Follow the algorithm: An exploratory investigation of music on YouTube

Airoldi, Massimo; Beraldo, Davide; Gandini, Alessandro

doi:10.1016/j.poetic.2016.05.001

Cited by 102 publications

(91 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…An example of how this works is given by music consumption. Airoldi et al (2016) collected a sample of more than 22000 music videos, obtained from a scraping of the YouTube API, and analysed their clustering properties via social network analysis in an explicit attempt to investigate the relationships of relatedness among each video. The authors evidence how, while a majority of the videos cluster together on the basis of usual criteria, such as genre or chronological associations, a significant portion of the videos also come to be associated by what they call a 'situational' mode of consumption, which is a peculiar feature also of dedicated music platforms that aggregate music content for consumption on the basis of the mood or situation (e.g., running, dinner, etc.).…”

Section: The 'Mystery' Of the Algorithm And Digital Methods Of Researchmentioning

confidence: 99%

Researching YouTube

Arthurs

Drakopoulou

Gandini

2018

Convergence: The International Journal of Research into New Med

Self Cite

161

View full text Add to dashboard Cite

Section: The 'Mystery' Of the Algorithm And Digital Methods Of Researchmentioning

confidence: 99%

Researching YouTube

Arthurs

Drakopoulou

Gandini

2018

Convergence: The International Journal of Research into New Med

Self Cite

161

View full text Add to dashboard Cite

“…YouTube video network density. Airoldi et al [2] used the first 25 videos on the relevant list to construct the relevant network, which had an average degree of 3.2. By comparison, our Vevo video network is much denser at the same cutoff, with an average degree of 10.…”

Section: The Network Of Youtube Videosmentioning

confidence: 99%

“…This value is slightly higher than the YouTube network contribution measured by Zhou et al [55] in 2010 (reported below 30%). We posit two potential reasons: (1) the Vevo network is more tightly connected than a random YouTube video network [2]; (2) traffic on recommendation links may have increased since then, signifying the advances of modern recommender systems. Furthermore, among the 31.4% networked views, 85.9% are estimated from the same artist, echoing the network homogeneity found by Airoldi et al [2].…”

Section: The Impacts Of Network On Video Popularity Predictionmentioning

confidence: 99%

“…The main goals of recommender systems are maximizing the chance that a user clicks on an item in the next step [4,16,17,48] or in a longer time horizon [5,10,23]. However, recommendation in social systems remains as an open problem for two reasons: (1) a limited conceptual understanding of how finite human attention is allocated over the network of content, in which some items gain popularity at the expense of, or with the assistance of others; (2) the computational challenge of jointly recommending a large collection of items. The second gap comes from a lack of fine-grained measurements on the attention captured by items structured as a network.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Estimating Attention Flow in Online Video Networks

Rizoiu

Xie

2019

Proc. ACM Hum.-Comput. Interact.

View full text Add to dashboard Cite

Online videos have shown tremendous increase in Internet traffic. Most video hosting sites implement recommender systems, which connect the videos into a directed network and conceptually act as a source of pathways for users to navigate. At present, little is known about how human attention is allocated over such large-scale networks, and about the impacts of the recommender systems. In this paper, we first construct the Vevo network -a YouTube video network with 60,740 music videos interconnected by the recommendation links, and we collect their associated viewing dynamics. This results in a total of 310 million views every day over a period of 9 weeks. Next, we present large-scale measurements that connect the structure of the recommendation network and the video attention dynamics. We use the bow-tie structure to characterize the Vevo network and we find that its core component (23.1% of the videos), which occupies most of the attention (82.6% of the views), is made out of videos that are mainly recommended among themselves. This is indicative of the links between video recommendation and the inequality of attention allocation. Finally, we address the task of estimating the attention flow in the video recommendation network. We propose a model that accounts for the network effects for predicting video popularity, and we show it consistently outperforms the baselines. This model also identifies a group of artists gaining attention because of the recommendation network. Altogether, our observations and our models provide a new set of tools to better understand the impacts of recommender systems on collective social attention.

show abstract

“…In the literature review, there are some proposition of how the YouTube's recommendation system is functioning. According to [4], there are some orientation that the video recommendation approach used by YouTube is the collaborative filtering where the principal inputs of the algorithm are patterns of shared viewership. The recommendation is predicted by exploring a video graph representation where two videos are estimated to be related if there are many users that watch the video B after the video A.…”

Section: Case Study: Youtube As a Deep Learning-based Recommendermentioning

confidence: 99%

Deep Learning-Based Recommendation: Current Issues and Challenges

Fakhfakh¹,

Ammar²,

Amar³

2017

ijacsa

View full text Add to dashboard Cite

Abstract-Due to the revolutionary advances of deep learning achieved in the field of computer vision, object recognition and natural language processing, the deep learning gained much attention. The recommendation task is influenced by the deep learning trend which shows its significant effectiveness. The deep learning based recommender models provides a better detention of user preferences, item features and users-items interactions history. In this paper, we provide a recent literature review of researches dealing with deep learning based recommendation approaches which is preceded by a presentation of the main lines of the recommendation approaches and the deep learning techniques. Then we finish by presenting the recommendation approach adopted by the most popular video recommendation platform YouTube which is based essentially on deep learning advances.

show abstract

Follow the algorithm: An exploratory investigation of music on YouTube

Cited by 102 publications

References 29 publications

Researching YouTube

Researching YouTube

Estimating Attention Flow in Online Video Networks

Deep Learning-Based Recommendation: Current Issues and Challenges

Contact Info

Product

Resources

About