2021 Beauty Contest D title translation and ideas

2021 ICM

Problem D: The Influence of Music

Music has been part of human societies since the beginning of time as an essential component of cultural heritage. As part of an effort to understand the role music has played in the collective human experience, we have been asked to develop a method to quantify musical evolution. There are many factors that can influence artists when they create a new piece of music, including their innate ingenuity, current social or political events, access to new instruments or tools, or other personal experiences. Our goal is to understand and measure the influence of previously produced music on new music and musical artists.

Since ancient times, music has become a part of human society and an important part of cultural heritage. In order to understand the role of music in the collective human experience, we were asked to develop aMethods of quantifying music development. When creating new music, there are many factors that affect the artist, including his talented creativity, current social or political events, use of new musical instruments or tools, or other personal experiences. Our goal is to understand and measure the impact of previously produced music on new music and music artists.

• Our methods to quantify music development are: social network analysis, community discovery algorithms, and information dissemination models in social networks
• Understand and measure the impact of previously produced music on new music and music artists : establish a characteristic evaluation system model for previous music and musicians (principal component analysis: dimensionality reduction, machine learning: hierarchical clustering) to analyze genres and genres The difference between musicians and the characteristics within and between genres , the LSTM long and short time memory network is used to measure the evolution of genres in time
• The musical influence of a single musician is measured by the degree of the apex in the musician's social network and the size of the subnet . The musical influence of the previous musicians results in more subsequent works with similar musical characteristics!

Some artists can list a dozen or more other artists who they say influenced their own musical work. It has also been suggested that influence can be measured by the degree of similarity between song characteristics, such as structure, rhythm, or lyrics. There are sometimes revolutionary shifts in music, offering new sounds or tempos, such as when a new genre emerges, or there is a reinvention of an existing genre (e.g. classical, pop/rock, jazz, etc.). This can be due to a sequence of small changes, a cooperative effort of artists, a series of influential artists, or a shift within society.

Some artists can list a dozen or more artists that they think have an influence on their music. It is also recommendedMeasure influence by the similarity between song characteristics (such as structure, rhythm or lyrics). Music sometimes undergoes revolutionary changes, providing new sounds or rhythms, such as when new genres appear, or reinventing existing genres (such as classical, pop/rock, jazz, etc.). This may be due to a series of small changes, the collaborative efforts of artists, a series of influential artists or changes within society.

• In the sub-network, it can be found that the music influence of the central node of the network is greater, and the overall music genre of the sub-network is highly consistent with the central node. The song characteristics of the network are highly similar, and the direct mutual music influence of the network nodes is greater. !
• Analyze the characteristics of the artists at the central node of the subnet of the music development network : high talent, special age, and extensive and profound influence on the development of genres

Many songs have similar sounds, and many artists have contributed to major shifts in a musical genre. Sometimes these shifts are due to one artist influencing another. Sometimes it is a change that emerges in response to external events (such as major world events or technological advances). By considering networks of songs and their musical characteristics, we can begin to capture the influence that musical artists have on each other. And, perhaps, we can also gain a better understanding of how music evolves through societies over time.

Many songs have similar sounds, and many artists have contributed to a major change in music genre. Sometimes these changes are due to one artist affecting another artist. Sometimes this change occurs in response to external events (such as major world events or technological progress). By consideringThe network of songs and their musical characteristics, We can start to capture the mutualinfluences. And, maybe, we can better understandMusic over timeThe passage of development in the entire society.

• External events, the evolution of music genres, the influence between music artists, the influence of music on society ( compilation of documentation )

Your team has been identified by the Integrative Collective Music (ICM) Society to develop a model that measures musical influence. This problem asks you to examine evolutionary and revolutionary trends of artists and genres. To do this, your team has been given several data sets by the ICM:

Your team has been recognized by the Integrated Collective Music (ICM) Association to develop a model to measure the impact of music. This question requires you to checkThe evolution and revolutionary trends of artists and genres. To this end, ICM provides some data sets for your team:

• Painting focus : the evolution of models, artists and genres that measure the influence of music! (The final conclusion of the paper!)

  Combined with the last question: the establishment of a music network knowledge map can describe the impact of events and social environment (social events, political factors, Internet factors) on music and the evolution of music as a whole!

1. “influence_data” 1 represents musical influencers and followers, as reported by the artists themselves, as well as the opinions of industry experts. These data contains influencers and followers for 5,854 artists in the last 90 years.

1) "Influence_data" represents music influencers and followers, and is reported by the artist himself and the opinions of industry experts. These data include influencers and followers of 5,854 artists in the past 90 years.

2. “full_music_data”2 provides 16 variable entries, including musical features such as danceability, tempo, loudness, and key, along with artist_name and artist_id for each of 98,340 songs. These data are used to create two summary data sets, including:

a. mean values by artist “data_by_artist”,

b. means across years “data_by_year”.

2) "full_music_data" provides 16 variable entries, including music characteristics, such as dance , rhythm , loudness and keys , as well as 98,340 songs for each artist_name and artist_id. This data is used to create two summary data sets, including:

a. The value of the artist "data_by_artist"

b. Indicates cross-year "data_by_year"

Note: DATA provided in these files are a subset of larger data sets. These files CONTAIN THE ONLY DATA YOU SHOULD USE FOR THIS PROBLEM.

To carry out this challenging project, the ICM Society asks your teams to explore the evolution of music through the influence across musical artists over time, by doing the following：

• Use the influence_data data set or portions of it to create a (multiple) directed network(s) of musical influence, where influencers are connected to followers. Develop parameters that capture ‘music influence’ in this network. Explore a subset of musical influence by creating a subnetwork of your directed influencer network. Describe this subnetwork. What do your ‘music influence’ measures reveal in this subnetwork?

  Use the influence_data data set or part of it to create one (multiple)A directed network of musical influenceTo connect influencers to followers. Develop parameters that capture the "music influence" in this network. Explore a subset of music influence by creating subnets of the targeted influencer network. Describe this subnet. What does your "music influence" measure reflect in this sub-network?

  1. Use the social network analysis model to create one (multiple)A directed network of musical influence

     Social network analysis model !

     The first network is an unpowered directed graph. The nodes are influencers and followers, and influencers point to followers.

  2. Develop parameters that capture the "music influence" in this network

     Exploring the parameters of the influence of music propagation through the community discovery algorithm can identify closely connected subnets. We consider the influence of music to be the weighted quantitative average of the degree of the nodes of the graph and the size of the subnet to which they belong.

  3. Explore a subset of music influence by creating subnets of the targeted influencer network. Describe this subnet. What does your "music influence" measure reflect in this sub-network?

     After the community discovery algorithm, it can be found that in the overall music influence social network, 16 subnets have been identified. It can be found that the music influence of the central node of the network is greater, and the overall music genre of the subnet is highly consistent with the central node.

• Use full_music_data and/or the two summary data sets (with artists and years) of music characteristics, to develop measures of music similarity. Using your measure, are artists within genre more similar than artists between genres?

  Use full_music_data and/or two summary data sets of music characteristics (including artist and year) to developMusic similarity measure. Using your metric, are the artists of the genre more similar than the artists of the genre?

  Artists within most genres are more similar than artists between genres

  • Principal component analysis-dimensionality reduction
  • Characteristic indicators of music (abstract concepts: rhythm, emotional factors, popularity...)
  • Cluster analysis results (hierarchical clustering)
  • Get the result (artists within the genre are more similar)

• Compare similarities and influences between and within genres. What distinguishes a genre and how do genres change over time? Are some genres related to others?

  Compare the similarities and influences between and within genres. What is the difference of genres( Visualization! ), how about the genreChange with time( Visualization! )?Are some types related to other types？

  1. The higher the genre, the lower the cluster model index within the genre
  2. Time series model of genre and time ()
  3. Genre influence model
  4. This problem needs to be analyzed on the genres, before passing through the correlation between (1) the influence and followers, can be introduced between the dynamic evolution of the genre, such as the genres A and B genres produce evolved evolved CD genre. By From the previous data analysis of each genre, it is possible to know which characteristics of the genre have changed in the process of genre evolution, and what is the difference between the genres. Detailed explanation and a large amount of data analysis and visualization are the focus of this question.

• Indicate whether the similarity data, as reported in the data_influence data set, suggest that the identified influencers in fact influence the respective artists. Do the ‘influencers’ actually affect the music created by the followers? Are some music characteristics more ‘contagious’ than others, or do they all have similar roles in influencing a particular artist’s music?

  Indicate whether the similarity data reported in the data_influence dataset indicates that the identified influencer is actually influencing the corresponding artist. Will "influencers" actually influence the music created by followers? Are certain musical characteristics more "infectious" than others, or do they play a similar role in influencing the music of a particular artist?

  • According to the establishment of social communication models (node ​​importance theory, node centrality theory), and the comparison between the results of community discovery algorithms and real artist genres.

    The conclusion is that the identified influencer is actually influencing the corresponding artist. The greater the influence of a node, the higher the genre similarity with the surrounding nodes, and the higher influence influencers have greater musical similarity to the music created by the followers. degree.

  • Through the quantitative analysis of the music characteristics of music artists of different levels of influence

    The conclusion is to find that certain musical characteristics are more contagious and are influencing more musicians to converge towards larger genres.

• Identify if there are characteristics that might signify revolutions (major leaps) in musical evolution from these data?

  What artists represent revolutionaries (influencers of major change) in your network?

  Determine from these data whether there are features that may mark a revolution (major leap) in the development of music ? In your network, which artists represent revolutionaries (influencers of major changes)?

  • Establish an LSTM long and short time memory network to visualize the changes in music characteristics between years (Figure); the changes in genre popularity between years (Figure)

    The conclusion is: the decline of instrumentalness, the extraordinary prosperity of POP&Rock in the 1960s, and the profound influence on the popularity of the following music genres

  • Artist influence ranking (table)

    The conclusion is that the most influential artists are almost all musicians of the POP&Rock genre in the 1960s.

  • Combined with the influence of American society in the 1960s (reasonable explanation)

• Analyze the influence processes of musical evolution that occurred over time in one genre.

  Can your team identify indicators that reveal the dynamic influencers, and explain how the genre(s) or artist(s) changed over time?

  Analyze the influence process of a genre over time. ( How does the influence of the communication process cause the musical characteristics of a genre to change over time ?) Can your team identify indicators that reveal dynamic influencers and explain the changes in genres or artists over time?

  • Visualize changes in the popularity of a genre (Figure)

  • Establish a fuzzy comprehensive evaluation model

    Solve the influence of the artist's comprehensive music development (evolution) : the influence of the artist's communication + the popularity of the artist + the number of the artist's songs

  • The conclusion is that the higher the comprehensive music development (evolution) influence of artists in the genre, the higher the popularity of the genre.

• How does your work express information about cultural influence of music in time or circumstances? Alternatively, how can the effects of social, political or technological changes (such as the internet) be identified within the network?

  How does your work express information about the cultural impact of music in terms of time or environment? Or, how to identify the impact of social, political, or technological changes (such as the Internet) in the Internet?

  • Introducing knowledge graph theory, knowledge graph is a comprehensive analysis of social networks that incorporates more characteristic information.
  • The influence of social cultural background and history on the development of music (combined with the desire to express the heart in the 1960s)
  • The impact of technology and Internet technology on communication (changes in the production technology and communication methods of music involved, and classical music is more inclined to the way of concerts)

• Model optimization and sensitivity analysis

  • Social network analysis (complex network model), community discovery algorithm
  • Principal component analysis, hierarchical clustering
  • Multiple logistic regression
  • Social network communication model
  • LSTM Long and Short Time Neural Recurrent Network
  • Fuzzy Comprehensive Evaluation Method Model
  • Knowledge Graph

• Summary

Write a one-page document to the ICM Society about the value of using your approach to understanding the influence of music through networks. Considering the two problem data sets were limited to only some genres, and subsequently to those artists common to both data sets, how would your work or solutions change with more or richer data? Recommend further study of music and its effect on culture.

ICM Association to write a document page , which relates to the use of your way to understand the value of music influenced by the network. Considering that these two problem data sets are limited to certain types, and then for the artists shared by the two data sets, how will your work or solution change with more or richer data? It is recommended to further study music and its influence on culture.

The ICM Society, an interdisciplinary and diverse group from the fields of music, history, social science, technology, and mathematics, looks forward to your final report.

Your PDF solution of no more than 25 total pages should include:

• One-page Summary Sheet.
• Table of Contents.
• Your complete solution.
• One-page document to ICM society.
• References list.

Note: New for 2021! The ICM Contest now has a 25-page limit. All aspects of your submission count toward the 25-page limit: Summary Sheet, Table of Contents, Main Body of Solution, Images and Tables, One-page Document, Reference List, and any Appendices.

Attachments

We provide the following four data files for this problem. THE DATA FILES PROVIDED CONTAIN THE ONLY DATA YOU SHOULD USE FOR THIS PROBLEM.

1. influence_data.csv

2. full_music_data.csv

3. data_by_artist.csv

4. data_by_year.csv

Data Descriptions

1. influence_data.csv

(Data is encoded in utf-8 to allow for handling of special characters):

• influencer_id: A unique identification number given to the person listed as influencer.(string of digits)

  Influencer_id: A unique identification number given to the person listed as an influencer.

• influencer_name: The name of the influencing artist as given by the follower or industry experts. (string)

  Influencer_name: The name of an influential artist given by a follower or industry expert.

• influencer_main_genre: The genre that best describes the bulk of the music produced by the influencing artist. (if available) (string)

  Influencer_main_genre: The genre that best describes most of the music created by influential artists.

• influencer_active_start: The decade that the influencing artist began their music career.(integer)

  Influencer_active_start: The ten years since the influential singer started his music career.

• follower_id: A unique identification number given to the artist listed as follower. (string of digits)

  Follower_id: The unique identifier for the artist listed as a follower.

• follower_name: The name of the artist following an influencing artist. (string)

  Follower_id: The unique identifier for the artist listed as a follower.

• follower_main_genre: The genre that best describes the bulk of the music produced by the following artist. (if available) (string)

  Follower_main_genre: The genre that best describes most of the music created by the artists who follow.

• follower_active_start: The decade that the following artist began their music career.(integer)

  Follower_active_start: Follow the artist for ten years since they started their music career.

2. full_music_data.csv

3. data_by_artist.csv

4. data_by_year.csv

Spotify audio features from the “full_music_data”, “data_by_artist”, “data_by_year”:

• artist_name: The artist who performed the track. (array)

  The artist who sang this song

• artist_id: The same unique identification number given in the influence_data.csv file.(string of digits)

  The same unique identification number given in the influence_data.csv file.

Characteristics of the music:

• danceability: A measure of how suitable a track is for dancing based on a combination of musical elements including tempo, rhythm stability, beat strength, and overall regularity. A value of 0.0 is least danceable and 1.0 is most danceable. (float)

  Dance: According to the combination of music elements such as rhythm, rhythm stability, beat intensity and overall regularity, it is a measure of whether a piece of music is suitable for dancing. 0.0 is the least suitable value for dancing, and 1.0 is the most suitable value for dancing.

• energy: A measure representing a perception of intensity and activity. A value of 0.0 is least intense/energetic and 1.0 is most intense/energetic. Typically, energetic tracks feel fast, loud, and noisy. For example, death metal has high energy, while a Bach prelude scores low on the scale. Perceptual features contributing to this attribute include dynamic range, perceived loudness, timbre, onset rate, and general entropy. (float)

  Energy: A measure of strength and vitality. 0.0 is the minimum intensity value, and 1.0 is the maximum intensity value. Usually, the energy-filled track feels fast and loud. And noisy. For example, the energy of death metal is high, and Bach’s Overture scores low on the scale. Perceptual characteristics that contribute to this attribute include dynamic range, perceived loudness, timbre, seizure rate, and general entropy.

• valence: A measure describing the musical positiveness conveyed by a track. A value of 0.0 is most negative and 1.0 is most positive. Tracks with high valence sound more positive (e.g. happy, cheerful, euphoric), while tracks with low valence sound more negative (e.g. sad, depressed, angry). (float)

  Potency: A measure that describes the musicality conveyed by the soundtrack. 0.0 is the most negative value and 1.0 is the most positive value. High-price audio tracks sound more positive (such as happy, happy, euphoric), while low-price audio tracks sound more negative (such as sadness, depression, anger).

• tempo: The overall estimated tempo of a track in beats per minute (BPM). In musical terminology, tempo is the speed or pace of a given piece and derives directly from the average beat duration. (float)

  Rhythm: The overall estimated tempo of the track calculated in beats per minute (BPM). In music mink science, rhythm is the speed or rhythm of a given work, directly derived from the average beat duration.

• loudness: The overall loudness of a track in decibels (dB). Values typical range between -60 and 0 db. Loudness values are averaged across the entire track and are useful for comparing relative loudness of tracks. Loudness is the quality of a sound that is the primary psychological correlate of physical strength (amplitude). (float)

  Loudness: The overall loudness of the audio track, in decibels (dB). The typical range of values ​​is between -60 and 0 decibels. The loudness value averages across the entire track and is useful for comparing the relative loudness of the track. Loudness is the nature of sound, and is the main psychological link to physical strength (amplitude).

• mode: An indication of modality (major or minor), the type of scale from which its melodic content is derived, of a track. Major is represented by 1 and minor is 0.

  Mode: An indication of the mode (major or minor) of the track. Mode is a type of scale, and its melody content comes from this. Large call 1 means, small call 0 means.

• key: The estimated overall key of the track. Integers map to pitches using standard Pitch Class notation. E.g. 0 = C, 1 = C♯/D♭, 2 = D, and so on. If no key was detected, the value for key is -1. (integer)

  Key: Estimated key of the entire track. Integers are mapped to pitch using standard pitch class notation. For example: 0-C, 1- c# /Db, 2= D, etc. If the key value is not detected, the key value is -1.

Type of vocals:

• acousticness: A confidence measure of whether the track is acoustic (without technology enhancements or electrical amplification). A value of 1.0 represents high confidence the track is acoustic. (float)

  Acoustics: A degree of confidence that determines whether the track is acoustic (without technical enhancement or electronic amplification). 1.0 represents the high confidence of the audio track.

• instrumentalness: Predicts whether a track contains no vocals. “Ooh” and “aah” sounds are treated as instrumental in this context. Rap or spoken word tracks are clearly “vocal”. The closer the instrumentalness value is to 1.0, the greater likelihood the track contains no vocal content. Values above 0.5 are intended to represent instrumental tracks, but confidence is higher as the value approaches 1.0. (float)

  Instrumental: predict whether the audio track does not contain human voices. The sounds of "Ooh" and "aah" are considered useful in this context. The soundtrack of rap or spoken language is the obvious "voice". The closer the instrumental value is to 1.0, the more likely the song will not contain vocal content. A value higher than 0.5 indicates an instrumental trajectory, but when the value is close to 1.0, the confidence is higher.

• liveness: Detects the presence of an audience in a track. Higher liveness values represent an increased probability that the track was performed live. A value above 0.8 provides strong likelihood that the track is live. (float)

  Activity: Detect whether there are viewers in the track. A higher activity value indicates an increased possibility of performing tracking in real time. If the value is higher than 0.8, it indicates that the track is likely to be real-time.

• speechiness: Detects the presence of spoken words in a track. The more exclusively speech-like the recording (e.g. talk show, audio book, poetry), the closer to 1.0 the attribute value. Values above 0.66 describe tracks that are probably made entirely of spoken words. Values between 0.33 and 0.66 describe tracks that may contain both music and speech, either in sections or layered, including such cases as rap music. Values below 0.33 most likely represent music and other non-speech-like tracks. (float)

  Voice: Detect whether the voice exists in the audio track. The more voice-like recordings (such as talk shows, audio books, poems), the closer the attribute value is to 1.0. A value higher than 0.66 indicates an audio track that may be composed entirely of spoken words. A value between 0.33 and 0.66 describes an audio track that contains both music and language. It can be segmented or layered, including rap music. Values ​​below 0.33 are likely to represent music and other non-verbal audio tracks.

• explicit: Detects explicit lyrics in a track (true (1) = yes it does; false (0) = no it does not OR unknown). (Boolean)

  Explicit: Detect explicit lyrics in the audio track (true (1) = yes; false (0) = absent or unknown).

Description:

• duration_ms: The duration of the track in milliseconds. (integer)

  Track duration, in milliseconds.

• popularity: The popularity of the track. The value will be between 0 and 100, with 100 being the most popular. The popularity is calculated by algorithm and is based, in the most part, on the total number of plays the track has had and how recent those plays are. Generally speaking, songs that are being played more frequently now will have a higher popularity than songs that were played more frequently in the past. Duplicate tracks (e.g. the same track from a single and an album) are rated independently. Artist and album popularity are derived mathematically from track popularity. (integer)

  The popularity of this track. The value will be between 0 and 100, with 100 being the most commonly used. Popularity is calculated by an algorithm, based to a large extent on the total number of plays of the song and the most recent time of these plays. Generally speaking, songs played more frequently now will be more popular than songs played more frequently in the past. Repeated audio tracks (for example, the same audio track from a single and album) are independently rated. The popularity of artists and albums is calculated from the popularity of songs.

• year: The year of release of a track. (integer from 1921 to 2020)

  The year the single was released.

• release_date: The calendar date of release of a track mostly in yyyy-mm-dd format, however precision of date may vary and some just given as yyyy.

  The calendar date of the audio track release is mostly in yyyy-mm-dd format, but the accuracy of the date may be different, and some only give yyyy.

• song_title (censored): The name of the track. (string) Software was run to remove any potential explicit words in the song title.

  The name of the audio track. The (string) software is run to remove any potential explicit text in the title of the song.

• count: The number of songs a particular artist is represented in the full_music_data.csv file.(integer)

  Represents the full_music_data.csv of an artist in the complete music data file