Information Overload
• Recommender Systems
– Helps users finding music they like
→ Increase usability
5. Seite 5
Page 5
Research on Music Recommender System
• Publicly available data necessary
• Twitter
– People share what they are listening at the moment
• Get additional information from Spotify
– Additional listening events
– Additional information about the tracks and the artists
– Additional information about the listening context
• The additional information is necessary to build a more
specialized recommender system
7. Seite 7
Page 7
The Dataset
• Generated dataset based Tweets that contains
– <UserID, ArtistID, TrackID>-triples
– Boolean preferences (listened/not listened)
• Cleaning
– Removed duplicates
– Removed certain accounts i.e. @SpotifyNowPlaying
– Removed “Various Artists”
8. Seite 8
Page 8
Dataset Snapshot
• Dataset contains
– 513,489 listening events
– by 68,045 unique users
– listening to 97,586 unique tracks
– by unique 40,593 artists
• Distribution
– In average 4.77 tweets per user (SD= 30.02)
– Median of 2
9. Seite 9
Page 9
Artist Recommendations using this Dataset
• No content based information
– Recommendations are computed using collaborative filtering
• Collaborative Filtering (CF)
– CF recommends items that the most similar users of a user
listened to (and are new to the user)
• CF relies on
– A user similarity measure
– A number of nearest neighbors 𝑘
10. Seite 10
Page 10
User Similarity
• Boolean Preferences
– Jaccard Coefficient is suitable
– 𝐽𝑎𝑐𝑐𝑎𝑟𝑑𝑖,𝑗 =
𝑆 𝑖 ∩ 𝑆 𝑗
𝑆 𝑖 ∪ 𝑆 𝑗
• Include all the information available
– Compute Jaccard Coefficient using the artist listening history
– Compute Jaccard Coefficient using the track listening history
– Combined using an weighted average
• 𝑢𝑠𝑒𝑟𝑆𝑖𝑚 = 𝑤 𝑎 ∗ 𝑎𝑟𝑡𝑖𝑠𝑡𝑆𝑖𝑚 + 𝑤𝑡 ∗ 𝑡𝑟𝑎𝑐𝑘𝑆𝑖𝑚
11. Seite 11
Page 11
Parameter Tuning
• Input Parameters
– 𝑤 𝑎, 𝑤𝑡, 𝑘
– Optimized using a Genetic Algorithm (GA)
– Fitness = Precision of the recommender system
– In average a good solution was found after 4.14 iterations
(SD=2.27)
12. Seite 12
Page 12
Genetic Algorithm
• 𝑤 𝑎,𝑤𝑡, 𝑘 are float point genes between 0 and 1 and form a
individual
• Random initial distribution
• The fitness of each individual is measured using the
precision
• Crossover and mutations of the best individual
• Terminate if the precision is 1 or a certain number of
generations is reach
14. Seite 14
Page 14
Evaluation Setup
• Offline Evaluation
– From each user we removed 1/3 of the listening events for
testing
– Recommended 𝑝 ∗ 𝑆𝑖𝑧𝑒 𝑜𝑓 𝑡ℎ𝑒 𝑇𝑒𝑠𝑡𝑠𝑒𝑡 items
– Varied 𝑝 between 0 and 1
– Computed precision and recall for each 𝑝
• Parameters used for the Evaluation
– 𝑤 𝑎 = 0.21
– 𝑤𝑡 = 0.94
– 𝑘 = 59
15. Seite 15
Page 15
Evaluation Metrics
• Hit: Item found in the testset
• 𝑝𝑟𝑒𝑐𝑖𝑠𝑜𝑛 =
ℎ𝑖𝑡𝑠
𝑛𝑢𝑚𝑏𝑒𝑟 𝑜𝑓 𝑟𝑒𝑐𝑜𝑚𝑚𝑒𝑛𝑑𝑎𝑡𝑖𝑜𝑛𝑠
• Relevant Items: All items in the testset
• 𝑟𝑒𝑐𝑎𝑙𝑙 =
ℎ𝑖𝑡𝑠
𝑠𝑖𝑧𝑒 𝑜𝑓 𝑡ℎ𝑒 𝑡𝑒𝑠𝑡𝑠𝑒𝑡
16. Seite 16
Page 16
Performance of the optimized Recommender
System n Precision Recall
1 0.4656 0.0228
2 0.3622 0.0547
3 0.3137 0.0782
4 0.2812 0.1003
5 0.2531 0.1195
6 0.2315 0.1286
7 0.2170 0.1396
8 0.2170 0.1396
9 0.1871 0.1583
10 0.1871 0,1583
0
0,1
0,2
0,3
0,4
0,5
Precision/Recall
Number of Recommendations (% of the Testset)
Precision
Recall
17. Seite 17
Page 17
Discussion
• Heading into the right direction
• Performance is limited for a high number of
recommendations
– Data sparsity
– Too general approach
• Performance improvements with
– Reducing data sparsity
– Specialized algorithm that fits more to music
recommendation
18. Seite 18
Page 18
Next Steps towards a more specialized RS
• Match Spotify and Twitter Users
– Early experiments show that we can match ~ 10% of the
dataset
– Better matching than using the username and played tracks?
• Extract listening context from playlist names, i.e.
– Christmas
– Workout, training
– Driving
– …
19. Seite 19
Page 19
Next Steps towards a more specialized RS
• The offline evaluation is rather limited
• Create an intuitive webinterface
• Conduct a live user experiment