Online Music Platforms Research Articles

Thai Rap Songs Through the World Englishes Approach: Code-Switching and Nativization

Abstract This study examines the English elements and nativized English features present in recent Thai rap songs. The source data comes from a Thai rap playlist called Thai Rapper on the online music platform Spotify. All English units found in the lyrics were manually counted and classified. The results diverged from most studies of Thai-English code-switching in Thai media in that, among the English elements considered, sentences were employed most frequently. Among nativized English features, semantic shift was most frequently employed. I argue that the local and global English identity flows (Pennycook 2009) index a shift in the Thai rap community toward assimilation of their Thai hip-hop identity into global street culture, a phenomenon becoming more prevalent among today’s Thai youth.

浅谈线上音乐平台中的韩文歌词汉译

In recent years, cultural exchanges between China and South Korea are no longer as active as before due to China's growing awareness of protecting local culture. However, “Korean wave” culture, especially Korean pop songs such as K-POP, remains hugely popular in China. On China's major online music platforms, Korean songs account for a large proportion of listeners. Music is a borderless language, and lyrics are an important means to promote music. Therefore, it is of great significance to study the Chinese translation of Korean lyrics. Although there are some similarities between Chinese and Korean languages, there are still great differences in cultural background, pronunciation and grammar. This paper aims to discuss the principles of translating Korean lyrics from Chinese by analyzing the current situation, influencing factors and concrete examples.

Quantifying the impact of homophily and influencer networks on song popularity prediction.

Forecasting the popularity of new songs has become a standard practice in the music industry and provides a comparative advantage for those that do it well. Considerable efforts were put into machine learning prediction models for that purpose. It is known that in these models, relevant predictive parameters include intrinsic lyrical and acoustic characteristics, extrinsic factors (e.g., publisher influence and support), and the previous popularity of the artists. Much less attention was given to the social components of the spreading of song popularity. Recently, evidence for musical homophily-the tendency that people who are socially linked also share musical tastes-was reported. Here we determine how musical homophily can be used to predict song popularity. The study is based on an extensive dataset from the last.fm online music platform from which we can extract social links between listeners and their listening patterns. To quantify the importance of networks in the spreading of songs that eventually determines their popularity, we use musical homophily to design a predictive influence parameter and show that its inclusion in state-of-the-art machine learning models enhances predictions of song popularity. The influence parameter improves the prediction precision (TP/(TP FP)) by about 50% from 0.14 to 0.21, indicating that the social component in the spreading of music plays at least as significant a role as the artist's popularity or the impact of the genre.

Brand on the run: place brands as judgement devices and sources of local advantage in the music industry

ABSTRACT Products from certain areas are assumed to share qualities by virtue of where they are made. This article considers the economic significance of such place brands in the wider market for symbolic goods. It forwards a theory of these as judgement devices, whereby place reputation serves to lower search costs in symbolic goods markets with excess supply. This theory is investigated through a study of an online music platform where a weak form of place branding is available to producers. Results suggest that branding is associated with musical success at the individual level and that place brands may act as strategic resources for producers from creative clusters. Branding effects do not necessarily depend on the content of the place brand signal (i.e., country acts branded from Nashville are not especially privileged) and may be based in simpler heuristic mechanisms where a listed origin is a stamp of quality or an aid in recognition.

Effect of collaborative-filtering-based recommendation algorithms on opinion polarization.

A central role in shaping the experience of users online is played by recommendation algorithms. On the one hand they help retrieving content that best suits users taste, but on the other hand they may give rise to the so-called "filter bubble" effect, favoring the rise of polarization. In the present paper we study how a user-user collaborative-filtering algorithm affects the behavior of a group of agents repeatedly exposed to it. By means of analytical and numerical techniques we show how the system stationary state depends on the strength of the similarity and popularity biases, quantifying respectively the weight given to the most similar users and to the best rated items. In particular, we derive a phase diagram of the model, where we observe three distinct phases: disorder, consensus, and polarization. In the last users spontaneously split into different groups, each focused on a single item. We identify, at the boundary between the disorder and polarization phases, a region where recommendations are nontrivially personalized without leading to filter bubbles. Finally, we show that our model well reproduces the behavior of users on the online music platform last.fm. This analysis paves the way to a systematic analysis of recommendation algorithms by means of statistical physics methods and opens the possibility of devising less polarizing recommendation algorithms.

MKGCN: Multi-Modal Knowledge Graph Convolutional Network for Music Recommender Systems

With the emergence of online music platforms, music recommender systems are becoming increasingly crucial in music information retrieval. Knowledge graphs (KGs) are a rich source of semantic information for entities and relations, allowing for improved modeling and analysis of entity relations to enhance recommendations. Existing research has primarily focused on the modeling and analysis of structural triples, while largely ignoring the representation and information processing capabilities of multi-modal data such as music videos and lyrics, which has hindered the improvement and user experience of music recommender systems. To address these issues, we propose a Multi-modal Knowledge Graph Convolutional Network (MKGCN) to enhance music recommendation by leveraging the multi-modal knowledge of music items and their high-order structural and semantic information. Specifically, there are three aggregators in MKGCN: the multi-modal aggregator aggregates the text, image, audio, and sentiment features of each music item in a multi-modal knowledge graph (MMKG); the user aggregator and item aggregator use graph convolutional networks to aggregate multi-hop neighboring nodes on MMKGs to model high-order representations of user preferences and music items, respectively. Finally, we utilize the aggregated embedding representations for recommendation. In training MKGCN, we adopt the ratio negative sampling strategy to generate high-quality negative samples. We construct four different-sized music MMKGs using the public dataset Last-FM and conduct extensive experiments on them. The experimental results demonstrate that MKGCN achieves significant improvements and outperforms several state-of-the-art baselines.

Understanding Disclosure and Support for Youth Mental Health in Social Music Communities

Online music platforms that include social networking features sometimes become supportive social communities where young people can disclose their emotional distress and receive support. However, few studies have examined young people's disclosure in social music communities or the support they provide or receive. In this study, which focuses on a large online music platform as a research site, we used mixed methods to analyze young users' comments (N = 163) and the associated replies (N = 2,732) related to their psychological distress (e.g., depression, anxiety, stress, and loneliness). We found that the main types of comments involved experience sharing, and these comments often invoked peer support in the form of encouragement, caring, or self-disclosure. We also conducted an interview study with 13 young users of our research site to understand their perceptions of and motives for engaging in disclosure and support. The interviewees stated that music-induced and comment-induced emotional resonance was the main reason for their disclosure and support. Finally, we discussed the implications of our findings for designing a supportive social music community to benefit youth mental health.

An Exploration of Musicality and Literary Qualities in Translated Lyrics on Online Music Platforms: A Case Study of the Translated Lyrics of "Young and Beautiful"

An Exploration of Musicality and Literary Qualities in Translated Lyrics on Online Music Platforms: A Case Study of the Translated Lyrics of "Young and Beautiful"

Bowing to five pecks of rice: how online monetization programs shape artistic novelty

Studies on creative industries have explored how producers’ properties shape their decisions about pursuing artistic novelty in their products. But how do external shocks, such as new remuneration opportunities, affect artistic novelty? In this paper, I investigate how the launch of monetization programs on online music platforms shapes musical novelty. I examined an original dataset of 12,394 songs on a Chinese music platform that launched its monetization program in 2013. Using computational tools developed in Music Information Retrieval (MIR) to compare song similarity based on their acoustic properties, I employed a novel approach to measure and model the impact of the monetization program on the musical novelty of the songs. The results suggest that while many more songs were uploaded to the platform after the program launch, these new songs are generally less novel than those before. Moreover, the decrease is particularly significant among songs released by indie companies, Pop musicians, or veteran producers. These findings demonstrate that monetization programs will restrain artistic novelty, especially among producers who are more autonomously skillful, unspecialized, or experienced.

Indonesian consumers’ emotional and psychological factors in the nexus of fear of missing out (FOMO)

This research examines the effect of emotional and psychological factors and their implications for fear of missing out (FOMO) on the online music platform. The object of this study is Spotify. The population in this study was respondents in Indonesia. The purposive sampling technique was used, where the sample criteria used consisted of Spotify users who have seen the Spotify Wrapped campaign at least once on social media. The SEM-AMOS is use to analyzed questionnaire data of 150 respondents. It was found that the varying psychological needs relatedness and unfulfilled psychological needs for self will positively affect FOMO. The result also shows that anticipated elation and anticipated envy from others have a positive effect on FOMO. It was also found that comforting rationalizations negatively influence FOMO and FOMO positively and significantly affect purchase intention. This study finds that comforting rationalization explains concerns about alternatives and offers behavioural mitigation that assist individuals to make their choices and reduce their FOMO.

Personalized Music Recommendation Algorithm Based on Spark Platform.

Aiming at the shortcomings of traditional recommendation algorithms in dealing with large-scale music data, such as low accuracy and poor real-time performance, a personalized recommendation algorithm based on the Spark platform is proposed. The algorithm is based on the Spark platform. The K-means clustering model between users and music is constructed using an AFSA (artificial fish swarm algorithm) to optimize the initial centroids of K-means to improve the clustering effect. Based on the scoring relationship between users and users and users and music attributes, the collaborative filtering algorithm is applied to calculate the correlation between users to achieve accurate recommendations. Finally, the performance of the designed recommendation model is validated by deploying the recommendation model on the Spark platform using the Yahoo Music dataset and online music platform dataset. The experimental results show that the use of improved AFSA can complete the optimization of K-means clustering centroids with good clustering results; combined with the distributed fast computing capability of Spark platform with multiple nodes, the recommendation accuracy has better performance than traditional recommendation algorithms; especially when dealing with large-scale music data, the recommendation accuracy and real-time performance are higher, which meet the current demand of personalized music recommendation.

User's Virtual Social Needs and Playlist Selection Behavior: Design Implications for Online Music Platform

User's Virtual Social Needs and Playlist Selection Behavior: Design Implications for Online Music Platform

Splice and the platformization of hip hop production: Navigating the online music platform for royalty-free samples

As a large marketplace of royalty-free samples, the music platform Splice has worked to centralize and open up the process of hip hop production to over 4 million users, varying from beginning bedroom producers to established producers like Turbo (who has worked on tracks for artists including Young Thug, Gunna and Lil Baby). Founded by sound engineer Matt Aimonetti and GroupMe co-founder Steve Martocci in 2013, Splice experienced extreme growth during the COVID-19 pandemic as more aspiring producers took up beat-making from home. Hip hop producers have long used the internet to exchange and sell samples for beat production through direct messaging, sample blogs and sample marketplaces. While these digital exchanges have enabled quicker collaboration and accessibility for producers, they have also set the groundwork for companies like Splice to have an unprecedented influence in musical interactions and activity. Online platforms geared towards hip hop production and beat-making are becoming increasingly critical to the music industry, offering an important opportunity to examine digital creative economies and the platformization of cultural production. Splice incorporates features such as curation and algorithmic recommendation of samples to aid creators in their production process. Through interviews with producers who use Splice and a critical analysis of the platform’s user experience, this article demonstrates that producers can feel the need to strike a balance when engaging with the platform, finding ways to use automated tools that make their work more efficient while simultaneously striving to maintain high standards of individual creativity and technical skills. This suggests that it is necessary to have a nuanced understanding of Splice’s impact on music production and how it differs from streaming platforms because of its particular logics and functionalities geared towards music creators as a primary userbase.

Preservation and promotion of China\u2019s musical cultural heritage on the internet

The study investigates different ways of preservation and popularization of Chinese traditional music using the Internet. The study collected data by analyzing various methods of presenting traditional Chinese music in online platforms YouTube, TikTok, and Likee. Common groups for YouTube are instrumental music (46.8%) and vocal music (23.9%), whereas, for TikTok and Likee, it is dancing performances (68.6% and 71.8%) and instrumental music (21.6% and 22.3%). The samples containing information about the content on the online platforms YouTube and TikTok are continuously growing in August, October, and December, while the Likee platform has seen a decline in all indicators. For the online platform YouTube, the largest increases were seen for vocal music theory and instrumental music for August, October, and December, while for the TikTok platform, the corresponding indicators were for Chinese music theory and educational dance performances in August and October. For online platform Likee for the aforementioned months, vocal music has seen the biggest decline over time. The obtained data can be useful for a better understanding of the audience’s requests, which makes it possible to popularize music content more productively. The authors see such study as necessary for the implementation of new business projects in the operation of online music platforms, changes in approaches to licensing over the Internet, and reform of the music industry. The development of the Internet popularizes Chinese musical culture on a global scale, opens up new opportunities for the Chinese population (professionals and amateurs, adults and children) to study the musical heritage of other countries, promotes musical diversity, and can bring substantial financial benefits not only to individuals or companies, but also to the state as a whole.

Disperse and Preserve the Perverse: How Hip-Hop Censorship Changed Popular Music Production in China

How do states censor an artistic genre that challenges the social norms? The answers to this question in the existing literature are mostly based on investigations of particular artists or artworks of the genre, while the impact on the entire genre field remains unchecked. This paper explores how censorship of an artistic genre changes artistic forms of that genre while also triggering strategic reactions from the artists of closely related genres. Using an original dataset of 53,364 songs released on a Chinese online music platform, I study the impact of Hip-Hop censorship in China in 2018 on Hip-Hop as well as Pop, Rock, and Folk songs in terms of how they sound and what topics they write about in the lyrics. I propose a novel approach to measuring sound similarities and topic prevalence in song lyrics using computational tools including Music Information Retrieval (MIR), neural networks, and topic models. I found that Hip-Hop songs produced after the censorship sound significantly different from those before, with a bigger impact on popular songs than unpopular ones. Moreover, genres of similarly restricted production sound more like Hip-Hop after the censorship, while genres of large-scale production sound less “Hip-Hopy”. The censorship also made Hip-Hop musicians engage less with topics related to violence, smoking, or drinking but more with sexual content in a covered form. The findings thus suggest a model of dispersion in explaining the mechanism of censorship in cultural production.

Disperse and preserve the perverse: computing how hip-hop censorship changed popular music genres in China

How do political interventions reshape genre boundaries? Previous studies on genres only tangentially touch on this question as they mostly focus on the artistic, economic, or critical consequences of genre spanning. This paper fills in this gap by exploring the impact of music censorship on the censored genre and other related genres. Using an original dataset of 53,364 songs released on a Chinese online music platform, I study how Hip-Hop censorship in China in 2018 impacted Hip-Hop as well as Pop, Rock, and Folk songs in terms of how they sound and what topics are engaged in the lyrics. I propose a novel, computational approach to measure sound similarities between songs by using Music Information Retrieval (MIR) algorithms which synthesize audio signal processing and neural networks. I also measure the change of topic prevalence in song lyrics by using topic models supplemented with a dictionary approach. I found that post-censorship Hip-Hop songs sound significantly different from pre-censorship ones, with a bigger impact on the high-profile songs. Moreover, Rock, as a close genre to Hip-Hop, became more “Hip-Hoppy”, while Pop, a mixed category that reflects trending genres, became less “Hip-Hoppy”; the impact on these two genres is more salient among their low-profile songs. Folk, a genre distanced from Hip-Hop, remained generally untouched. The censorship also made Hip-Hop musicians engage less with topics related to violence and deviant behaviors but more with sexual terms, albeit in a covered form and not necessarily related to sexual conduct per se. The findings suggest a dispersion model in explaining the outcome of political interventions in genres, where stylistic conventions of the censored genre are dispersed from salient works of that genre to less influential ones as well as to adjacent genres.

Music Feature Classification Based on Recurrent Neural Networks with Channel Attention Mechanism

With the advancement of multimedia and digital technologies, music resources are rapidly increasing over the Internet, which changed listeners’ habits from hard drives to online music platforms. It has allowed the researchers to use classification technologies for efficient storage, organization, retrieval, and recommendation of music resources. The traditional music classification methods use many artificially designed acoustic features, which require knowledge in the music field. The features of different classification tasks are often not universal. This paper provides a solution to this problem by proposing a novel recurrent neural network method with a channel attention mechanism for music feature classification. The music classification method based on a convolutional neural network ignores the timing characteristics of the audio itself. Therefore, this paper combines convolution structure with the bidirectional recurrent neural network and uses the attention mechanism to assign different attention weights to the output of the recurrent neural network at different times; the weights are assigned for getting a better representation of the overall characteristics of the music. The classification accuracy of the model on the GTZAN data set has increased to 93.1%. The AUC on the multilabel labeling data set MagnaTagATune has reached 92.3%, surpassing other comparison methods. The labeling of different music labels has been analyzed. This method has good labeling ability for most of the labels of music genres. Also, it has good performance on some labels of musical instruments, singing, and emotion categories.

Rebuilding the Music Industry through Community

Devon Léger is a music publicist (HearthPR) and music writer (Folk Alley, No Depression). In this piece, he describes how online music platforms Bandcamp and Twitch have supported musicians during the pandemic and provided new ways for artists to connect with fans, build community, and monetize their music.

Social Music Curation That Works

Social interactions, such as sharing songs and listening together, are fundamental to the experience of music. Yet our understanding of these interactions and how they influence social dynamics with today's streaming platforms is lacking. To better understand successful instances of social music practice, we conducted a two-part study to investigate real-world usage of collaborative playlists (CPs). Using an exploratory survey, we queried CP users on characteristics---Who, What, When, Where, Why, and How---and practices around favorite CPs, which serve as concrete examples of successful social music curation on streaming platforms. We found these playlists to vary in group sizes, purposes, listening contexts, engagement behaviors, and content attributes. We also observed significant cross-category interactions; for one, group size led to differences in perceived roles and frequency of actions within users' favorite CPs. Subsequent interviews confirmed favorite CPs as being exemplary of success, and users further elucidated factors that engender and hinder CP success. Together, our results underscore the importance of social motivations for engaging in CPs and of building greater understanding around these experiences. To these point we derived six design implications to inform development of CP platforms and online music platforms at large.

A method of music autotagging based on audio and lyrics

With the development of the Internet and technology, online music platforms and music streaming services are flourishing. Information overload due to an abundance of digital music has become a common problem for many users. Social tags that are helpful for music recommendations have been discussed. However, label sparsity and a cold start problem, commonly observed with social tags, limit the effectiveness in supporting the recommendation system. A music autotagging system then becomes an alternative solution for supplementing a shortage of tags. Most prior studies on automatic labeling used only audio data for their analysis. However, some studies have suggested that lyrics enhance the music classification system to obtain more information and improve the overall accuracy. In addition to lyrics, audio data are also an important resource for finding music features. In summary, this paper proposes a music autotagging system that relies on both audio and lyrics to solve the above problems. Due to the development of deep learning algorithms in recent years, many scholars have effectively used neural networks to extract audio and textual features. Some of them also considered a structure of lyrics to extract features that consequentially improves the classification task. For lyric feature extraction, this study employs two types of deep learning models: convolutional neural networks (CNNs) and recurrent neural networks (RNNs). The feature extraction architecture is mainly motivated and characterized by the lyric architecture. In addition, a multitask learning method is adopted to learn correlations between tags. The experiments support that a multitask learning classifier that combines audio and lyric information has a better performance than a single-task learning classification method using only audio data than previous studies.