Networks of Music Groups as Success Predictors

Dmitry Zinoviev
Dmitry ZinovievFull Professor at Suffolk University
Networks of Music Groups as
Success Predictors
Dmitry Zinoviev
Department of Mathematics and Computer Science
Suffolk University, Boston
Dmitry Zinoviev * Suffolk University 2
Research Question
Who Rocks and Why?
Dmitry Zinoviev * Suffolk University 3
Real Research Questions
● Does sharing performers with other groups
influence the groups' eventual success?
● If so, is the success predictable from the
performers' sharing network?
● What is the linguocultural and genre structure
of the ex-Soviet music universe?
Dmitry Zinoviev * Suffolk University 4
Research Strategy
● Collect data about sharing and success
● Build a network based on shared musicians
● Define “success”
● Correlate network measures (such as centralities)
with success measures
● Attempt to predict success from the network
measures using machine learning techniques
● Look into genres/languages and communities
Dmitry Zinoviev * Suffolk University 5
DATA
Dmitry Zinoviev * Suffolk University 6
Data Set
● 4,560 non-academic music groups performing in
the USSR and post-Soviet countries in 1960–2015
● 17,000 performers (at least 3,600 shared)
● 275 genres (rock, pop, disco, jazz, folk, etc.)
● Wikipedia pages in 122 languages
Dmitry Zinoviev * Suffolk University 7
New Groups by Year
Dmitry Zinoviev * Suffolk University 8
2,216 Groups on Wikipedia
● Russia
● Estonia
● Ukraine
● Latvia
● Lithuania
● Belarus
● Moldova
Dmitry Zinoviev * Suffolk University 9
NETWORK
Dmitry Zinoviev * Suffolk University 10
Network Construction
●
Group → node; labels in the original language
● Two nodes connected if the groups shared at least
one musician over their lifetime
● Undirected, unweighted, unconnected graph with
no loops and no parallel edges
● For each node, calculate degree, average neighbors
degree, closeness, betweenness, and eigenvalue
centrality, and clustering coefficient
Dmitry Zinoviev * Suffolk University 11
Network
Overview
● Node size
represents
degree
(number of
shares)
Dmitry Zinoviev * Suffolk University 12
Network Description
● 80% of the groups (3,602) are in the giant
connected component; all other connected
components have <13 groups each
● Excellent community structure (m=0.76), 43
communities; each of the largest 25 communities
has 20+ groups
● Community = groups that have a lot of mutual
musician sharing
Dmitry Zinoviev * Suffolk University 13
SUCCESS
Dmitry Zinoviev * Suffolk University 14
What's “Success”?
● No sales data!
● No charts!
● Informal/semi-legal/illegal status
● Proxies for long-term success (we still remember them!):
– Wikipedia page(s) visit frequency within last 3 years (collected
from http://stats.grok.se)
– Wikipedia page(s) Google PageRank
– Available for 2,000 groups
Dmitry Zinoviev * Suffolk University 15
PageRank (PR) Correlations
Dmitry Zinoviev * Suffolk University 16
Visit Frequency (VF) Correlations
Dmitry Zinoviev * Suffolk University 17
Prediction
● Random Decision Forest (RDF) machine learning
predictor
● Predict above-median VF vs below-median VF:
accuracy 71% (expected by chance: 50%)
● Predict Google PR: accuracy 49% (expected by
chance: 17%)
● Quite poor, but not hopeless
Dmitry Zinoviev * Suffolk University 18
GENRES
Dmitry Zinoviev * Suffolk University 19
Genres and Sharing
● Build a network of similar genres (recursive
generalized similarity):
– Two genres are similar if used by similar groups
– Two groups are similar if play similar genres
●
Genre → node; two nodes are connected if the
genres are “very similar”
● Community structure (m=0.3):
– Punk/jazz, metal, disco/pop, blues/hip-hop, light rock
Dmitry Zinoviev * Suffolk University 20
Genre
Network
Metal
Light rock
Punk
Soul
Folk/jazz/hh
Disco
Ethno
Some genres are
hierarchical
(rock/metal/black metal).
TODO: Assign them to
different levels.
Dmitry Zinoviev * Suffolk University 21
Musicians Prefer Similar Genres
Dmitry Zinoviev * Suffolk University 22
LINGUOCULTURAL
STRUCTURE
Dmitry Zinoviev * Suffolk University 23
Languages, Genres, and Sharing
● Group sharing network has 25 communities with
20+ groups in each
● Preferred language = language of the most
frequently visited Wikipedia page
● Look into genres and preferred languages within
each community: Are they homo- or
heterogeneous?
Dmitry Zinoviev * Suffolk University 24
Genres per Community
In 9
communities,
>50% of groups
perform the one
genre.
In 23
communities,
>50% of groups
perform in no
more than 2
genres.
71% of all
shares—
homogeneous
Dmitry Zinoviev * Suffolk University 25
Preferred Languages per Community
In 24
communities,
>50% of groups
have the same
preferred
language!
84% of all shares
—homogeneous
Dmitry Zinoviev * Suffolk University 26
Language and Genre Homogeneity: Either or Both?
Language-defined
Genre-defined
Not very convincing?
Mixed
Dmitry Zinoviev * Suffolk University 27
Conclusion
● Musician sharing networks of non-academic music
groups in the USSR and post-Soviet countries have
community structure inspired by preferred
language and musical genre
● Centrality and clustering measures of this network
are correlated with long-term success of groups in
terms of popularity on Wikipedia and to some
extent can serve as success predictors
1 of 27

Recommended

Soviet Popular Music Landscape: Community Structure and Success Predictors by
Soviet Popular Music Landscape: Community Structure and Success PredictorsSoviet Popular Music Landscape: Community Structure and Success Predictors
Soviet Popular Music Landscape: Community Structure and Success PredictorsDmitry Zinoviev
168 views30 slides
Facebook as a communication channel of diverse ideas that are not presented i... by
Facebook as a communication channel of diverse ideas that are not presented i...Facebook as a communication channel of diverse ideas that are not presented i...
Facebook as a communication channel of diverse ideas that are not presented i...Tena Čačić
693 views13 slides
Incorporating Web2 Tools by
Incorporating Web2 ToolsIncorporating Web2 Tools
Incorporating Web2 Toolsjohnsoncr62
202 views22 slides
Najib_Ullah_Resume_Mocks-2 by
Najib_Ullah_Resume_Mocks-2Najib_Ullah_Resume_Mocks-2
Najib_Ullah_Resume_Mocks-2Najib Nicko
107 views2 slides
Sla news and updates for february 2015 update by
Sla news and updates for february 2015 updateSla news and updates for february 2015 update
Sla news and updates for february 2015 updateBarbara Monaghan
100 views11 slides
Spanish 2 slideshow by
Spanish 2 slideshowSpanish 2 slideshow
Spanish 2 slideshowChris P. Duke
122 views9 slides

More Related Content

More from Dmitry Zinoviev

The “Musk” Effect at Twitter by
The “Musk” Effect at TwitterThe “Musk” Effect at Twitter
The “Musk” Effect at TwitterDmitry Zinoviev
42 views17 slides
Are Twitter Networks of Regional Entrepreneurs Gendered? by
Are Twitter Networks of Regional Entrepreneurs Gendered?Are Twitter Networks of Regional Entrepreneurs Gendered?
Are Twitter Networks of Regional Entrepreneurs Gendered?Dmitry Zinoviev
25 views22 slides
Using Complex Network Analysis for Periodization by
Using Complex Network Analysis for PeriodizationUsing Complex Network Analysis for Periodization
Using Complex Network Analysis for PeriodizationDmitry Zinoviev
30 views18 slides
Algorithms by
AlgorithmsAlgorithms
AlgorithmsDmitry Zinoviev
220 views14 slides
Text analysis of The Book Club Play by
Text analysis of The Book Club PlayText analysis of The Book Club Play
Text analysis of The Book Club PlayDmitry Zinoviev
334 views11 slides
Exploring the History of Mental Stigma by
Exploring the History of Mental StigmaExploring the History of Mental Stigma
Exploring the History of Mental StigmaDmitry Zinoviev
451 views14 slides

More from Dmitry Zinoviev(20)

Are Twitter Networks of Regional Entrepreneurs Gendered? by Dmitry Zinoviev
Are Twitter Networks of Regional Entrepreneurs Gendered?Are Twitter Networks of Regional Entrepreneurs Gendered?
Are Twitter Networks of Regional Entrepreneurs Gendered?
Dmitry Zinoviev25 views
Using Complex Network Analysis for Periodization by Dmitry Zinoviev
Using Complex Network Analysis for PeriodizationUsing Complex Network Analysis for Periodization
Using Complex Network Analysis for Periodization
Dmitry Zinoviev30 views
Text analysis of The Book Club Play by Dmitry Zinoviev
Text analysis of The Book Club PlayText analysis of The Book Club Play
Text analysis of The Book Club Play
Dmitry Zinoviev334 views
Exploring the History of Mental Stigma by Dmitry Zinoviev
Exploring the History of Mental StigmaExploring the History of Mental Stigma
Exploring the History of Mental Stigma
Dmitry Zinoviev451 views
Roles and Words in a massive NSSI-Related Interaction Network by Dmitry Zinoviev
Roles and Words in a massive NSSI-Related Interaction NetworkRoles and Words in a massive NSSI-Related Interaction Network
Roles and Words in a massive NSSI-Related Interaction Network
Dmitry Zinoviev288 views
“A Quaint and Curious Volume of Forgotten Lore,” or an Exercise in Digital Hu... by Dmitry Zinoviev
“A Quaint and Curious Volume of Forgotten Lore,” or an Exercise in Digital Hu...“A Quaint and Curious Volume of Forgotten Lore,” or an Exercise in Digital Hu...
“A Quaint and Curious Volume of Forgotten Lore,” or an Exercise in Digital Hu...
Dmitry Zinoviev411 views
Network analysis of the 2016 USA presidential campaign tweets by Dmitry Zinoviev
Network analysis of the 2016 USA presidential campaign tweetsNetwork analysis of the 2016 USA presidential campaign tweets
Network analysis of the 2016 USA presidential campaign tweets
Dmitry Zinoviev228 views
The Lord of the Ring. A Network Analysis by Dmitry Zinoviev
The Lord of the Ring. A Network AnalysisThe Lord of the Ring. A Network Analysis
The Lord of the Ring. A Network Analysis
Dmitry Zinoviev833 views

Recently uploaded

INTRODUCTION TO PLANT SYSTEMATICS.pptx by
INTRODUCTION TO PLANT SYSTEMATICS.pptxINTRODUCTION TO PLANT SYSTEMATICS.pptx
INTRODUCTION TO PLANT SYSTEMATICS.pptxRASHMI M G
5 views19 slides
2. Natural Sciences and Technology Author Siyavula.pdf by
2. Natural Sciences and Technology Author Siyavula.pdf2. Natural Sciences and Technology Author Siyavula.pdf
2. Natural Sciences and Technology Author Siyavula.pdfssuser821efa
13 views232 slides
ZEBRA FISH: as model organism.pptx by
ZEBRA FISH: as model organism.pptxZEBRA FISH: as model organism.pptx
ZEBRA FISH: as model organism.pptxmahimachoudhary0807
14 views17 slides
Major important agricultural crop Diseases list by
Major important agricultural crop Diseases listMajor important agricultural crop Diseases list
Major important agricultural crop Diseases listYuvarajYuva27
9 views21 slides
ELECTRON TRANSPORT CHAIN by
ELECTRON TRANSPORT CHAINELECTRON TRANSPORT CHAIN
ELECTRON TRANSPORT CHAINDEEKSHA RANI
26 views16 slides
Factors affecting fluorescence and phosphorescence.pptx by
Factors affecting fluorescence and phosphorescence.pptxFactors affecting fluorescence and phosphorescence.pptx
Factors affecting fluorescence and phosphorescence.pptxSamarthGiri1
10 views11 slides

Recently uploaded(20)

INTRODUCTION TO PLANT SYSTEMATICS.pptx by RASHMI M G
INTRODUCTION TO PLANT SYSTEMATICS.pptxINTRODUCTION TO PLANT SYSTEMATICS.pptx
INTRODUCTION TO PLANT SYSTEMATICS.pptx
RASHMI M G 5 views
2. Natural Sciences and Technology Author Siyavula.pdf by ssuser821efa
2. Natural Sciences and Technology Author Siyavula.pdf2. Natural Sciences and Technology Author Siyavula.pdf
2. Natural Sciences and Technology Author Siyavula.pdf
ssuser821efa13 views
Major important agricultural crop Diseases list by YuvarajYuva27
Major important agricultural crop Diseases listMajor important agricultural crop Diseases list
Major important agricultural crop Diseases list
YuvarajYuva279 views
ELECTRON TRANSPORT CHAIN by DEEKSHA RANI
ELECTRON TRANSPORT CHAINELECTRON TRANSPORT CHAIN
ELECTRON TRANSPORT CHAIN
DEEKSHA RANI26 views
Factors affecting fluorescence and phosphorescence.pptx by SamarthGiri1
Factors affecting fluorescence and phosphorescence.pptxFactors affecting fluorescence and phosphorescence.pptx
Factors affecting fluorescence and phosphorescence.pptx
SamarthGiri110 views
Determination of color fastness to rubbing(wet and dry condition) by crockmeter. by ShadmanSakib63
Determination of color fastness to rubbing(wet and dry condition) by crockmeter.Determination of color fastness to rubbing(wet and dry condition) by crockmeter.
Determination of color fastness to rubbing(wet and dry condition) by crockmeter.
ShadmanSakib639 views
Evaluation and Standardization of the Marketed Polyherbal drug Patanjali Divy... by Anmol Vishnu Gupta
Evaluation and Standardization of the Marketed Polyherbal drug Patanjali Divy...Evaluation and Standardization of the Marketed Polyherbal drug Patanjali Divy...
Evaluation and Standardization of the Marketed Polyherbal drug Patanjali Divy...
Heavy Tails Workshop NeurIPS2023.pdf by Charles Martin
Heavy Tails Workshop NeurIPS2023.pdfHeavy Tails Workshop NeurIPS2023.pdf
Heavy Tails Workshop NeurIPS2023.pdf
Charles Martin96 views
Best Hybrid Event Platform.pptx by Harriet Davis
Best Hybrid Event Platform.pptxBest Hybrid Event Platform.pptx
Best Hybrid Event Platform.pptx
Harriet Davis11 views
AI for automated materials discovery via learning to represent, predict, gene... by Deakin University
AI for automated materials discovery via learning to represent, predict, gene...AI for automated materials discovery via learning to represent, predict, gene...
AI for automated materials discovery via learning to represent, predict, gene...
Gel Filtration or Permeation Chromatography by Poonam Aher Patil
Gel Filtration or Permeation ChromatographyGel Filtration or Permeation Chromatography
Gel Filtration or Permeation Chromatography
KeyAI. Solving a math problem to recover lost crypto assets. by RFID INC
KeyAI. Solving a math problem to recover lost crypto assets.KeyAI. Solving a math problem to recover lost crypto assets.
KeyAI. Solving a math problem to recover lost crypto assets.
RFID INC35 views
RADIATION PHYSICS.pptx by drpriyanka8
RADIATION PHYSICS.pptxRADIATION PHYSICS.pptx
RADIATION PHYSICS.pptx
drpriyanka815 views
Eukaryotic microbiology lab Dos and Donts.pptx by Prasanna Kumar
Eukaryotic microbiology lab Dos and Donts.pptxEukaryotic microbiology lab Dos and Donts.pptx
Eukaryotic microbiology lab Dos and Donts.pptx
Prasanna Kumar8 views
Exploring the nature and synchronicity of early cluster formation in the Larg... by Sérgio Sacani
Exploring the nature and synchronicity of early cluster formation in the Larg...Exploring the nature and synchronicity of early cluster formation in the Larg...
Exploring the nature and synchronicity of early cluster formation in the Larg...
Sérgio Sacani1.6K views
DNA manipulation Enzymes 2.pdf by NetHelix
DNA manipulation Enzymes 2.pdfDNA manipulation Enzymes 2.pdf
DNA manipulation Enzymes 2.pdf
NetHelix6 views
Non Aqueous titration: Definition, Principle and Application by Poonam Aher Patil
Non Aqueous titration: Definition, Principle and ApplicationNon Aqueous titration: Definition, Principle and Application
Non Aqueous titration: Definition, Principle and Application

Networks of Music Groups as Success Predictors

  • 1. Networks of Music Groups as Success Predictors Dmitry Zinoviev Department of Mathematics and Computer Science Suffolk University, Boston
  • 2. Dmitry Zinoviev * Suffolk University 2 Research Question Who Rocks and Why?
  • 3. Dmitry Zinoviev * Suffolk University 3 Real Research Questions ● Does sharing performers with other groups influence the groups' eventual success? ● If so, is the success predictable from the performers' sharing network? ● What is the linguocultural and genre structure of the ex-Soviet music universe?
  • 4. Dmitry Zinoviev * Suffolk University 4 Research Strategy ● Collect data about sharing and success ● Build a network based on shared musicians ● Define “success” ● Correlate network measures (such as centralities) with success measures ● Attempt to predict success from the network measures using machine learning techniques ● Look into genres/languages and communities
  • 5. Dmitry Zinoviev * Suffolk University 5 DATA
  • 6. Dmitry Zinoviev * Suffolk University 6 Data Set ● 4,560 non-academic music groups performing in the USSR and post-Soviet countries in 1960–2015 ● 17,000 performers (at least 3,600 shared) ● 275 genres (rock, pop, disco, jazz, folk, etc.) ● Wikipedia pages in 122 languages
  • 7. Dmitry Zinoviev * Suffolk University 7 New Groups by Year
  • 8. Dmitry Zinoviev * Suffolk University 8 2,216 Groups on Wikipedia ● Russia ● Estonia ● Ukraine ● Latvia ● Lithuania ● Belarus ● Moldova
  • 9. Dmitry Zinoviev * Suffolk University 9 NETWORK
  • 10. Dmitry Zinoviev * Suffolk University 10 Network Construction ● Group → node; labels in the original language ● Two nodes connected if the groups shared at least one musician over their lifetime ● Undirected, unweighted, unconnected graph with no loops and no parallel edges ● For each node, calculate degree, average neighbors degree, closeness, betweenness, and eigenvalue centrality, and clustering coefficient
  • 11. Dmitry Zinoviev * Suffolk University 11 Network Overview ● Node size represents degree (number of shares)
  • 12. Dmitry Zinoviev * Suffolk University 12 Network Description ● 80% of the groups (3,602) are in the giant connected component; all other connected components have <13 groups each ● Excellent community structure (m=0.76), 43 communities; each of the largest 25 communities has 20+ groups ● Community = groups that have a lot of mutual musician sharing
  • 13. Dmitry Zinoviev * Suffolk University 13 SUCCESS
  • 14. Dmitry Zinoviev * Suffolk University 14 What's “Success”? ● No sales data! ● No charts! ● Informal/semi-legal/illegal status ● Proxies for long-term success (we still remember them!): – Wikipedia page(s) visit frequency within last 3 years (collected from http://stats.grok.se) – Wikipedia page(s) Google PageRank – Available for 2,000 groups
  • 15. Dmitry Zinoviev * Suffolk University 15 PageRank (PR) Correlations
  • 16. Dmitry Zinoviev * Suffolk University 16 Visit Frequency (VF) Correlations
  • 17. Dmitry Zinoviev * Suffolk University 17 Prediction ● Random Decision Forest (RDF) machine learning predictor ● Predict above-median VF vs below-median VF: accuracy 71% (expected by chance: 50%) ● Predict Google PR: accuracy 49% (expected by chance: 17%) ● Quite poor, but not hopeless
  • 18. Dmitry Zinoviev * Suffolk University 18 GENRES
  • 19. Dmitry Zinoviev * Suffolk University 19 Genres and Sharing ● Build a network of similar genres (recursive generalized similarity): – Two genres are similar if used by similar groups – Two groups are similar if play similar genres ● Genre → node; two nodes are connected if the genres are “very similar” ● Community structure (m=0.3): – Punk/jazz, metal, disco/pop, blues/hip-hop, light rock
  • 20. Dmitry Zinoviev * Suffolk University 20 Genre Network Metal Light rock Punk Soul Folk/jazz/hh Disco Ethno Some genres are hierarchical (rock/metal/black metal). TODO: Assign them to different levels.
  • 21. Dmitry Zinoviev * Suffolk University 21 Musicians Prefer Similar Genres
  • 22. Dmitry Zinoviev * Suffolk University 22 LINGUOCULTURAL STRUCTURE
  • 23. Dmitry Zinoviev * Suffolk University 23 Languages, Genres, and Sharing ● Group sharing network has 25 communities with 20+ groups in each ● Preferred language = language of the most frequently visited Wikipedia page ● Look into genres and preferred languages within each community: Are they homo- or heterogeneous?
  • 24. Dmitry Zinoviev * Suffolk University 24 Genres per Community In 9 communities, >50% of groups perform the one genre. In 23 communities, >50% of groups perform in no more than 2 genres. 71% of all shares— homogeneous
  • 25. Dmitry Zinoviev * Suffolk University 25 Preferred Languages per Community In 24 communities, >50% of groups have the same preferred language! 84% of all shares —homogeneous
  • 26. Dmitry Zinoviev * Suffolk University 26 Language and Genre Homogeneity: Either or Both? Language-defined Genre-defined Not very convincing? Mixed
  • 27. Dmitry Zinoviev * Suffolk University 27 Conclusion ● Musician sharing networks of non-academic music groups in the USSR and post-Soviet countries have community structure inspired by preferred language and musical genre ● Centrality and clustering measures of this network are correlated with long-term success of groups in terms of popularity on Wikipedia and to some extent can serve as success predictors