Music Selection Research Articles

Exploring Spotify's Music Popularity Dynamics and Forecasting with Machine Learning

Abstract. Spotify, one of the largest music streaming service providers, boasts a vast user base and an extensive music catalog. To gain a deeper understanding of Spotify users' music preferences and behavioral patterns, this paper conducts a thorough analysis and explores the correlation between music features and user behavior. It collects Spotify users' music listening data and extracts various music features such as energy, danceability, valence, and beats per minute (BPM). These features not only reflect the musical style and rhythm but also potentially correlate with users' preferences and listening habits. Then we employ two machine learning models, Decision Trees and Random Forests, to model and analyze Spotify users' behavior data. Through these models, we can accurately identify potential relationships between music features and user behavior. The experimental results indicate that music features such as energy, danceability, valence, and BPM have a significant impact on users' music selection and preferences. By analyzing the most popular songs on Spotify over different time periods, we discover that songs with high energy, danceability, and valence tend to be more popular among users. This finding not only validates the correlation between music features and user behavior but also reveals the user preferences and market demands behind music trends. For music streaming service providers, understanding users' music preferences and behavioral patterns is crucial. By deeply analyzing user data, music streaming services can better satisfy users' needs, enhance user experience, and stand out in the fiercely competitive market. These findings have important practical implications for music streaming service providers and provide new insights and methodologies for the research and development of the music industry.

The Effect of Music Distraction on Dental Anxiety During Invasive Dental Procedures in Children and Adults: A Meta-Analysis

Background: Dental anxiety and odontophobia are common issues, leading to challenges with oral hygiene and dental health. Music distraction offers an effective and side effect-free solution to alleviate pain and increase the acceptability of dental treatments. Our meta-analysis aimed to assess the efficacy of music distraction in reducing patient anxiety during invasive dental procedures in children and adults. Methods: The PubMed, Web of Science, and Embase databases were searched for clinically controlled trials, using the keywords “music” and “dental anxiety”. The main outcome measured was the anxiety score. A meta-analysis was conducted using a random-effects model to estimate the standardized mean differences (SMDs). The subgroup analyses were conducted based on age groups, music preferences, and music styles. The research protocol has been registered with PROSPERO (Registration ID: CRD42022357961). Results: A total of 24 controlled clinical trials involving 1830 participants met the inclusion criteria for the meta-analysis. Music distraction significantly reduced dental anxiety during invasive procedures under local anesthesia (SMD, −0.50; 95% CI, −0.80 to −0.21; p = 0.0009; I2 = 83%). Our subgroup analysis revealed that music distraction was more effective in adults (SMD, −0.51; p = 0.0007) than in children (SMD, −0.47; p = 0.13) in reducing dental anxiety. Regarding music selection, music chosen by the participant (SMD, −1.01; p = 0.008) demonstrated more anxiolytic effects than by the author (SMD, −0.24; p = 0.02). Regarding music styles, classical music (SMD, −0.69; p = 0.009) was associated with better anxiolytic effects in adults. Conclusions: Our meta-analysis supports the use of music to alleviate dental anxiety during invasive procedures. Listening to classical or customized music can serve as an effective adjunct to outpatient surgical care in dental clinics.

Influencing Factors and Countermeasures to Improve the Expressive Power of Guzheng Artistry

As one of the traditional Chinese musical instruments, guzheng has a deep cultural heritage and unique artistic charm. The improvement of guzheng's artistic expression is of great significance to the inheritance and development of guzheng culture. This paper analyses the factors affecting the guzheng's artistic expression from the aspects of players' skill level, emotional commitment, music selection and arrangement, as well as the playing environment, and puts forward corresponding countermeasures to improve the performance. Firstly, to improve the players' professionalism, including skills training and music theory learning. Secondly, to cultivate the players' musical emotion, so as to make the performance more infectious. Thirdly, innovate music arrangement and performance techniques to meet the needs of different audiences. Finally, improve the playing environment and equipment to provide good material conditions for playing. Through empirical analyses, this paper verifies the effectiveness of the proposed countermeasures and provides useful insights for the future enhancement of guzheng's expressive power.

HARMONIOUS RHYTHMS: EXPLORING THE IMPACT OF MUSIC ON PRODUCTIVITY IN EDUCATIONAL AND WORKPLACE SETTINGS

Background: The relationship between music and productivity has garnered significant interest in both educational and workplace settings, prompting investigations into the cognitive and emotional mechanisms through which music influences task performance. Specific Background: Existing literature suggests that music can enhance cognitive processes, yet findings remain inconclusive regarding its overall impact on productivity levels, particularly in relation to individual differences and environmental factors. Knowledge Gap: Limited empirical studies have simultaneously addressed how genre preferences, personality traits, and contextual variables moderate the effects of music on productivity, highlighting the need for a comprehensive examination of these interactions. Aims: This research aims to elucidate the relationship between music listening and productivity levels among students and employees by employing a mixed-methods approach, integrating quantitative surveys and qualitative interviews. Results: Preliminary findings indicate that music listening positively influences cognitive processes such as concentration and memory while also alleviating stress and anxiety, thus enhancing overall task performance. However, variations were noted based on individual music preferences and the nature of the tasks performed. Novelty: This study uniquely synthesizes insights from psychology, neuroscience, and organizational behavior to provide a nuanced understanding of how music can be effectively integrated into productivity-enhancing strategies. Implications: The results suggest that educators and employers should consider individual preferences and contextual factors when incorporating music into productivity frameworks. By fostering environments conducive to music listening and allowing flexibility in music selection, stakeholders can optimize performance and well-being, thereby promoting creativity and satisfaction in both educational and workplace settings.

Effects of Music Therapy on Patients with Cancer Receiving Outpatient Treatment

Patients with cancer often experience anxiety when waiting for diagnostic test results, before receiving treatment, or when informed of a recurrence. Therefore, appropriate interventions are required at each of these stages. This study determines the effects of music therapy with preferred music on anxiety, blood pressure, pulse, and the satisfaction of patients with cancer when receiving outpatient intravenous therapy in a long-term care facility. This quasi-experimental non-equivalent control-group and non-synchronized study was conducted in the outpatient injection room of a long-term care facility in South Korea. This study included 57 patients (divided into experimental and control groups) with female reproductive system/breast or digestive system cancer who received short-term intravenous vitamin C on an outpatient basis. The participants chose from a music selection table for each genre, which was based on the prior research, under the supervision of a professor experienced in music therapy. The participants selected 20 songs to listen to for 1 h while receiving intravenous therapy. The participants were surveyed for state anxiety and satisfaction to confirm the effects of music therapy, and their systolic and diastolic blood pressure and pulse were measured. The state anxiety (U=282, p=.046) and satisfaction (U=262, p=.016) scores of the experimental and control groups revealed significant differences. There were no significant differences in systolic blood pressure (U=311, p=.13), diastolic blood pressure (t=1.88, p=.065), and pulse (t=-0.5, p=.61) between the experimental and control groups. Music therapy is an effective intervention for reducing anxiety and improving satisfaction in patients with cancer when receiving short-term outpatient treatment. However, to generalize these results, a larger sample size of participants is needed with similar types of cancer.

Impact of Music Selection on Motivation and Performance during Cardiopulmonary Exercise Testing

Impact of Music Selection on Motivation and Performance during Cardiopulmonary Exercise Testing

A GAI-based multi-scale convolution and attention mechanism model for music emotion recognition and recommendation from physiological data

Due to the subjectivity of emotions and the limited number of emotion categories, existing deep learning models require assistance to achieve objective, accurate, and flexible personalized music emotion recommendations. This paper introduces a deep learning approach that combines Generative Artificial Intelligence (GAI) and explicitly leverages physiological indicators to enhance the model's intelligence, versatility, and automation. Physiological indicators such as Heart Rate Variability (HRV) and Galvanic Skin Response (GSR) can be measured using sensors placed on the body's surface, providing more precise information about human emotional changes. This research employs a three-dimensional emotion model, including the tension-arousal axis, energy-arousal axis, and valence axis, to explain the correlation and accuracy between music data and emotions. Based on this, a music emotion classifier is designed, incorporating GAI algorithms to recommend music by matching users' physiological and emotional types with the emotional features of music. The classifier uses Mel-Frequency Cepstral Coefficients (MFCC) to transform audio into Mel-spectrogram as input features. The music emotion selection module adopts a GAI framework of Variational Autoencoder (VAE) and integrates multi-scale parallel convolution and attention mechanism modules. Experimental results demonstrate that this approach is competitive compared to existing deep learning architectures on PMEmo, RAVDESS, and Soundtrack datasets. Furthermore, due to GAI's efficient classification capability, this model is suitable for resource-constrained mobile devices and other smart devices. The results of this study can be applied to emotion-based music recommendation systems, contributing to emotional interventions and improving the performance of exercise and music therapy.

Music-Based Interventions for Symptom Management in Critically Ill, Mechanically Ventilated Adults: A Scoping Review of the Literature.

Background: Patients in intensive care units experience high symptom burden during mechanical ventilation (MV). Pharmacologic symptom management is associated with side effects and increased morbidity. Music-based interventions (MBIs) have been associated with reductions in both anxiety in MV adults and pain for critically ill adults, yet their use for the management of other burdensome symptoms has not been evaluated. The purpose of this scoping review is to map the state of evidence for the use of prerecorded music listening MBIs for symptom management in MV adults. Methods: A systematic search of the literature was conducted across four electronic databases (PubMed, EMBASE, CINAHL, and Web of Science) for experimental designed studies that measured the efficacy of MBIs for the management of physical and psychological symptoms including anxiety, sedation/agitation, dyspnea, distress, delirium, sleep, stress, fear, loneliness, or depression in critically ill, MV adults between January 1, 1998, and April 18, 2023. Results: A total of 643 abstracts and 29 clinical trials were included. Overall, the risk of bias, assessed using the Evidence Project tool, was moderate. MBIs were mostly delivered with headphones using music selected either by investigators or from a limited selection. MBIs were associated with reduced pain, agitation, dyspnea, distress and anxiety, and improved tolerance of MV and sedative weaning. Outcomes of delirium were mixed. No studies explored sleep disturbances, fear, or loneliness. Conclusions: Use of MBIs improved symptom experience for critically ill adults during MV. Future studies employing unrestricted patient-preferred music selections and exploring outcomes of sleep quality, psychological distress, and delirium are needed in this highly symptomatic patient population.

I Cannot Miss It for the World: The Relationship Between Fear of Missing out (FOMO) and Acceptance of ChatGPT

According to the technology acceptance model, people’s acceptance of new technology is influenced by their perception of its usefulness and ease of use. We expand the research agenda by identifying the fear of missing out (FOMO) as a potential factor shaping people’s attitudes toward ChatGPT. We predicted that FOMO experiences, characterized by strong desires to stay connected with other people’s lives, would be linked to more AI-related supportive attitudes. In Study 1 (N = 209), university students with more frequent experiences of FOMO showed more favorable attitudes toward ChatGPT. Study 2 (N = 126) found that participants with a greater FOMO were more likely to choose an invitation letter purportedly authored by ChatGPT, despite it being composed by a human, which provided a behavioral choice confirmation of the observed relationship. Study 3 (N = 186) replicated the findings in a tourism context by employing non-student populations. Study 4 (N = 150) explored the propensity for participants to engage with ChatGPT in personal music selection process and obtained the same effect. Together, these findings suggest that the FOMO bias may exert an additional influence on the endorsement of new technologies, which highlights the important role of emotion in technology acceptance.

Information seeking behaviour in music conductors’ repertoire selection

Introduction. Music repertoire selection is a process driven by music conductors. They focus on scoring, ensemble composition, acquisition methods (i.e., acquiring the music). Information needs and seeking are core to repertoire selection and conductors’ tasks/roles. It cannot be considered in isolation; other conductor responsibilities, past experiences, and external factors (e.g., finances) influence the process and information seeking. We report findings from an exploratory study conducted in 2023 with 37 conductors. Method. Brief literature review, triangulated with findings from a mixed-method study. A semi-structured questionnaire collected quantitative data from 37 conductors and individual online interviews collected qualitative data from two conductors. Analysis. Quantitative data revealed typical tasks requiring information, issues to consider in repertoire selection (e.g., text, ensemble capabilities), internet usage and other information seeking activities and sources. Qualitative data elaborated on factors influencing repertoire selection and information seeking e.g., repertoire inspiration and financial factors. Results & discussion. Three core themes influencing information seeking are discussed: process of repertoire selection, user (individual conductor) characteristics, external factors. The repertoire selection (process) is mapped against information seeking behaviour (activities, sources), user characteristics and external factors. Conclusion. Music repertoire selection’s interdependence with other tasks of music conductors, the importance of individuality and inevitable external factors, influence information seeking.

‘Alexa, play metal’: exploring music selection and personal information management via voice assistants

Introduction. Music streaming services have changed how music is played and perceived, but also how it is managed by individuals. Voice interfaces to such services are becoming increasingly com-mon, for example through voice assistants on mobile and smart devices, and have the poten-tial to further change personal music management by introducing new beneficial features and new challenges. Method. To explore the implications of voice assistants for personal music listening and management we surveyed 248 participants online and in a lab setting to investigate (a) in which situa-tions people use voice assistants to play music, (b) how the situations compare to established activities common during non-voice assistant music listening, and (c) what kinds of com-mands they use. Analysis. We categorised 653 situations of voice assistant use, which reflect differences to non-voice assistant music listening, and established 11 command types, which mostly reflect finding or refinding activities but also indicate keeping and organisation activities. Results. Voice assistants have some benefits for music listening and personal music management, but also a notable lack of support for traditional personal information management activities, like browsing, that are common when managing music. Conclusion. Having characterised the use of voice assistants to play music, we consider their role in per-sonal music management and make suggestions for improved design and future research.

The Influence of Music on Athletic Performance

Purpose: This study sought to explore the influence of music on athletic performance. Methodology: The study adopted a desktop research methodology. Desk research refers to secondary data or that which can be collected without fieldwork. Desk research is basically involved in collecting data from existing resources hence it is often considered a low cost technique as compared to field research, as the main cost is involved in executive’s time, telephone charges and directories. Thus, the study relied on already published studies, reports and statistics. This secondary data was easily accessed through the online journals and library. Findings: The findings reveal that there exists a contextual and methodological gap relating to the influence of music on athletic performance. Preliminary empirical review revealed that music served as a potent tool for regulating arousal levels, enhancing motivation, and directing attentional focus during physical activity. By aligning music characteristics with athletes' preferences and task demands, coaches optimized performance outcomes. Moreover, personalized music selection facilitated motor coordination and cognitive engagement, contributing to improved performance and enjoyment of sports. Overall, the study emphasized the importance of considering individual differences and contextual factors in designing effective music interventions for athletes. Unique Contribution to Theory, Practice and Policy: The Arousal Regulation Theory, Synchronization Hypothesis and Attentional Focus Theory may be used to anchor future studies on the influence of music on athletic performance. The study offered comprehensive recommendations for theory, practice, and policy in sports and exercise contexts. These recommendations included integrating music interventions into training and competition protocols, tailoring music selection to individual preferences, and leveraging music's potential to enhance cognitive function and decision-making skills among athletes. Additionally, the study highlighted the importance of strategic manipulation of music tempo and characteristics to elicit specific psychological and physiological responses conducive to optimal performance. Further research was deemed necessary to explore the underlying mechanisms through which music influences athletic performance and to develop evidence-based guidelines for integrating music into sports practice and policy.

“The Part of the Music Industry That God Forgot”

In October 2020, the B2B (business-to-business) background music company Soundtrack Your Brand—formerly Spotify Business—launched the world’s first full-catalog on-demand streaming service for background music. Although background music providers have licensed, curated, and distributed music to businesses for nearly a century, they have only recently started embracing the new possibilities of streaming. Now, streaming is rapidly influencing the background music industry’s features, music selection practices, and economics. While scholars in music and media studies have extensively studied B2C (business-to-consumer) streaming services such as Spotify and Apple Music, they have largely neglected streaming’s impact on background music. This article investigates how streaming is impacting the B2B background music industry, drawing upon platform analysis, marketing materials, and interviews with background music CEOs and researchers. After reviewing background music’s history and effects, the article examines how streaming is influencing business-oriented background music features, such as scheduling, zoning, messaging, and monitoring. It then considers streaming’s impact on background music selection practices, demonstrating how businesses are increasingly using features popularized by mainstream consumer services, such as playlists, algorithmic recommendations, and massive catalogs of music. The final section explores how streaming is shaping the economics of the background music industry, particularly for rightsholders who have historically been underpaid billions of dollars in public performance royalties. I argue that streaming may improve background music’s efficiency for businesses, but it also potentially reifies broader concerns about social control, surveillance, and inequitable artist remuneration that have become increasingly prevalent in the streaming age.

Accelerated construction of stress relief music datasets using CNN and the Mel-scaled spectrogram.

Listening to music is a crucial tool for relieving stress and promoting relaxation. However, the limited options available for stress-relief music do not cater to individual preferences, compromising its effectiveness. Traditional methods of curating stress-relief music rely heavily on measuring biological responses, which is time-consuming, expensive, and requires specialized measurement devices. In this paper, a deep learning approach to solve this problem is introduced that explicitly uses convolutional neural networks and provides a more efficient and economical method for generating large datasets of stress-relief music. These datasets are composed of Mel-scaled spectrograms that include essential sound elements (such as frequency, amplitude, and waveform) that can be directly extracted from the music. The trained model demonstrated a test accuracy of 98.7%, and a clinical study indicated that the model-selected music was as effective as researcher-verified music in terms of stress-relieving capacity. This paper underlines the transformative potential of deep learning in addressing the challenge of limited music options for stress relief. More importantly, the proposed method has profound implications for music therapy because it enables a more personalized approach to stress-relief music selection, offering the potential for enhanced emotional well-being.

EMOTION BASED MUSIC RECOMMENDATION SYSTEM

The daily lives of people are greatly influenced by music. Everyone wants to listen to music that suits their personal tastes and mood. Users are constantly needed to manually browse the music and construct a playlist based on their mood. The suggested project, which creates a music playlist depending on users' current moods, is quite effective. The most effective approach to convey a person's current mood is through their facial expressions. Webcams are used to capture facial expressions, which are then fed into a learning algorithm to determine the most likely emotion. The emotion recognition system is built using the FER 2013 dataset for training, which allows it to identify seven different emotions. Its operation involves capturing live video input from a webcam, processing it through the model, and then providing a prediction of the detected emotion. By employing webcams to capture real-time facial expressions, the system dynamically adapts playlist recommendations to match the user's emotional state. This seamless integration of emotion recognition technology with music selection enhances user experience by ensuring that the music aligns with their current feelings, thereby fostering a more immersive and personalized listening experience.

Music Recommendation System by Detection of Emotions

Abstract: Expressing emotions through facial expressions is a fundamental aspect of human communication, offering insight into an individual's mood and well-being. The subtle nuances of the eyes, cheeks, forehead, and even the curve of a smile convey a wealth of emotional information. Music, as an art form, holds a unique power to relax and comfort both body and mind. Our project capitalizes on the synergy between these two elements by developing a system capable of discerning emotions from facial expressions and selecting appropriate music in response. This innovative approach not only aids in calming individuals and improving their mood but also streamlines the music selection process, saving valuable time. Furthermore, we aim to create software that offers this functionality universally, enabling users to access emotional music responses anytime, anywhere.

Enhancing Mood Based Music Selection through Physiological Sensing Technology

Abstract: This research paper presents the development of an emotional sensor system that combines computer vision techniques with physiological sensors to detect and analyse facial expressions. The system utilizes a webcam for capturing facial images and integrates Arduino-based hardware components such as a pulse sensor, temperature sensor, galvanic skin sensor, and heart rate sensor for comprehensive emotional analysis. The proposed system aims to contribute to various fields such as human-computer interaction, psychology, and healthcare by providing a non-invasive and real-time method for emotion detection and monitoring.

Hybrid Deep Learning Approach to Emotion-Infused Music Recommendation

Music holds a crucial place in our daily lives, uplifting our spirits and contributing to our overall well-being. However, not all musical genres are suitable for every emotional state, and the vast digital music repositories make it challenging to pinpoint the perfect tune for a specific mood. With the ever-expanding song options, individuals often face confusion when selecting tracks. To address this, a context-aware music recommendation system is introduced, designed to recognize users' current emotions and suggest music that aligns with those feelings. This system takes a comprehensive approach, integrating both context and emotion elements to enhance user preference prediction. The overarching goal is to simplify the music selection process, providing users with a more seamless, intuitive, and enjoyable listening experience. The forthcoming evaluation will delve into performance metrics and research findings, contributing to the ongoing refinement and optimization of this context-sensitive music recommendation strategy. Keywords: Emotion Detection, CNN(Convolutional Neural Network),Video and audio music recommendation

Literature Review : Emotion-Based Music Recommendation System with Age Detection

This research introduces an innovative Emotion-Based Music Recommendation System coupled with Age Estimation. Leveraging computer vision techniques, specifically Convolutional Neural Networks (CNNs), the proposed system analyzes facial data, obtained either through a camera or OpenCV, to discern both the emotional state and age of an individual. The synergy of emotion and age information serves as the foundation for personalized music recommendations. To compose playlists and propose songs, a third-party API is used, personalizing the musical experience to the user's emotional state and age group. This integration of facial analysis, deep learning, and music recommendation aims to enhance user engagement and satisfaction by providing a more contextually relevant and emotionally resonant music selection. Keywords— Emotion-Based Music Recommendation System, Age Estimation, Convolutional Neural Networks (CNN), OpenCV, Deep Learning, Third-Party API.

Deconfounded Cross-modal Matching for Content-based Micro-video Background Music Recommendation

Object-oriented micro-video background music recommendation is a complicated task where the matching degree between videos and background music is a major issue. However, music selections in user-generated content (UGC) are prone to selection bias caused by historical preferences of uploaders. Since historical preferences are not fully reliable and may reflect obsolete behaviors, over-reliance on them should be avoided as knowledge and interests dynamically evolve. In this article, we propose a Deconfounded Cross-Modal matching model to mitigate such bias. Specifically, uploaders’ personal preferences of music genres are identified as confounders that spuriously correlate music embeddings and background music selections, causing the learned system to over-recommend music from majority groups. To resolve such confounders, backdoor adjustment is utilized to deconfound the spurious correlation between music embeddings and prediction scores. We further utilize Monte Carlo estimator with batch-level average as the approximations to avoid integrating the entire confounder space calculated by the adjustment. Furthermore, we design a teacher–student network to utilize the matching of music videos, which is professionally generated content (PGC) with specialized matching, to better recommend content-matching background music. The PGC data are modeled by a teacher network to guide the matching of uploader-selected UGC data of student network by Kullback–Leibler–based knowledge transfer. Extensive experiments on the TT-150k-genre dataset demonstrate the effectiveness of the proposed method. The code is publicly available on https://github.com/jing-1/DecCM