Music has a close relationship with people's emotion and mental status. Music recommendation has both economic and social benefits. Unfortunately, most existing music recommendation methods were ...constructed based on genre features (e.g., style and album), which cannot meet the emotional needs of listeners. Furthermore, the “filter bubble” effect may make the situation even worse, when a user seeks music for emotional support. In this study, we designed a novel emotion-based personalized music recommendation framework to meet users’ emotional needs and help improve their mental status. In our framework, we designed a LSTM-based model to select the most suitable music based on users’ mood in previous period and current emotion stimulus. A care factor was used to adjust the results so that users’ mental status could be improved by the recommendation. The empirical experiments and user study showed that the recommendations of our novel framework are precise and helpful for users.
•An emotion-aware computational model based on affective user profiles is proposed•An affective coherence score between an item and the user profile is defined•The model is integrated in state-of-art ...recommendation approaches•The way preferences depend on user emotional state varies from user to user
Decision making is the cognitive process of identifying and choosing alternatives based on preferences, beliefs, and degree of importance given by the decision maker to objects or actions. For instance, choosing which movie to watch is a simple, small-sized decision-making process. Recommender systems help people to make this kind of choices, usually by computing a short list of suggestions that reduces the space of possible options. These systems are strongly based on the knowledge of user preferences but, in order to fully support people, they should be grounded on a holistic view of the user behavior, that includes also how emotions, mood, and personality traits influence her choosing patterns.
In this work, we investigate how to include emotional aspects in the recommendation process. We suggest that the affective state of the user, defined by a set of emotions (e.g., joy, surprise), constitutes part of choosing situation that should be taken into account when modeling user preferences.
The main contribution of the paper is a general emotion-aware computational model based on affective user profiles in which each preference, such as a 5-star rating on a movie, is associated with the affective state felt by the user at the time when that preference was collected.
The model estimates whether an unseen item is suitable for the current affective state of the user, by computing an affective coherence score that takes into account both the affective user profile and not-affective item features. The approach has been implemented into an Emotion-aware Music Recommender System, whose effectiveness has been assessed by performing in-vitro experiments on two benchmark datasets. The main outcome is that our system showed improved accuracy of recommendations compared to baselines which include no affective information in the recommendation model.
Music, as a carrier of emotional sustenance, can not only achieve spiritual resonance in the process of listening but also reflect the vitality of life in the rhythm of music. As an effective relief ...method, music intervention has far-reaching significance in the development of psychotherapy. In the practice of music therapy, music selection is particularly important, and the rationality and rigor of music selection directly affect the therapeutic effect. The process of music selection in music therapy is in common with Internet music recommendation, so it has theoretical and practical value to apply personalized music recommendation algorithms to music therapy. In this paper, driven by big data, a music recommendation model based on an improved collaborative filtering (CF) algorithm is proposed, which combines the psychological adjustment of users’ music preferences and different music rhythm features to select music for music therapy and provides theoretical support for music therapy selection. The results show that the construction of music resources for music therapy based on an improved CF algorithm can greatly improve the music selection process of music therapy.
In the process of the rapid development of mobile networks, music recommendation systems (MRSs) have experienced considerable success in recent years. Conventional music recommendation systems are, ...however, in general based on the simple user–track relationships or the content of songs and recommend songs according to intrinsic factors. Furthermore they do not consider the users’ contextual factors towards providing them with a more interpretable, efficient and smart recommendation experience. To address these issues, we propose a novel Heterogeneous Information Network-based Music Recommendation System (HIN-MRS). By considering the extrinsic factors, such as contextual factors, internal factors, such as the user’s personalized preference, and the heterogeneous relationship between items of song information, this method can perceive the user’s music selection from multiple aspects, automatically maintain the user’s playlist and improve the user’s music experience. First we used the obtained textual data to extract the user’s music preference to provide the topic which is usually related to the contextual factors, by means of which an HIN-MRS can realize the perception of the mobile environment. Second, after determining the topics, we built a small-scale HIN of songs (song HIN) according to topics and used a graph-based algorithm to generate recommendations. The recommendation method based on an HIN renders the recommendation process more efficient and the recommendation results more accurate and increases the users satisfaction. The results of our final experiments also prove the significant advantages of the proposed model over the conventional approaches.
Tag-aware dynamic music recommendation Zheng, Ervine; Kondo, Gustavo Yukio; Zilora, Stephen ...
Expert systems with applications,
09/2018, Letnik:
106
Journal Article
Recenzirano
•Model users’ time-sensitive preference on music.•Use dynamic matrix factorization integrated with tag information to provide time-sensitive music recommendation.•Conduct extensive experiments over ...real-world data for evaluation.
We present a tag-aware dynamic music recommendation framework that achieves personalized and accurate music recommendations to users. The proposed framework leverages the available semantic labels (in terms of tags) of music tracks to complement a highly sparse user-item interaction matrix, which effectively addresses the data sparsity issue faced by most music recommendation systems. Music tracks are more accurately represented by aggregating the latent factors derived from both the tag space and the user interaction information. The proposed framework further employs a Gaussian state-space model to capture the evolving nature of users’ preferences over time, which helps achieve time-sensitive recommendation of music. A variational approximation is developed to achieve fast inference and learning of model parameters. Experiments conducted using actual music data and comparison with state-of-the-art competitive recommendation algorithms help demonstrate the effectiveness of the proposed framework.
Personalized and fascinating music recommendations are becoming increasingly in demand as the advent of technology continues to change the way that people consume music. Traditional music ...recommendation systems primarily rely on user listening history and preferences, often neglecting the emotional and experiential dimensions that make music a deeply personal and entertaining endeavour. This research introduces a music recommendation system after classifying the tracks using a novel Gravitational Search Optimized Recursive Neural Networks (GS-RNN) approach. GS-RNN addressed this gap by integrating the Gravitational Search Algorithm (GSA) with Recursive Neural Networks (RNN) to create a content-based recommendation system that assesses audio signal similarity. Evaluation metrics, including accuracy (80%), logarithmic loss (0.85), precision (84%), recall (83%), and F1-score (88%), demonstrate GS-RNN’s superiority over existing techniques. Genre-specific accuracy analysis further underscores the model’s capability to suggest songs within the same genre. Overall, GS-RNN presents a novel and effective paradigm for music recommendations.
•Proposal of a collaborative filtering (CF) method for music recommendation.•The method is based on user and artist characterization.•Only playing information that can be implicitly obtained is ...needed.•The proposal can be applied for both rating prediction and item recommendation.•The method outperforms other CF approaches.
The great quantity of music content available online has increased interest in music recommender systems. However, some important problems must be addressed in order to give reliable recommendations. Many approaches have been proposed to deal with cold-start and first-rater drawbacks; however, the problem of generating recommendations for gray-sheep users has been less studied. Most of the methods that address this problem are content-based, hence they require item information that is not always available. Another significant drawback is the difficulty in obtaining explicit feedback from users, necessary for inducing recommendation models, which causes the well-known sparsity problem. In this work, a recommendation method based on playing coefficients is proposed for addressing the above-mentioned shortcomings of recommender systems when little information is available. The results prove that this proposal outperforms other collaborative filtering methods, including those that make use of user attributes.
Our work is concerned with the subjective perception of music similarity in the context of music recommendation. We present two user studies to explore inter- and intra-rater agreement in ...quantification of general similarity between pieces of recommended music. Contrary to previous efforts, our test participants are of more uniform age and share a comparable musical background to lower variation within the participant group. The first study uses carefully curated song material from five distinct genres while the second uses songs from a single genre only, with almost all songs in both studies previously unknown to test participants. Repeating the listening tests with a two week lag shows that intra-rater agreement is higher than inter-rater agreement for both studies. Agreement for the single genre study is lower since genre of songs seems a major factor in judging similarity between songs. Mood of raters at test-time is found to have an influence on intra-rater agreement. We discuss the impacts of our results on evaluation of music recommenders and question the validity of experiments on general music similarity.
Abstract Music and affects share a long history. In recent times, 4E cognitive sciences (embodied, embedded, enacted, and extended), situated affectivity, and related ecological theoretical ...frameworks have been conceptualizing music as a case of a tool for feeling. Drawing on this debate, I propose to further theorize the role of music in situating our affectivity by analyzing how the very affective affordances of music are technologically situated. In other words, I propose to shift the attention from music as a tool for feeling to the tools for feeling music. I argue that the experience of music as a tool for feeling may be altered, enhanced, or lessened depending on the tools for feeling music. I investigate the extent to which AI might be a case of a tool for feeling music and examine the influence it could exert over musical affectivity. I conclude that AI can be considered a tool for feeling music of curatorial type and that the limitations and/or biases of AI as a method risk lessening the power of musical affective affordances.