Exploiting MUSIC model to solve cold-start user problem in content-based music recommender systems

The new user cold-start problem is a grand challenge in content-based music recommender systems. This happens when the systems do not have sufficient information regarding the user’s preferences. Towards solving this problem, in this study, a rating prediction framework is proposed. The proposed framework allows the systems to predict the user’s rating scores for unrated musical pieces, by which good recommendations can be generated. The core idea here is to leverage the so-called MUSIC model, i.e., a five-factor musical preference model, which is characterized by Mellow, Unpretentious, Sophisticated, Intense, and Contemporary as the user’s musical preference profiles. When a user newly joins the systems, the first five-factor musical preference profile is established based on the user’s age and brain type information which is extracted from questionnaires. When the user experiences the systems for a certain period, his/her rating scores for experienced musical pieces are utilized for generating the second five-factor musical preference profile. The recommendations are then provided based on the rating scores predicted from a non-linear combination of these two five-factor musical preference profiles. The results demonstrated the effectiveness of the five-factor musical preference in alleviating the new user cold-start problem. In addition, the proposed method can potentially provide high-quality recommendations.

Diurnal fluctuations in musical preference

The rhythm of human life is governed by diurnal cycles, as a result of endogenous circadian processes evolved to maximize biological fitness. Even complex aspects of daily life, such as affective states, exhibit systematic diurnal patterns which in turn influence behaviour. As a result, previous research has identified population-level diurnal patterns in affective preference for music. By analysing audio features from over two billion music streaming events on Spotify, we find that the music people listen to divides into five distinct time blocks corresponding to morning, afternoon, evening, night and late night/early morning. By integrating an artificial neural network with Spotify's API, we show a general awareness of diurnal preference in playlists, which is not present to the same extent for individual tracks. Our results demonstrate how music intertwines with our daily lives and highlight how even something as individual as musical preference is influenced by underlying diurnal patterns.

The Role of Artistic Creative Activities in Navigating the COVID-19 Pandemic in Australia

During the COVID-19 pandemic some Australians turned to artistic creative activities (ACAs) as a way of managing their own mental health and well-being. This study examined the role of ACAs in regulating emotion and supporting mental health and well-being during the COVID-19 pandemic, and also attempted to identify at-risk populations. We proposed that (1) participants would use ACAs as avoidance-based emotion regulation strategies; and (2) music engagement would be used for emotion regulation. Australian participants (N = 653) recruited from the general public completed an online survey, which included scales targeting anxiety (GAD7 scale), depression (PHQ9 scale) and loneliness (two UCLA Loneliness Scales, referring to “Before” and “Since” COVID-19). Participants reported which ACAs they had undertaken and ceased during the pandemic using an established list and ranked their undertaken ACAs in terms of effectiveness at making them “feel better.” For their top-ranked ACA, participants then completed the Emotion Regulation Scale for Artistic Creative Activities (ERS-ACA), and if participants had undertaken any musical ACAs, also the Musical Engagement Questionnaire (MusEQ). The results supported both hypotheses. ANOVAs indicated that participants ranked significantly higher on the “avoidance” ERS-ACA subscale than the other subscales, and that participants ranked significantly higher on the emotion regulation and musical preference MusEQ subscales than the other subscales. Additionally, while ACAs such as “Watching films or TV shows” and “Cookery or baking” were common, they ranked poorly as effective methods of emotion regulation, whereas “Listening to music” was the second-most frequently undertaken ACA and also the most effective. “Singing” and “Dancing” were among the most ceased ACAs but also ranked among the most effective for emotion regulation, suggesting that support for developing pandemic-safe approaches to these ACAs may provide well-being benefits in future crises. Additionally, correlation analyses showed that younger participants, those who took less exercise during the pandemic, and those with the highest musical engagement reported the poorest well-being. We conclude that ACAs provided an important resource for supporting mental health and well-being during the COVID-19 pandemic in Australia and could potentially support mental health and well-being in future crises.

The Relationship Between Valence and Chills in Music: A Corpus Analysis

Chills experienced in response to music listening have been linked to both happiness and sadness expressed by music. To investigate these conflicting effects of valence on chills, we conducted a computational analysis on a corpus of 988 tracks previously reported to elicit chills, by comparing them with a control set of tracks matched by artist, duration, and popularity. We analysed track-level audio features obtained with the Spotify Web API across the two sets of tracks, resulting in confirmatory findings that tracks which cause chills were sadder than matched tracks and exploratory findings that they were also slower, less intense, and more instrumental than matched tracks on average. We also found that the audio characteristics of chills tracks were related to the direction and magnitude of the difference in valence between the two sets of tracks. We discuss these results in light of the current literature on valence and chills in music, provide a new interpretation in terms of personality correlates of musical preference, and review the advantages and limitations of our computational approach.

Testing the Omnivore Hypothesis in Russia

In the last thirty years, a significant shift from the homology to omnivore argument has occurred in musical preference studies. Studies on the omnivore argument mainly come from North and South America, Western and sometimes Eastern Europe. To the best of our knowledge, there are no empirical tests of musical omnivorousness in Russia. The aim of this paper is to reveal omnivore musical preferences in Russia, and analyzes the links between musical preferences, social-demographic profiles, and tolerance. Our research also emphasizes the territory dimension. The research setting is the Perm Region. A survey of 2,400 Perm Region citizens is analyzed using principal component analysis and linear regression provides evidence for the research. Our findings do not indicate omnivore musical tastes in Russia that contradicts the conclusions of the research in other cultures. Instead of finding the omnivore pattern, we found Bourdieu-like patterns of classical versus pop music taste and nostalgic taste versus contemporary taste. Representatives of each taste pattern have a specific social-demographic profile. The urbanization factor influences musical preferences as well. The paper discusses the limitations of the research and directions for further work. Acknowledgements. The publication was prepared within the framework of the project “Intergenerational cultural dynamics” No 18-011-00548А supported by Russian Fundamental Research Fund.

Diurnal fluctuations in musical preference

The rhythm of human life is governed by diurnal cycles, as a result of endogenous circadian processes evolved to maximise biological fitness. Even complex aspects of daily life, such as affective states, exhibit systematic diurnal patterns which in turn influence behaviour. As a result, previous research has identified population-level diurnal patterns in affective preference for music. By analysing audio features from over two billion music streaming events, we find that the music people listen to can be divided into five distinct time blocks corresponding to morning, afternoon, evening, night and late night/early morning. By integrating an artificial neural network with Spotify’s API, we show a general awareness of diurnal preference in playlists, which is not present to the same extent for individual tracks. Our results demonstrate how music intertwines with our daily lives and highlight how evensomething as individual as musical preference is influenced by underlying diurnal patterns.

Musical Preference: Role of Personality and Music-Related Acoustic Features

Personality factors, typically determined by the Big Five Inventory (BFI), have been a primary method for investigating individual preferences in music. While these studies have yielded a number of insights into musical choices, weaknesses exist, owing to the methods by which music is characterized and categorized. For example, musical genre, music-preference dimensions (e.g., reflective and complex), and musical attributes (e.g., strong and mellow), reported within the literature, have arguably produced inconsistent and thus difficult to interpret results. We attempt to circumvent these inconsistencies by classifying music using objectively quantifiable acoustic features that are fundamental to Western music, such as tempo and register. Moreover, it is our contention that the link between musical preference and personality may operate primarily at the level of acoustic features and not at broader categorization levels, such as genre. This study attempts to address this issue. Ninety participants listened to and indicated preference for stimuli that were systematically manipulated by dynamics (attack rate), mode, register, and tempo. Personality was measured using the BFI, allowing for analysis of personality traits and preference for acoustic features. Results supported the link between personality and preference for certain acoustic features. Preference with respect to dynamics was related to openness and extraversion; mode to conscientiousness and extraversion; register to extraversion and neuroticism; and tempo to conscientiousness, extraversion, and neuroticism. Though significant, these associations were relatively weak; therefore, future research could expand the number of manipulated acoustic features. Specific attempts should also aim to disentangle the effects of genre versus acoustic features on musical preferences. Personality–preference relationships at the acoustic-feature level are discussed with respect to music recommender systems and other aspects of the literature.