In recent years, music has become increasingly universal due to technological advances. All kinds of music have become more complex and a large amount around us. How recommending the music that user is interested in from a wide variety of music is the development intentions of the music recommendation system MRS (Music Recommendation System). In the recommending system, the most widely known is Content-based (CB) and Collaborative (COL). Chen et al. have proposed an alternative way that used CB and COL of music recommendation. The purpose of the CB method is to recommend the music objects that belong to the music groups the user is recently interested in. Each transaction is assigned a different weight, where the latest transaction has the highest weight. The preferences of users are derived from the access histories and recorded in profiles. Based on the collaborative approach, the purpose of the COL method is to provide unexpected findings due to the information sharing between relevant users. But in the CB method, the formula of computing music group weight pays much attention to the weight of the transaction. This will lead to the result that the group weight of music group B which appears once in the later transaction is larger than the group weight of the music group A which appears many times in the earlier transaction. In the COL method, they do not care the density of the group, where high density means that the transactions which the music group appears are close in the access history of the user. This will lead to the result that the supports of the groups which have different densities are the same, and then the users may be grouped together. Therefore, in this thesis, we propose the TICI (Transaction-Interest-Count-Interest) method to improve the CB method. Considering the two situations of the music group that user is interested in, the large count of music group and the appearance in the later transaction, we put two parameters: Count-Interest and Transaction-Interest in our TICI method to let users choose which weight they want to emphasize. Sometimes, people not only want the music object from one group. We extend the TICI method to find the group pair that the user is interested in. We use two thresholds: CountT and WeightT to decide which candidates can be in the large itemset. In our propose method, we have two possible ways to find the result. And we propose the DI (Density-Interest) method to improve the COL method. Our DI method calculates the supports of music groups and consider the distributions of appearances of the music group. From our simulation results, we show that our TICI method could provide better performance than the CB method. Moreover, our DI method also could provide better performance than the COL method.

Spotify is currently the worlds leading music streaming ser-vice. As the leader in music streaming the task of providing listeners with music recommendations is vital for Spotify. Listening to playlists is a popular way of consuming music, but traditional recommender systems tend to fo-cus on suggesting songs, albums or artists rather than pro-viding consumers with playlists generated for their needs. This thesis presents a scalable and generalizeable approach to music recommendation that performs song selection for the problem of playlist generation. The approach selects tracks related to a playlist theme by finding the charac-terizing variance for a seed playlist and projects candidate songs into the corresponding subspace. Quantitative re-sults shows that the model outperforms a baseline which is taking the full variance into account. By qualitative results the model is also shown to outperform professionally curated playlists in some cases.

Music listening is considered one of the most ubiquitous activities in everyday life, and one of the main reasons why people listen is to affect and regulate their mood. The vast availability and unlimited access of music has made it difficult to find relevant music that fits both the context and the preferences of the music listener. The aim of this project was to investigate the personalized relationship between music and mood using everyday technologies, focusing on how a listening experience could be adapted to the desired affect of a music listener while also taking the user’s individual listening history into account. In large, the project concentrated on the possibility of using context-aware music recommendation to generate personalized playlists by focusing on the audio features and corresponding mood of the music. A web-based application was developed to act as a prototype for the study, where the application allowed users to connect to Spotify, pick a desired mood and generate a playlist. By allowing people to access music in this personalized way, a user study could be conducted in order to investigate their music listening while incorporating this recommendation tool. The findings showed that the users’ found the experience to be engaging in that they could use the application as a companion to everyday tasks in addition to it being a tool for getting new, personalized music recommendations. Overall, the participants also found the generated playlists to be accurate to their music preferences and desired affective state.

With the volume of digital media available today, automatic music recommendation services have proven a useful tool for consumers, allowing them to better discover new and enjoyable music. Typically, this technology is based on collaborative filtering techniques, employing human-generated metadata to base recommendations. Recently, work in content-based recommendation systems have emerged in which the audio signal itself is analyzed for relevant musical information from which models are built that attempt to mimic human similarity judgments. The current state-of-the-art for content-based music recommendation uses a timbre model based on MFCCs calculated on short segments of tracks. These feature vectors are then modeled using GMMs (Gaussian mixture models). GMM modeling of frame-based MFCCs has been shown to perform fairly well on timbre similarity tasks. However, a common problem is that of hubs , in which a relative small number of songs falsely appear similar to many other songs, significantly decreasing the accuracy of similarity recommendations. In this thesis, we explore the origins of hubs in timbre-based modeling and propose several remedies. Specifically, we find that a process of model homogenization, in which certain components of a mixture model are systematically removed, improves performance as measured against several ground-truth similarity metrics. Extending the work of Aucouturier, we introduce several new methods of homogenization. On a subset of the uspop data set, model homogenization improves artist R-precision by a maximum of 3.5% and agreement to user collection co-occurrence data by 7.4%. We also find differences in the effectiveness of the various homogenization methods for hub reduction, with the proposed methods providing the best results. Further, we extend the modeling of frame-based MFCC features by using a kernel density estimation approach to non-parametric modeling. We find that such an approach significantly reduces the number of hubs (by 2.6% of the dataset) while improving agreement to ground-truth by 5% and slightly improving artist R-precision as compared with the standard parametric model. Finally, to test whether these principles hold for all musical data, we introduce an entirely new data set consisting of Indian classical music. We find that our results generalize here as well, suggesting that hubness is a general feature of timbre-based similarity music modeling and that the techniques presented to improve this modeling are effective for diverse types of music.

With a rapid growth in smartwatch and smartwatch audio technologies, there is a lack of knowledge regarding user needs for smartwatch audio experiences and how those needs can be satisfied through user-centered design. Previous smartwatch user behavior studies suggest that audio app usage is not a primary use case for the smartwatch. However, audio applications are increasingly incorporated into smartwatches, which leads to the question of the apps’ purpose, validity, overlooked contexts and use cases. This thesis aims to understand what kind of audio experience(s) a user-centered design process might generate for the smartwatch. The design process generated insights from smartwatch users of audio applications, that were used as design guidelines for Context Awareness, Micro-interactions, and Device Ecosystem. The resulting prototype HeartBeats considers Context Awareness with heart rate music recommendations, Micro-interactions with one-handed song skipping and Quickplay music, and Device Ecosystem with speaker access and phone battery support. / Med en snabb teknisk utveckling av smartklockor och tillhörande ljudteknik finns det en kunskapsbrist om användarbehov och hur dessa kan tillfredsställas genom användarcentrerad design. Tidigare forskning om smartklocksanvändares beteenden tyder på att ljudapplikationer inte är ett huvudsakligt användningsområde för smartklockor. Ljudapplikationer implementeras dock allt mer i smartklockor, vilket leder till frågan om vilket värde de ger och om användningsområden möjligen har förbisetts. Den här uppsatsen syftar till att förstå vilka sorts ljudupplevelser en användarcentrerad designprocess skulle resultera i för smartklockor. Designprocessen resulterade i insikter om smartklocksanvändares beteenden med ljudapplikationer, vilket användes som designriktlinjer för kontextmedvetenhet, mikrointeraktioner och ekosystem av enheter. Den resulterande prototypen HeartBeats nyttjar kontextmedvetenhetgenom att rekommendera musik med användarens hjärtrytm i åtanke, mikrointeraktioner med en gest för att byta låt och snabbstart av musik, samt ekosystem av enheter genom snabb åtkomst till klockhögtalare och stöd för att spara telefonbatteri.

This thesis proposes a two-stage recommendation system for providing music recommendations based on seed playlists as inputs. The goal is to help businesses find relevant and brand-fit music to play in their venues. The problem of recommending music using machine learning has been investigated quite a bit in both academia and the industry, with collaborative filtering and content-based filtering being the major approaches used. One of the difficulties of creating a recommendation system is how to evaluate it. In this thesis, both a quantitative and a qualitative evaluation are made to determine how well the results correspond to the actual quality of recommendations. The application of recommending music to businesses also poses different problems than a service directed at end consumers, mostly related to how many track recommendations are needed. A two-stage approach was used with Stage 1 producing candidates and a Stage 2 model using a neural network comparing five tracks from the playlist with a candidate was used to rank said candidates. The results show that the Stage 2 model has substantially better results in both the qualitative and quantitative evaluation compared to Stage 1. The quality of the recommendations from the whole system is not completely satisfactory, and some possible reasons for this are discussed, including improving the Stage 1 candidate generator (which was not modified in the scope of this thesis). / Automatisk musikrekommendation med hjälp av maskininlärning har utforskats av både industrin och akademin genom åren, där två huvudsakliga metoder utkristalliserats: collaborative filtering samt content-based filtering. I det här arbetet har en content-based modell tagits fram, uppdelad i två stadier: Steg 1 som genererar kandidater som Steg 2 sedan ordnade om med hjälp av ett neuralt nätverk som jämförde 5 låtar i taget från en spellista med motsvarande kandidater genererade av Steg 1 En av svårigheterna med att skapa automatiska rekommendationer är utvärderingen av den. I det här arbetet har både en kvantitativ och kvalitativ studie utförts för att försäkra att resultaten motsvarar den faktiska kvaliten hos rekommendationerna. Slutmålet med att hjälpa företag med musikrekommendation ställer också unika problem att lösa i jämförelse med en tjänst för privatpersoner, framförallt relaterat till storleken på de returnerade rekommendationerna. Resultaten visade att Steg 2 lyckades rangordna rekommendationerna från Steg 1 på ett sätt som gav högre poäng i både den kvantitativa och kvalitativa utvärderingen av systemen. De slutgiltiga resultaten var inte helt tillfredsställande, och potentialla orsaker till detta diskuteras. Dessa inkluderar Steg 1 (som inte modifierades inom ramen för detta arbete). Utvärderingen visade dock att de kvantitativa utvärderingsramarna verkar motsvara den upplevda kvaliten hos rekommendationerna baserat på den kvalitativa utvärderingen.

在WEB2.0的時代，網際網路中充斥著各式各樣的互動式平台。就音樂網站而言，使用者除了聽音樂外，更開始習慣於虛擬空間中交流及分享意見，並且在這些交流、分享的過程中留下他們的足跡，間接的提供許多帶有個人色彩的資訊。利用這些資訊，更貼近使用者的推薦系統因應而生。本研究中，將針對使用者過去存取過的音樂特徵以及使用者於系統中留下的文字評論特徵這兩個部份的資料，做音樂特徵的擷取、找尋具有價值的音樂特徵區間、建立使用者音樂特徵偏好，以及文字特徵的擷取、建立使用者文字特徵偏好。接著，採用協同式推薦方式，將具有相同興趣的使用者分於同一群，推薦給使用者與之同群的使用者的喜好物件，但這些推薦之物件為該使用者過去並沒有任何記錄於這些喜好物件上之物件。我們希望對於音樂推薦考慮的開始不只是音樂上之特徵，更包含了使用者交流、互動中留下的訊息。 / In the era of Web2.0, it is flooded with a variety of interactive platforms on the internet. In terms of music web site, in addition to listening to music, users got used to exchanging their comments and sharing their experiences through virtual platforms. And through the process of exchanging and sharing, they left their footprints. These footprints indirectly provide more information about users that contains personal characteristics. Moreover, from this information, we can construct a music recommendation system, which provides personalized service. In this research, we will focus on user’s access histories and comments of users to recommend music. Moreover, the user’s access histories are analyzed to derive the music features, then to find the valuable range of music features, and construct music profiles of user interests. On the other hand, the comments of users are analyzed to derive the textual features, then to calculate the importance of textual features, and finally to construct textual profiles of user interests. The music profile and the textual profile are behaviors for user grouping. The collaborative recommendation methods are proposed based on the favorite degrees of the users to the user groups they belong to.

The last decade has brought with it a wave of innovative technology, shifting the channels through which creative content is created, consumed, and categorized. And, as our interactions with creative multimedia content shift towards online platforms, the sheer quantity of content on these platforms has necessitated the integration of algorithmic guidance in the discovery of these spaces. In this way, the recommendation algorithms that guide users' interactions with various art forms have been cast into the role of gatekeepers and begun to play an increasingly influential role in shaping the creation of artistic content. The work laid out in the following chapters fuses three major areas of research: graph representation learning, music information retrieval, and fairness as applied to the task of music recommendation. In recent years, graph neural networks (GNNs), a powerful new architecture which enables deep learning approaches to be applied to graph or network structures, have proven incredibly influential in the music recommendation domain. In tandem with the striking performance gains that GNNs are able to achieve, many of these systems, have been shown to be strongly influenced by the degree, or number of outgoing edges, of individual nodes. More concretely, recent works have uncovered disparities in the qualities of representations learned by state of the art GNNs between nodes which are strongly and weakly connected. Translating these findings to the sphere of recommender systems, where nodes and edges are used to represent the interactions between users and various items, these disparities in representation that are contingent upon a node's connectivity can be seen as a form of popularity bias. And, indeed, within the broader recommendation community, popularity bias has long been considered an open problem, in which recommender systems begin to favor mainstream content over, potentially more relevant, but niche or novel items. If left unchecked these algorithmic nudged towards previously popular content can create, intensify, and enforce negative cycles that perpetuate disparities in representation on both the user and the creator ends of the content consumption pipeline. Particularly in the recommendation of creative (e.g. musical) content, the downstream effects in these disparities of visibility can have genuine economic consequences for artists from under-represented communities. Thus, the problem of popularity bias is something that must be addressed from both a technical and societal perspective. And, as the influence of recommender systems continues to spread, the effects of this phenomenon only become more spurious, as they begin to have critical downstream effects that shape the larger ecosystems in which art is created. Thus, the broad focus of thesis is the mitigation of popularity bias in music recommendation. In order to tailor our exploration of this issue to the graph domain, we begin by formalizing the relationship between degree fairness and popularity bias. In doing so, we concretely define the notion of popularity, grounding it in the structural principles of an interaction network, and enabling us to design objectives that can mitigate the effects of popularity on representation learning. In our first work, we focus on understanding the effects of sampling on degree fairness in uni-partite graphs. The purpose of this work is to lay the foundation for the graph neural network model which will underlie our music recommender system. We then build off this first work by extending the initial fairness framework to be compatible with bi-partite graphs and applying it to the music domain. The motivation of this work is rooted in the notion of discovery, or the idea that users engage with algorithmic curation in order to find content that is both novel and relevant to their artistic tastes. We present the intrinsic relationship between discovery objectives and the presence of popularity bias, explaining that the presence of popularity bias can blind a system to the musical qualities that underpin the underlying needs of music listening. As we will explain in later sections, one of the key elements of this work is our ability to ground our fairness notion in the musical domain. Thus, we propose a domain-aware, individual fairness-based approach which addresses popularity bias in graph neural network (GNNs) based recommender systems. In order to facilitate this domain awareness, we perform extensive dataset augmentation, taking two state of the art music recommendation datasets and augmenting them with rich multi-modal node-level features. Finally, we ground our evaluation in the cold start setting, showing the importance of inductive methodologies in the music space. / La dernière décennie a apporté avec elle une vague de technologies innovantes, modifiant la manière dont le contenu créatif est créé, consommé et catégorisé. Et, à mesure que nos interactions avec les contenus multimédias créatifs se déplacent vers les plateformes en ligne, la quantité de contenu sur ces plateformes a nécessité l’intégration d’un guidage algorithmique dans la découverte de ces espaces. De cette façon, les algorithmes de recommandation qui guident les interactions des utilisateurs avec diverses formes d’art ont été jetés dans le rôle de gardiens et ont commencé à jouer un rôle de plus en plus influent dans l’élaboration de la création de contenu artistique. Le travail présenté dans les chapitres suivants fusionne trois grands domaines de recherche : l’apprentissage de la représentation graphique, la recherche d’informations musicales et l’équité appliquée à la tâche de recommandation musicale. Alors que l’influence des systèmes de recommandation continue de s’étendre et de s’intensifier, il est crucial de prendre en compte les effets en aval que les choix de conception peuvent avoir sur l’écosystème plus large de la création artistique. Ces dernières années, l’intégration des réseaux sociaux dans la tâche de recommandation musicale a donné naissance aux réseaux neuronaux de graphes (GNN), une nouvelle architecture capable de faire des prédictions sur les structures de graphes. Parallèlement aux gains miraculeux que les GNN sont capables de réaliser, bon nombre de ces systèmes peuvent également être la proie de biais de popularité, les forçant à privilégier le contenu grand public par rapport à des éléments potentiellement plus pertinents, mais de niche ou nouveaux. S’il n’est pas maîtrisé, ce cycle négatif peut perpétuer les disparités de représentation entre la musique d’artistes, de genres ou de populations minoritaires. Et, ce faisant, les disparités dans la visibilité des éléments peuvent entraîner des problèmes à la fois du point de vue des performances et de la société. L’objectif de la thèse est l’atténuation du biais de popularité. Premièrement, le travail formalise les liens entre l’équité individuelle et la présence d’un biais de popularité parmi les contenus créatifs. Ensuite, nous étendons un cadre d’équité individuelle, en l’appliquant au domaine de la recommandation musicale. Le coeur de cette thèse s’articule autour de la proposition d’une approche basée sur l’équité individuelle et sensible au domaine qui traite le biais de popularité dans les systèmes de recommandation basés sur les réseaux de 5 neurones graphiques (GNN). L’un des éléments clés de ce travail est notre capacité à ancrer notre notion d’équité dans le domaine musical. Afin de faciliter cette prise de conscience du domaine, nous effectuons une augmentation étendue des ensembles de données, en prenant deux ensembles de données de recommandation musicale à la pointe de la technologie et en les augmentant avec de riches fonctionnalités multimodales au niveau des noeuds. Enfin, nous fondons notre évaluation sur le démarrage à froid, montrant l’importance des méthodologies inductives dans l’espace musical.

The rapid growth of the Internet and the advancements of the Web technologies have made it possible for users to have access to large amounts of on-line music data, including music acoustic signals, lyrics, style/mood labels, and user-assigned tags. The progress has made music listening more fun, but has raised an issue of how to organize this data, and more generally, how computer programs can assist users in their music experience. An important subject in computer-aided music listening is music retrieval, i.e., the issue of efficiently helping users in locating the music they are looking for. Traditionally, songs were organized in a hierarchical structure such as genre->artist->album->track, to facilitate the users’ navigation. However, the intentions of the users are often hard to be captured in such a simply organized structure. The users may want to listen to music of a particular mood, style or topic; and/or any songs similar to some given music samples. This motivated us to work on user-centric music retrieval system to improve users’ satisfaction with the system. The traditional music information retrieval research was mainly concerned with classification, clustering, identification, and similarity search of acoustic data of music by way of feature extraction algorithms and machine learning techniques. More recently the music information retrieval research has focused on utilizing other types of data, such as lyrics, user access patterns, and user-defined tags, and on targeting non-genre categories for classification, such as mood labels and styles. This dissertation focused on investigating and developing effective data mining techniques for (1) organizing and annotating music data with styles, moods and user-assigned tags; (2) performing effective analysis of music data with features from diverse information sources; and (3) recommending music songs to the users utilizing both content features and user access patterns.

Perceptual features are qualitative features used to describe music properties in relation to human perception instead of typical musical theory concepts such as pitches and chords. This report describes a music discovery platform which uses three different methods of music playlist generation to investigate if and how perceptual features work when used for music discovery. One method abstracts away the complexity of perceptual features and the other two lets users use them directly. Two user testing sessions were performed to evaluate the browser and compare the different methods. Test participants found the playlist generation to work well in general, and especially found the method which uses emotions as an interface to be intuitive, enjoyable and something they would use to find new music. The other two methods which let users directly interact with perceptual features were less popular, especially among users without musical education. Overall, using perceptual features for music discovery was successful, although methods should be chosen with the intended audience in mind. / Perceptuella särdrag är kvalitativt framtagna särdrag som beskriver musik med fokus på mänsklig perception snarare än musikteoribegrepp som tonhöjd och ackord. Den här rapporten beskriver en musikhemsida som använder tre olika metoder för att generera spellistor med avsikt att undersöka om och hur perceptuella särdrag fungerar för att hitta ny musik. En metod abstraherar bort perceptuella särdragens komplexitet och de andra två metoderna låter testare använda dem utan abstraktion. Två användbarhetstest utfördes för att utvärdera musikhemsidan och jämföra de olika metoderna. Testanvändare tyckte överlag att genereringen av spellistor fungerade bra och att speciellt metoden som använde känslor som gränssnitt var intuitiv, rolig att använda och en metod de skulle använda för att hitta ny musik. De andra två metoderna som tillät användare att direkt använda perceptuella särdrag var mindre populära, speciellt bland användare utan musikutbildning. Överlag var användandet av perceptuella särdrag för att hitta musik en framgång, dock bör metoderna väljas utifrån användarnas kunskap.