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.

Academic Motivation in Introductory Business Analytics Courses: A Bayesian Approach

The MUSIC (eMpowerment, Usefulness, Success, Interest, Caring) Model of Academic motivation was developed to help instructors promote student motivation in the classroom. This study examines relationships among student perceptions of motivation and effort compared with their performance in undergraduate business analytics courses. Specifically, the study will attempt to answer the questions of whether students’ scores on the MUSIC model predict or explain effort, academic performance, course rating, and instructor rating. A Bayesian approach to linear regression is used to determine and understand the impact of the MUSIC model components on the aforementioned output measures.

Musical Preferences of Teenagers and Adults: Evidence from a Spanish-Speaking Sample

Music consumption is widely recognized as an important facet of everyday life, and the use of algorithms by online streaming services to suggest songs has aroused a growing scientific interest in how musical preferences are structured. However, existing studies have failed to include Latin genres of music. Therefore, the aim of this study was to develop and validate a measure to assess the musical preferences of Spanish-speaking teenagers and adults. To do this, two independent studies were developed ( N1 = 312 Spanish teenagers; N2 = 345 Spanish-speaking adults) using an instrument based on a theoretical structure consisting of 20 musical genres, which reflects the MUSIC model. The results indicated the exclusion of reggaetón for both groups, and confirmed the proposed theory of five dimensions of musical preferences: (a) Intense: emphasis on low sounds and use of electronic instruments; (b) Sophisticated: complex musical structure, dissonant harmonies, and melodies that explore unconventional patterns and diversified rhythms; (c) Contemporary: striking rhythm, emphasis on percussion and electronic instruments, versatility in the prosodic construction of lyrics, and often linked to themes such as inequality and social injustice; (d) Moving: strong connection to dance, especially partner dances, with strong potential for socialization; (e) Unpretentious: music with strong cultural roots specific to the research context. In conclusion, the Scale for Musical Preferences Assessment proved to be an effective instrument for assessing the musical preferences of teenagers and adults, presenting a standard structure for both groups, although there were differences in their perception of musical genres.

Pedagogical conditions and methods aimed at the formation of musical-auditory representations of future teachers of Musical Arts

The article is devoted to the phenomenon of auditory representations, their content, compliance with musical content, formation, tuning and implementation in the performance process of the future teacher during piano training. The purpose of the article is to substantiate the pedagogical conditions and develop the methods aimed at forming of the future music teacher’s musical-auditory representations. The goal is realised through the implementation of relevant tasks using the methods of theoretical research: analysis, synthesis, deduction, systematisation, pedagogical observation. In the article musical-auditory representation is considered as a professional skill of a musician, formed on the basis of the understanding of semantics – semantic units of musical language, which facilitates the qualitative reproduction of artistic and figurative content and maximum efficiency of musician’s own performance process in creation of artistic-pedagogical and performing interpretations. The list of the skills acquired by the applicant during the formation of auditory perceptions is specified, namely: analytical (to identify and understand the symbolism of musical language; its genre and style) (compare semantic constructs of different musical directions); reflexive, figurative-auditory and sensorimotor. The pedagogical conditions for the formation of auditory representations are offered: gradual expansion of a musical thesaurus in the course of the profession-centred training; stimulating auditory perception by recognising and understanding the elements of musical language; the direction of musical-perceptual experience on the coordination of auditory representations with the sign-semantic context of the performed works. In accordance with the defined conditions, a number of methods have been developed: comparative textual analysis; figurative and auditory analysis; perceptual-auditory analysis; associative music model; semantic identification; artistic reincarnation; polytonation expressiveness; tactile-auditory method. Further research involves the development of the future Arts teachers’ auditory perceptions in classes on accompaniment and ensemble playing, taking into account the specifics of these subjects.

One Small Step in the Lecture Hall, One Big Step for Student Motivation: Short Bursts of In-Class Small Group Work

Great teachers are continually introducing strategies to engage students, especially those who teach large-lecture classes, whose format can limit active learning and student motivation to engage in learning. Implementation of active teaching strategies must be assessed for effectiveness. Using the simple MUSIC model postcourse assessment survey, student motivation to engage in learning was statistically quantified. A simple short intervention of in-class group work led to significant areas of improvement, which included the students’ perception of the class’ Usefulness towards their future career ( p < .01), their perceived ability for Success in the class ( p < .01), their Interest in the material ( p < .01), and their perception of the instructor Caring about their success ( p < .05). No change was seen in e Mpowerment. In addition, students rated the ease of the class ( p < .01) and the overall satisfaction with the course ( p < .01) significantly higher than the previous semester, prior to the in-class group work implementation. The implementation of this short simple intervention of in-class group work was highly successful in increasing student motivation in a large-lecture, in-major required exercise and health class and can be easily adapted to other large-lecture classes.

Frequently Occurring Melodic Patterns are Easier to Recall

Melodic memory continues to present a paradox. Listeners excel at recognizing melodies once encoded in long term memory, but often struggle during encoding. In order to investigate this paradox, we employ a recall design to investigate melodic encoding. Here we report results from a forward, serial recall within-subjects melodic memory experiment (n = 39) using an expert population of musicians trained in moveable-do solfege in order to model melodic memory using music theoretic response categories. Compatible with theoretical frameworks predicting a processing facilitation advantage, more frequently occurring musical patterns are remembered more quickly and more accurately than less frequently occurring patterns. The evidence presented here is consistent with evidence suggesting that latent understanding of musical schemas can be modeled with musical corpora. Further, computationally derived measures related to information processing from both the Information Dynamics of Music model and FANTASTIC toolbox outperform models of melodic memory that only account for the length of the melody measured in number of notes. Results from this experiment demonstrate how expert populations can provide valuable insight into melodic memory and tonal cognition. The framework provided here also provides an empirical basis linking literature investigating melodic anticipation with melodic memory.

Course of Artificial Intelligence + Composition for Young Backbone Teachers

Based on the analysis of the needs in the education field, the basic application framework scenarios of the current artificial intelligence technology in the field of music education are constructed. The characteristics of various models (typed music model, Markov chain model, genetic algorithm model, neural network model, etc.) are used to improve the rule knowledge to form a practical and effective hybrid model. The innovation lies in combining non-note units (reproducing structures) in music composition to intelligently compose tracks by combining formulas and matrix data combinations. The project conducts in-depth cooperation on the training of composition teachers and students from the fields of curriculum teaching, practical teaching, and innovation competition, and strives to combine theoretical teaching and engineering cases, practical teaching and industrial products, subject competition and intelligent technology. Combination to achieve collaborative education of industry-academia cooperation.

Seni Beluk Cikondang Indigenous Village Reviewed from the Perspective of Music Education

The research was conducted to develop a music model based on local wisdom at Cikondang village, Pangalengan, West Java. The research problem was that, along with the changing times, the next generation tended to ignore the values of local wisdom. Therefore, through music learning, the values of art could be understood and actualized in everyday life. Music (nembang and ngabeluk) became a medium to express values in pupuh verses which contained wawacan about the relationship between man and their God, man, and others, and man and their surroundings. The data collection was done using observation, interview, and literature review then analyzed with the music education approach. The obtained results reveal that the learning process of seni beluk in Cikondang Village has taken place in the context of community education which is done informally, and formed naturally. There is no invitation or coercion from the elders to the next generation to learn this art form. Meanwhile, for people from the next generation who has a passion for learning. The learning steps do not only train their techniques, but they also learn about the values ingrained in the pupuh verses.