Talk #1: Music Popularity, Diffusion, and Recommendation in Social Networks: A Fusion Analytics Approach
Today, people can easily gain access to a massive amount of music-related information through streaming music and social networks. The music industry has begun to pay attention to promoting music by leveraging social networks such as YouTube. My interest involves understanding music and artist popularity, music diffusion, and music promotion in the social network context. My research questions include: What makes a music track popular? Is it possible to explain and predict a music track’s popularity? What are the key factors in the diffusion process for popular music? Can we design an effective recommendation system to make diffusion go faster? To answer these research questions, I am working on three essays. They involve fusion analytics and hybrid system design, that encompass theoretical arguments, econometric analysis of big data, and construction of a software application. Essay 1 investigates the patterns over time of music popularity by combining machine learning and explanatory econometric methods. Essay 2 examines the key impacts on the process of music diffusion by exploring cascade propagation. Essay 3 is a design science work that builds a decision tool to help industry professionals promote music and artists more effectively. My research has produced several massive data sets from multiple social networks, I hope to be able to shed light on new aspects of music popularity and how to promote music better.
Talk #2: Understanding Music Track Popularity in a Social Network
Thousands of music tracks are uploaded to the Internet every day through websites and social networks that focus on music. While some content has been popular for decades, some tracks that have just been released have been ignored. What makes a music track popular? Can the duration of a music track’s popularity be explained and predicted? By analysing data on the performance of a music track on the ranking charts, coupled with the creation of machine-generated music semantics constructs and a variety of other track, artist and market descriptors, this research tests a model to assess how track popularity and duration on the charts are determined. The dataset has 78,000+ track ranking observations from a streaming music service. The importance of music semantics constructs (genre, mood, instrumental, theme) for a track, and other non-musical factors, such as artist reputation and social information, are assessed. These may influence the staying power of music tracks in online social networks. The results show it is possible to explain chart popularity duration and the weekly ranking of music tracks. This research emphasizes the power of data analytics for knowledge discovery and explanation that can be achieved with a combination of machine-based and econometrics-based approaches.
These are pre-conference talks for 25th European Conference on Information Systems (ECIS 2017).
About the Speaker
Jing REN is a PhD student in the School of Information System, Singapore Management University under the supervision of Prof. Robert J. Kauffman. She received her M.Eng. degree in Digital Information Processing from Hefei University of Technology. Her research lies in the social media analysis, data mining, user behavior analysis, information diffusion and recommender systems. She is interested in applying data analytics, econometrics, optimization and other relevant methodologies to support decision-makers in digital media understanding and promotion.
