How can we understand and profile the musical preferences of consumers of online music providers? Do they tend to stick to a single genre, or do they explore beyond genre boundaries? How can we develop well-tailored recommendations based on existing knowledge of listeners?

To answer these questions, we utilize a dataset from Last.fm, which contains variables on social networking, tagging, and music artist listening information from its users. We construct a network of music artists by defining a tie between artists based on a threshold of shared listeners. Community detection methods are then applied to this network, revealing a strong similarity between the detected communities and musical genres. Our analyses reveal that users rarely confine themselves to a single genre. Therefore, we also identify key artists that act as bridges between genres.

Next, we incorporate supplementary internal artist-related data, such as user-generated tags, alongside external covariates—including genre, nationality, and years active—obtained via web scraping. Using this enriched dataset, we develop more nuanced and sophisticated user profiles. Based on these profiles, we propose a novel personalized recommendation list approach.

Our approach generates two types of recommendation lists: short lists that provide concise selections of artists for immediate exploration or purchase; and long lists that function as dynamic playlists, adapting to real-time user inputs. This structured, data-driven method enhances music recommendation systems, offering a more personalized and engaging listening experience.

he music industries increasingly matter to local economies, placemaking, and creative industries economic development (Hesmondhalgh, 2013; Rana & Campbell, 2019, 2020). However, the Canadian music industry maintains systemic barriers that reproduce inequality and discrimination, especially with regards to Black, racialized, newcomer, and immigrant musicians. Within the specific context of Canada, there remains a false tendency to believe these issues do not permeate its industries because of a storied history of so-called multiculturalism and acceptance (D’Amico-Cuthbert, 2021). Meanwhile, community music programs have been documented to foster inclusive opportunities for participants to engage in music making, alongside providing platforms and supports to develop music industry careers (Campbell, 2021; Marsh, 2012; Rimmer, 2012, 2018).

This paper presents findings from our collaborative “Mapping the Music Industries” research project, highlighting how our cultural mapping methodology (Duxbury, Garrett-Petts & MacLennan, 2015) expands what and who “counts” as a musician in the Toronto context. We forward cultural mapping as a method to make visible music networks that are otherwise poorly documented. We will present process findings from our methods to convene and co-create with our research participants, including four community conversation sessions, River of Experience drawings, follow-up semi-structured interviews, participation observation with community programs, and a Music Summit event with one of our research partners, AfroWave TO. We highlight tensions between the presence of vibrant diasporic music networks in Toronto and established funding and support models in Canada that often do not see or serve these diasporic networks. Alongside these tensions, we highlight the role of community music programs in providing 1)inclusive models for learning 2) music business knowledge and 3)spaces for relational exchange and networking alongside 4) raising the visibility of Black, racialized, and newcomer music. We explore the effects of these programs with a nuanced understanding of the anthropological Eurocentric origins of cultural and musical heritage work (Pryer, 2019), aiming to avoid reproducing essentialist discourse regarding diverse musicians with our alternative network mapping methods.

Using the Electronic Music Open Mic movement (EMOM) as a case study, we explore how networks are the basis of community building and movement-making. Since 2017 EMOM has been responding to inaccessible or even hostile open mic spaces for electronic and soundscape producers and performers. Situated within a long tradition of improvised electronic music it represents an emerging grassroots movement that expands internationally to include groups in Mexico, Australia, Germany, Canada and beyond, where technologies bridge the gap between audience and performer, adopting hybrid roles and collective experiences. This paper examines how social networks propel the movement beyond geographical or technological borders. New micro-electronic performance instruments—including the Korg Volca, Roland AIRA Compact, and Teenage Engineering’s Pocket Operator series, streaming platforms and virtual instruments—democratise music production and performance, enabling participatory leisure practices and music mobilities.

A concurrent mixed methods framework uses participant observations, organiser interviews (UK), EMOM community surveys and a digital ethnography of event-facilitating platforms and event streaming (UK and International). Using social network theories and modes of analysis we explore the fluid roles of organiser, performer and audience member at EMOM events highlighting how digital and material mobilities shape networked transnational music cultures. This research advances critical discussions on how we can use social network analysis to understand real-time music world-building. Technology plays a central role in democratising leisure; challenging homogenisation narratives, with the paper offering insights into the co-creation of digital and material leisure spaces. The study positions EMOM as an exemplar of how networked electronic sound worlds, portable technologies and digital platforms combine to reshape community, identity and creative expression within contemporary grassroots leisure environments.

This study addresses the research question: How do networks facilitate innovation and influence the success of artists and songs? Focusing on the analysis of the entire GroundUP Music Label, our investigation integrates network theory with empirical analysis to examine how collaborative structures drive creative breakthroughs and build social infrastructures for reach. Initially grounded in the forbidden triads hypothesis – which posits that artists bridging disconnected groups foster innovation (Vedres 2017) – we uncovered two recurring configurations at play. A select group of artists occupies forbidden triads, acting as brokers who connect diverse creative circles, while most artists operate within highly transitive networks that underscore the role of trust transfer in building careers.

Employing a mixed-methods approach, we combine quantitative analysis of Spotify collaboration data with qualitative interviews with key label artists, further enriched by complementary performance indicators such as social media reach and sales metrics. Our findings suggest that both expansive bridging and localized cohesion are crucial for innovation, as each configuration contributes uniquely to artistic influence and success.

Ultimately, this case study advances theoretical insights into bottom-up open innovation models through dual dynamics of network structures. It also highlights the broader paradigm in which 21st-century musicians leverage both social networks and digital technologies to serve their music, expand their reach, and enhance their artistic impact.

Keywords: Social Network Analysis, Innovation Mechanisms, Music Ecosystems, Trust Dynamics, Creative Networks

Introduction & Background

Musical keyboard instruments have undergone substantial transformation, from early acoustic pianos to the digital innovations seen in contemporary synthesizers. This evolution reflects both technological advancements and shifts in musical trends. The study aims to understand the key innovations that have shaped these instruments, with a particular focus on the interplay between technological development and musical creativity. In such rapid IT development generation, we standing on the technological view to explore how technological progress interact with the music industry. This study aims to explore three main questions. First, how does the technological evolutionary path of keyboard instruments develop in the past decades? Secondly, what significant technology milestones bring changes and impact on music industry? And finally we further explore the existence of emerging trends in the industry.

Methodology & Data

To analyze the technological evolution of musical keyboards, this study employs a quantitative approach using Main Path Analysis(MPA). MPA is a bibliometric method used to trace the most significant developmental trajectories in a citation network, offering insights into the flow of knowledge through scientific fields. Introduced by Hummon and Doreian in 1989, it works by assigning significance indices to citation links, representing the importance of these links in the diffusion of knowledge from earlier works to later ones. The main path is identified as the most critical sequence of citations that connects key publications in a network, highlighting the dominant ideas that have shaped the field (Liu & Lu, 2012). We apply this method to explore the knowledge trajectory path of keyboard development.

The research collects a dataset of 2,749 U.S. patents, sourced from the Derwent patent database, covering a period from 1920 to 2024. By analyzing technological network and main knowledge trajectory, the study identifies critical technological milestones and influential innovators, shedding light on the major stages of keyboard development and the flow of knowledge within the industry. We also integrate edge-betweenenss cluster method to identify the existence of emerging technological advancement applied the keyboard development.

Conclusion & Implications

To explore the knowledge trajectory, we learn from Main Path Analysis (MPA) which reveals three distinct stages in the evolution of musical keyboard instruments: the initial phase focused on acoustic improvements, followed by the integration of electronic components, and culminating in the current era of advanced digital innovations. Notably, key knowledge flows have been observed from the U.S. to Japan, with Yamaha playing a central role in driving innovation. Based on the results, we also find a reciprocal relationship between music and technology. Technological breakthroughs create new musical possibilities, while evolving musical genres inspire further innovation. These technological development stages also explain the emergence of different musical styles. This dynamic suggests that both music and technology continuously influence and propel each other forward, indicating ongoing potential for innovation in the field. Standing at technological view, the research explains the dynamic interactions between technology and music. We also how the importance of these technological developments for future advancements in musical instrument design and production.

Genres are aesthetic and social categories that organise the production and consumption of cultural objects, such as music. Previous research has described genre complexes in music and examined how genre unconventionality relates to the success or failure of musical styles. This paper will extend these approaches by asking how genre complexes influence cultural globalization using a network analytic approach to defining the genre space. We use data from Spotify on the daily top 200 most streamed songs from 68 countries between 2017 and 2021 (about 100,000 songs and 38,000 unique artists). Spotify assigns multiple genre labels to artists; our data include about 3000 unique degree descriptors. To reduce the dimensionality of these genre data, we define a bipartite artist-genre network and community detection methods to identify genre complexes, or clusters. The analysis explores the robustness of this approach to different community detection methods. To determine how genre affects cultural globalization, we define cultural success at the global scale as the number of countries in which a song reaches the top 200 (or alternative thresholds). We estimate zero-inflated negative binomial models of this county count outcome using these network-defined genre complexes as a key predictor. We find that genre complexes substantially explain variation in global cultural success.

### **Abstract**

This study examines the impact of **negative ties**, specifically copyright litigation, on artists' collaboration networks in the music industry. While negative ties, such as lawsuits, are typically associated with reputational damage and social isolation, we argue that they can also serve as catalysts for network reconfiguration and growth. Using a quasi-experimental matched units difference-in-differences (DiD) design, we analyze collaboration patterns of Billboard Hot 100 artists before and after they were sued for copyright infringement. The dataset includes 242 artists (121 sued, 121 matched controls) and 3,400 artist-year observations, with collaboration data sourced via web scraping from MusicBrainz.

Our findings suggest that lawsuits trigger a process of **network repair**, wherein sued artists expand their collaboration networks to counteract the negative repercussions of legal disputes. However, this expansion is not uniform; sued artists are more likely to collaborate with **less experienced** and **differently specialized** alters, who perceive greater benefits and lower risks in such partnerships. These results contribute to the literature on **negative ties** by demonstrating how event-type disruptions interact with state-type ties, influencing both animosity and collaboration. Additionally, this study advances research on creativity by showing how copyright disputes shape artistic collaboration beyond legal consequences. By bridging theories of **negative ties**, network evolution, and creative industries, our findings offer novel insights into the unintended yet strategic responses artists adopt in the face of reputational threats.

This presentation is part of the exploratory research for my doctoral thesis on the international circulation of rap music from Morocco and Egypt, and aims to present the initial findings related to the question of collaborations between rappers and beatmakers and the dynamics of creative innovation in their musical practices

The digital age has profoundly transformed the dynamics of musical production and its processes, especially with the rise of digital production software (Walzer, 2016), and the advent of social media that are reshaping interactions between players in an industry where relational connections play a central role (Budner & Grahl, 2016). These technological tools provide artists and beatmakers with new means to foster creativity and integrate collaborative networks.

The central question in this study is therefore:

How do the dynamics of musical production and the relationships between artists and producers stimulate creative innovation and structure collaborative networks?

This research focuses on the Moroccan rap scene and examines two axes: the relationships and power relations between rappers and beatmakers in the context of their collaborations; and the innovation aspect in these players’ creative practices (particularly through computer-assisted music software). This study seeks to understand how these dimensions influence the evolution of collaborative networks and new forms of musical creation.

The study will be based on interviews with five Moroccan rappers and five beatmakers, an analysis of specific collaboration cases based on these discussions, and a literature review on innovation in the creative field as well as artist-producer relationships.

Information on social networks has been incorporated into music recommendation systems to improve music recommendation quality. The underlying assumption is that social connections between users indicate similar music listening profiles. Existing cultural sociological research supports the notion that one's network patterns correlate with one's taste profiles. However, the questions of to what extent preference similarity relates to social connectedness, and whether social connections broaden users' consumption profiles, are both underexplored. Our work aims at filling these gaps by answering the following research questions. (1) Does music taste similarity correlate with social connectedness? Can we predict users' taste similarity based on their social closeness, and vice-versa? (2) How do music tastes evolve over time and to what extent does the evolution relate to social connections? We address these questions with a quantitative analysis of a large-scale dataset of 17,680 users of Last.fm. The dataset includes following-follower relationships information as well as users' listening events. Our findings will reveal whether social proximity is a reliable predictor of music preference similarity, and whether social networks facilitate or constrain music exploration. These insights on how social networks shape cultural consumption patterns will inform the design of more socially aware music recommendation systems.

Beijing has long been the center of China's independent music ecosystem. However, uneven regional development and the household registration system (hukou), which ties access to social resources to one’s registered place of residence, shape musical practices within the scene, where Beijing locals hold a relatively distinct advantage nationwide. This research investigates the role of regional identity in shaping collaborative networks among artists and support personnel in Beijing through a case study of BADHEAD, a sub-label under Modern Sky, one of China’s most influential music companies. BADHEAD has been instrumental in promoting rock-infused alternative music since 1999. By examining the collaborative networks formed by all artists and support personnel involved in BADHEAD’s album productions from 1999 to 2023, this research explores how regional identity influences the formation and dynamics of these networks.

Using a mixed-methods approach, this study constructs a relational database from the credits of albums released by BADHEAD during this period. Exponential Random Graph Models (ERGMs) are employed to model the networks. The study also incorporates archival materials on the history of Chinese music and interviews with participants. This research examines whether the collaborative networks evolve to exhibit a “local–nonlocal” divide over time and whether nonlocal musicians rely more on institutional support compared to their local counterparts.

This research sheds light on how structural inequalities embedded in regional identity intersect with music production, contributing to a further understanding of the interplay between social institutions and artistic collaboration in creative industries.

"Songify Your Day" was a collaborative songwriting project led by the University of Queensland’s School of Music in partnership with the Moreton Bay Regional Council and the Community Action for a Multicultural Society program in Caboolture, a regional Queensland community. Guided by a renowned Bollywood singer and a celebrated Queensland-based composer, 25 participants from diverse cultural and linguistic backgrounds, aged 18 to 82, took part in an immersive week-long workshop. The experience culminated in a live performance featuring 13 original songs reflecting their native and English languages, cultural identities, and personal memories spanning 13 countries.

This interdisciplinary research project aimed to enhance creativity as a means of fostering human flourishing, promoting psychosocial well-being, and strengthening social engagement. Social network research (SNR) played a key role in uncovering the social dynamics intertwined with songwriting. To map these processes, we applied Relational Hyper Event Models (RHEMs), analysing group interaction and activities such as singing, movement, dancing, playing instruments, discussions, and collective decision-making. These activities were grouped into three interaction types: talking, singing, and cheering. After systematically recording who interacted with whom and when, we applied RHEMs to trace the evolving social connections that drove participants’ engagement in artistic songwriting. Our analysis accounted for hierarchical structures, pre-existing relationships, and individual psychological status measured by the Mental Health Continuum Short Form (MHC-SF). The findings provided new insights into how SNR offered valuable theoretical and analytical contributions to understanding collective music-making practices.

This study employs statistical modelling to investigate the evolution of the Australian improvised musician network over four periods (1970-1990, 1991-1997, 1998-2004, 2005-2023), with particular attention to the period following the introduction of the Creative Nation policy (1998). Using The Jazz Discography (TJD) dataset, which provides extensive data on Australian jazz musicians, the research aims to identify the processes that shape the formation of the network and, potentially, the improvisatory interactions within it. Notably, the period from 1998 to 2004 saw the highest number of recordings, which coincides with a significant restructuring of the network, possibly influenced by the policy’s impact. To model the network’s evolution, Exponential Random Graph Models (ERGM), Bayesian Exponential Random Graph Models (BERGM), and Latent Order Logistic Regression (LOLOG) models were applied. ERGM identified key network formation processes but revealed limitations, particularly in its tendency to exhibit degeneracy in triangle-based models, leading to the adoption of LOLOG. LOLOG offered a more flexible approach by accounting for network dependencies within a full probabilistic framework. Additionally, BERGM was utilized for cross-validation, ensuring that most predictors provided moderate to high acceptance with the observed network and aligned well with the prior expectations. A custom metric, “minTriadicClosure”, was developed within the LOLOG package to measure the number of nodes participating in specified minimum numbers of triadic closures among collaborating musicians, highlighting isolated trios, and network islands disconnected from the larger clusters (a common scenario present among musicians collaborating frequently). The results demonstrate significant shifts in network connectivity, especially during the 1998-2004 period, where an increase in collaborative ties might suggest that cultural and policy shifts played a crucial role in reshaping the Australian improvised music scene, though questions remain about the lasting effects of these transformations.

Music worlds and especially the dynamics of local and translocal scenes are of interest for social network scientists as well as the influence of homogamy and sometimes propinquity to understand processes of musical taste formation and transmission (Crossley et al., 2015). Among SNA researchers, while the spatiality of music worlds is considered, it is rarely the main focus of research. In computational social science, recent works are taking the spatiality of music worlds into account. Way et al. (2020) analysed an adjacency matrix between music listening practices by country and the geographic origin of the artists listened to in each country. They show that both common official language and geographic proximity between countries increasingly shape listener streams during the 2014-2019 period. Computing similarity matrices, Lee et al. (2024) found a decrease in the co-occurrence of music discovered ("Shazamed") within post-soviet republics after the outbreak of the 2022 Russo-Ukrainian War at both the country and the city levels.

In this communication, we aim at measuring the extent to which musical streaming practices vary geographically on several scales and to explore the specific case of French overseas territories. Considering that musical streaming data have become an interesting source to measure socio-cultural proximities between territories, we rely on a dataset of 2.3 B of musical streams across 16 M of users on Deezer between 2020 and 2023. First, we study the co-occurrence of listened artists across countries at the world level using similarity measures. Second, we focus on the case of French departements and compare their patterns of musical listening taking into account the role of geographic distance in the observed results. Finally, we focus on the 5 French Overseas Territories having a departemental status. Sharing a common remoteness from mainland France, they all possess dynamic music scenes and traditionnal genres of their own, whereas, at the same time, being connected to the French and transnational music industry. To better characterise the linkages between these territories, 3.1) we measure the overlap between listening practices across them and 3.2) we compare the networks of co-listened artists in each one of them. By extracting subgraphs resulting from the difference between each pairs of networks, we intend to capture local sub-structures. Finally, 3.3) we consider the songs associated to more than one artist that are listened to within these French overseas territories. We partition this network to identify a common collaboration space between the most popular artists of these territories which could partly foster the proximity between them.