This is a pilot study examining the comparative effectiveness of self-administered therapeutic playlists in the treatment of anxiety symptoms. Interventions examined during this study include the musical contour regulation playlist (MCR-P) and a one-directional mood vectoring playlist (MV-P). Measures included the Spielberger State Trait Anxiety Inventory (STAI), and a Likert-type scale for participants to rate their pre- to post-listening levels of anxiety. At the conclusion of the study, participants took part in an interview which were analyzed for data that could help inform for whom the MCR-P intervention would be best suited. Both interventions discussed in this study are grounded in existing research in the fields of music therapy, psychotherapy, and neuroscience, and all playlists are personalized to take into account the musical preferences of each participant. Findings indicated that there was a significant relationship between use of the MCR-P and a reduction in symptoms of state and trait anxiety scores in participants with pretest trait anxiety scores at or above the 85th percentile (state p = 0.023; trait p = 0.037), and state anxiety scores in all participants (state p = 0.026). Analysis of all participant scores also indicated that there was a significant relationship between use of the MCR-P and a reduction in pre- to post-listening anxiety (p = 0.029) with greater effectiveness in participants with pretest trait anxiety scores at or above the 85th percentile (p = 0.01). Findings must be interpreted with caution due to the small sample size, but they indicate that this may be an effective tool to assist patients in the management of anxiety symptoms.

Submitted by Kilvya Braga (kilvyabraga@hotmail.com) on 2018-05-15T13:27:13Z No. of bitstreams: 1 VÍTOR DE SOUZA AMARAL - DISSERTAÇÃO (PPGCC) 2016.pdf: 474505 bytes, checksum: a4f88444155adc7bb62c7035f928a20b (MD5) / Made available in DSpace on 2018-05-15T13:27:13Z (GMT). No. of bitstreams: 1 VÍTOR DE SOUZA AMARAL - DISSERTAÇÃO (PPGCC) 2016.pdf: 474505 bytes, checksum: a4f88444155adc7bb62c7035f928a20b (MD5) Previous issue date: 2016 / Capes / Uma playlist pode ser definida como qualquer sequência de músicas para ser executada tipicamente de forma ordenada sem que seja necessário ao usuário ter que selecionar individualmente as músicas enquanto elas vão sendo tocadas. Muitos softwares são capazes de montar playlists de forma automática baseando-se nos mais diversos modelos, sendo este um aspecto muito importante de aplicações como Last.fm, Deezer, Spotify, etc. Muitos pesquisadores na área de Recuperação de Informação Musical (MIR) têm dedicado esforços no desenvolvimento de modelos geradores cada vez melhores,entretanto as atuai sformas de validação são reconhecidamente ineficientes e métodos considerados padrão possuem graves limitações. Neste trabalho, investigamos as percepções de DJs (pessoas que criam playlists para discotecagem em festas) sobre playlists automaticamente geradas por dois modelos diferentes, focando nas características relacionadas à criação de playlists identificadas nas amostras apresentadas, nas expectativas em relação a playlists geradas automaticamente em contraponto às criadas por outras pessoas e se e de qual forma percebe-se diferenças entre os itens criados pelos diferentes geradores. Foi realizada uma pesquisa qualitativa onde DJs de diversas localidades participaram de in-depth interviews. Foram colhidos relatos de experiências relacionadas à criação de playlists para discotecagem ou outras ocasiões, do uso desoftwares paraedição, execução e geração de playlists e dos hábitos de consumo de playlists. Entrevistados foram também apresentados a amostras de playlists de dois geradores e suas impressões foram colhidas. Concluímos que, ainda que de forma não explícita, os entrevistados conseguiram caracterizar e dar contexto aos diferentes geradores. Além disso playlists são percebidas como mais humanas quando eles conseguem identificar uma única motivação forte, uma única temática que norteia o agrupamento e encadeamento de músicas e que playlists menos homogêneas não são necessariamente percebidas como playlists ruins e são muitas vezes entendidas como surpresas positivas.

This is a mixed-methods pre-experimental clinical effectiveness trial that examines the effectiveness of a self-administered one-directional mood vectoring playlist in the management of symptoms of anxiety. This study used the Spielberger State Trait Anxiety Inventory, as well as a self-report Likert-type scale where participants rated their anxiety symptom severity, to explore the impact of the playlist intervention. Qualitative interviews sought to identify themes common among participants who were daily high responders and those who were daily low responders to the intervention in order to determine for whom this intervention would be most or least effective.Management of anxiety symptoms is particularly important at the moment, as mental health concerns and levels of anxiety are rising amid coronavirus lockdowns and stay at home orders. This intervention has a strong basis in music therapy research, neurological research, and psychotherapy treatments that are effectively used in the management of anxiety symptoms. Findings indicated a significant relationship between the intervention and a reduction in both state and trait anxiety scores over the full two-week course of treatment (p < 0.001). There was also a significant relationship found from pre-listening to post-listening on a daily basis (p = 0.003). This study has a small sample size and results should be interpreted with caution, but this is an indication that further studies on this intervention are warranted.

abstract: Playlists have become a significant part of the music listening experience today because of the digital cloud-based services such as Spotify, Pandora, Apple Music. Owing to the meteoric rise in usage of playlists, recommending playlists is crucial to music services today. Although there has been a lot of work done in playlist prediction, the area of playlist representation hasn't received that level of attention. Over the last few years, sequence-to-sequence models, especially in the field of natural language processing have shown the effectiveness of learned embeddings in capturing the semantic characteristics of sequences. Similar concepts can be applied to music to learn fixed length representations for playlists and the learned representations can then be used for downstream tasks such as playlist comparison and recommendation. In this thesis, the problem of learning a fixed-length representation is formulated in an unsupervised manner, using Neural Machine Translation (NMT), where playlists are interpreted as sentences and songs as words. This approach is compared with other encoding architectures and evaluated using the suite of tasks commonly used for evaluating sentence embeddings, along with a few additional tasks pertaining to music. The aim of the evaluation is to study the traits captured by the playlist embeddings such that these can be leveraged for music recommendation purposes. This work lays down the foundation for analyzing music playlists and learning the patterns that exist in the playlists in an end-to-end manner. This thesis finally concludes with a discussion on the future direction for this research and its potential impact in the domain of Music Information Retrieval. / Dissertation/Thesis / Masters Thesis Computer Science 2019

This paper examines how streaming services, with a particular focus on Spotify, have influenced music consumption through the implementation of algorithmically and humanly curated playlists and recommendation features. By placing the role of streaming services in a historical context, this paper explores streaming services as an extension of previous gatekeeping functions in the music industry. The paper examines how curated playlists and recommendations affect music consumption and the individual listener’s ability to discover new music. The result suggest that streaming services’ use of algorithmically and humanly curated playlists and recommendation functions constitute gatekeeping mechanisms. Due to the monopoly status of streaming services in society, this has an impact on what music is listened to and disseminated in society. Streaming services have also contributed to an increasingly more personalised music curation that differs from the governing mechanisms that previously controlled popular music. This partly contradicts the stated ambitions of streaming services to provide listeners with a means of discovering new music. The controlling functions of streaming services have in turn affected music creators who distribute their music on the platform. In what follows, it is explained how music creators have become increasingly aware of algorithmic features, leading to an adaptation of both the musical content and the music packaging to benefit from algorithmic advantages.

Sättet människor konsumerar musik har förändrats genom historien och i samband med digitaliseringen har nya möjligheter att lyssna på musik uppstått. I samband med denna övergång har även fler algoritmbaserade tillvägagångssätt för musiklyssnande uppkommit. Syftet med studien är att undersöka unga vuxnas upplevelser av den algoritmbaserade Radiofunktionen på musikstreamingtjänsten Spotify. Studien har även undersökt huruvida de algoritmbaserade förslagen eventuellt påverkar användarnas upplevelser och musikbeteenden.Undersökningen är baserad på sju respondenters upplevelser inom åldersspannet 20-30 år, i denna studie definierat som unga vuxna. Studien har genomförts via kvalitativa metoder däribland en inledande dagboksstudie, med syfte att förbereda respondenternas reflektiva tänkande vilket följdes upp med semistrukturerade intervjuer. Därefter transkriberades intervjuerna för att senare kodas och en tematisk analys genomfördes. Resultatet av studien påvisar att det finns en variation i användandet av radiofunktionen samt att majoriteten av respondenterna uttryckt en positiv upplevelse av Radio på Spotify. Studien bidrar med nya insikter kring algoritmbaserade upplevelser hos användare i relation till musikstreaming och framförallt funktionen radio, samt hur användandet kan skilja sig beroende på situation och anledning till användande. / The streaming of music has during the last two decades become a new standard for how people acquire and listen to music. In correlation with this shift, other possibilities for listening to music have been on the rise. The purpose of this study is to investigate the experience for young adults of algorithm-based playlist ”Radio” on the streaming service platform Spotify. The investigation will determine whether or not these algorithm-based suggestions potentially affect the users' experience of listening to music and overall music behavior.The study is based on the experience of seven respondents of ages ranging between 20-30 years old - through this study referred to as "young adults." The qualitative methods this research has followed consists of a simple initial diary study, in order to prepare the respondents reflective thinking before the following semi-structured interviews. The interviews were then transcribed and followed by coding as well as a thematical analysis. The results of the study show that there is a variation in the use of the ”Radio” phenomenon on Spotify and that the vast majority of the respondents participating in the investigation expressed an overall positive experience. Furthermore, this study indicates that the respondents utilize the feature on different occasions and for different purposes.