Tese de mestrado integrado. Engenharia Informática e Computação. Universidade do Porto. Faculdade de Engenharia. 2011

The goal with this assignment has been to study the product Spotalike and develop a new version to make the product more attractive. The studying of the product was done with the help of user data, such as how Spotalike is being used, what target audience it has, why it's being used, etc. The new version of Spotalike was planned by making design sketches and prototypes which were created as a first step in order to get a better picture of what the result would be. The new version is not available to the public, but it is fully functional and works locally. The solution that was concluded was to develop a music player which is built on the founding principles of the old Spotalike. The music player is developed with React and is powered by Spotify. Besides the old functions there are also new functions that has been implemented, and the interface has been redesigned. There is currently no new user data available to determine the result of the development, since the new version of Spotalike hasn't been made public yet. / Målet med detta projektarbete har varit att granska produkten Spotalike och utveckla en ny version som gör produkten mer eftertraktad. Problemgranskning har gjorts med analysering av användardata – hur Spotalike används, av vem, varför den används, osv. Den nya versionen av Spotalike planerades med hjälp av designskisser och prototyper som togs fram som första steg för att få en bättre bild av slutresultatet. Den nya versionen är inte tillgänglig publikt, men är fullt funktionell lokalt. Lösningen som togs fram var att skapa en musikspelare som bygger på de grundprinciper gamla Spotalike har. Musikspelaren är bygd med React och använder Spotify i bakgrunden som motor. Utöver de redan befintliga funktionerna så har även nya funktioner tagits fram och gränssnittet har redesignats. Någon ny användarstatistik för att se om lösningen har gynnat bra resultat i form av användarupplevelse finns inte tillgänglig då tjänsten ännu inte har hunnit bli tillgängligt publikt.

In the field of Music Data Mining, Mood and Topic information has been considered as a high level metadata. The extraction of mood and topic information is difficult but is regarded as very valuable. The immense growth of Web 2.0 resulted in Social Tags being a direct interaction with users (humans) and their feedback through tags can help in classification and retrieval of music. One of the major shortcomings of the approaches that have been employed so far is the improper filtering of social tags. This thesis delves into the topic of information extraction from songs’ tags and lyrics. The main focus is on removing all erroneous and unwanted tags with help of other features. The hierarchical clustering method is applied to create clusters of tags. The clusters are based on semantic information any given pair of tags share. The lyrics features are utilized by employing CLOPE clustering method to form lyrics clusters, and Naïve Bayes method to compute probability values that aid in classification process. The outputs from classification are finally used to estimate the accuracy of a tag belonging to the song. The results obtained from the experiments all point towards the success of the method proposed and can be utilized by other research projects in the similar field.

This report chronicles the process of investigating social theories and their relation to music experience in order to create a specific online community. The purpose of this community focuses on an historical perspective of music while facilitating the formation of varied knowledge-networks and relationship levels. Social theories are correlated with web applications and tools to support design choices that will appeal to users by providing opportunities for specific social functions. This research allows for an organized, detailed, and theoretical approach to the design of the online music community, Vinylsqueegee.com. / text

Avui en dia, la música està esbiaixada cap al consum d'alguns artistes molt populars. Per exemple, el 2007 només l'1% de totes les cançons en format digital va representar el 80% de les vendes. De la mateixa manera, només 1.000 àlbums varen representar el 50% de totes les vendes, i el 80% de tots els àlbums venuts es varen comprar menys de 100 vegades. Es clar que hi ha una necessitat per tal d'ajudar a les persones a filtrar, descobrir, personalitzar i recomanar música, a partir de l'enorme quantitat de contingut musical disponible. Els algorismes de recomanació de música actuals intenten predir amb precisió el que els usuaris demanen escoltar. Tanmateix, molt sovint aquests algoritmes tendeixen a recomanar artistes famosos, o coneguts d'avantmà per l'usuari. Això fa que disminueixi l'eficàcia i utilitat de les recomanacions, ja que aquests algorismes es centren bàsicament en millorar la precisió de les recomanacions. És a dir, tracten de fer prediccions exactes sobre el que un usuari pugui escoltar o comprar, independentment de quant útils siguin les recomanacions generades. En aquesta tesi destaquem la importància que l'usuari valori les recomanacions rebudes. Per aquesta raó modelem la corba de popularitat dels artistes, per tal de poder recomanar música interessant i desconeguda per l'usuari. Les principals contribucions d'aquesta tesi són: (i) un nou enfocament basat en l'anàlisi de xarxes complexes i la popularitat dels productes, aplicada als sistemes de recomanació, (ii) una avaluació centrada en l'usuari, que mesura la importància i la desconeixença de les recomanacions, i (iii) dos prototips que implementen la idees derivades de la tasca teòrica. Els resultats obtinguts tenen una clara implicació per aquells sistemes de recomanació que ajuden a l'usuari a explorar i descobrir continguts que els pugui agradar. / Actualmente, el consumo de música está sesgada hacia algunos artistas muy populares. Por ejemplo, en el año 2007 sólo el 1% de todas las canciones en formato digital representaron el 80% de las ventas. De igual modo, únicamente 1.000 álbumes representaron el 50% de todas las ventas, y el 80% de todos los álbumes vendidos se compraron menos de 100 veces. Existe, pues, una necesidad de ayudar a los usuarios a filtrar, descubrir, personalizar y recomendar música a partir de la enorme cantidad de contenido musical existente. Los algoritmos de recomendación musical existentes intentan predecir con precisión lo que la gente quiere escuchar. Sin embargo, muy a menudo estos algoritmos tienden a recomendar o bien artistas famosos, o bien artistas ya conocidos de antemano por el usuario.Esto disminuye la eficacia y la utilidad de las recomendaciones, ya que estos algoritmos se centran en mejorar la precisión de las recomendaciones. Con lo cuál, tratan de predecir lo que un usuario pudiera escuchar o comprar, independientemente de lo útiles que sean las recomendaciones generadas. En este sentido, la tesis destaca la importancia de que el usuario valore las recomendaciones propuestas. Para ello, modelamos la curva de popularidad de los artistas con el fin de recomendar música interesante y, a la vez, desconocida para el usuario.Las principales contribuciones de esta tesis son: (i) un nuevo enfoque basado en el análisis de redes complejas y la popularidad de los productos, aplicada a los sistemas de recomendación,(ii) una evaluación centrada en el usuario que mide la calidad y la novedad de las recomendaciones, y (iii) dos prototipos que implementan las ideas derivadas de la labor teórica. Los resultados obtenidos tienen importantes implicaciones para los sistemas de recomendación que ayudan al usuario a explorar y descubrir contenidos que le puedan gustar. / Music consumption is biased towards a few popular artists. For instance, in 2007 only 1% of all digital tracks accounted for 80% of all sales. Similarly, 1,000 albums accounted for 50% of all album sales, and 80% of all albums sold were purchased less than 100 times. There is a need to assist people to filter, discover, personalise and recommend from the huge amount of music content available along the Long Tail.Current music recommendation algorithms try to accurately predict what people demand to listen to. However, quite often these algorithms tend to recommend popular -or well-known to the user- music, decreasing the effectiveness of the recommendations. These approaches focus on improving the accuracy of the recommendations. That is, try to make accurate predictions about what a user could listen to, or buy next, independently of how useful to the user could be the provided recommendations. In this Thesis we stress the importance of the user's perceived quality of the recommendations. We model the Long Tail curve of artist popularity to predict -potentially- interesting and unknown music, hidden in the tail of the popularity curve. Effective recommendation systems should promote novel and relevant material (non-obvious recommendations), taken primarily from the tail of a popularity distribution. The main contributions of this Thesis are: (i) a novel network-based approach for recommender systems, based on the analysis of the item (or user) similarity graph, and the popularity of the items, (ii) a user-centric evaluation that measures the user's relevance and novelty of the recommendations, and (iii) two prototype systems that implement the ideas derived from the theoretical work. Our findings have significant implications for recommender systems that assist users to explore the Long Tail, digging for content they might like.

Recommendation systems make it easier for an individual to navigate through large datasets by recommending information relevant to the user. Companies such as Facebook, LinkedIn, Twitter, Netflix, Amazon, Pandora, and others utilize these types of systems in order to increase revenue by providing personalized recommendations. Recommendation systems generally use one of the two techniques: collaborative filtering (i.e., collective intelligence) and content-based filtering. Systems using collaborative filtering recommend items based on a community of users, their preferences, and their browsing or shopping behavior. Examples include Netflix, Amazon shopping, and Last.fm. This approach has been proven effective due to increased popularity, and its accuracy improves as its pool of users expands. However, the weakness with this approach is the Cold Start problem. It is difficult to recommend items that are either brand new or have no user activity. Systems that use content-based filtering recommend items based on extracted information from the actual content. A popular example of this approach is Pandora Internet Radio. This approach overcomes the Cold Start problem. However, the main issue with this approach is its heavy demand on computational power. Also, the semantic meaning of an item may not be taken into account when producing recommendations. In this thesis, a hybrid approach is proposed by utilizing the strengths of both collaborative and content-based filtering techniques. As proof-of-concept, a hybrid music recommendation system was developed and evaluated by users. The results show that this system effectively tackles the Cold Start problem and provides more variation on what is recommended.

One of the many challenges of machine learning are systems for automatic tagging of music, the complexity of this issue in particular. These systems can be practically used in the content analysis of music or the sorting of music libraries. This thesis deals with the design, training, testing, and evaluation of artificial neural network architectures for automatic tagging of music. In the beginning, attention is paid to the setting of the theoretical foundation of this field. In the practical part of this thesis, 8 architectures of neural networks are designed (4 fully convolutional and 4 convolutional recurrent). These architectures are then trained using the MagnaTagATune Dataset and mel spectrogram. After training, these architectures are tested and evaluated. The best results are achieved by the four-layer convolutional recurrent neural network (CRNN4) with the ROC-AUC = 0.9046 ± 0.0016. As the next step of the practical part of this thesis, a completely new Last.fm Dataset 2020 is created. This dataset uses Last.fm and Spotify API for data acquisition and contains 100 tags and 122877 tracks. The most successful architectures are then trained, tested, and evaluated on this new dataset. The best results on this dataset are achieved by the six-layer fully convolutional neural network (FCNN6) with the ROC-AUC = 0.8590 ± 0.0011. Finally, a simple application is introduced as a concluding point of this thesis. This application is designed for testing individual neural network architectures on a user-inserted audio file. Overall results of this thesis are similar to other papers on the same topic, but this thesis brings several new findings and innovations. In terms of innovations, a significant reduction in the complexity of individual neural network architectures is achieved while maintaining similar results.

Thesis discusses data mining the social media. It gives an introduction about the topic of data mining and possible mining methods. Thesis also explores social media and social networks, what are they able to offer and what problems do they bring. Three different APIs of three social networking sites are examined with their opportunities they provide for data mining. Techniques of text mining and document classification are explored. An implementation of a web application that mines data from social site Twitter using the algorithm SVM is being described. Implemented application is classifying tweets based on their text where classes represent tweets' continents of origin. Several experiments executed both in RapidMiner software and in implemented web application are then proposed and their results examined.