umu.sePublications
Change search
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf
SpotiBot — Turing Testing Spotify
Umeå University, Faculty of Arts, Department of culture and media studies. Umeå University, Faculty of Arts, Humlab.
Umeå University, Faculty of Arts, Humlab.
2018 (English)In: Digital Humanities Quarterly, ISSN 1938-4122, E-ISSN 1938-4122, Vol. 12, no 1Article in journal (Refereed) Published
Abstract [en]

Even if digitized and born-digital audiovisual material today amounts to a steadily increasing body of data to work with and research, such media modalities are still relatively poorly represented in the field of DH. Streaming media is a case in point, and the purpose of this article is to provide some findings from an ongoing audio (and music) research project, that deals with experiments, interventions and the reverse engineering of Spotify’s algorithms, aggregation procedures, and valuation strategies. One such research experiment, the SpotiBot intervention, was set up at Humlab, Umeå University. Via multiple bots running in parallel our idea was to examine if it is possible to provoke — or even undermine — the Spotify business model (based on the so called “30 second royalty rule”). Essentially, the experiment resembled a Turing test, where we asked ourselves what happens when — not if — streaming bots approximate human listener behavior in such a way that it becomes impossible to distinguish between a human and a machine. Implemented in the Python programming language, and using a web UI testing frameworks, our so called SpotiBot engine automated the Spotify web client by simulating user interaction within the web interface. The SpotiBot engine was instructed to play a single track repeatedly (both self-produced music and Abba’s “Dancing Queen”), during less and more than 30 seconds, and with a fixed repetition scheme running from 100 to n times (simultaneously with different Spotify Free ‘bot accounts’). Our bots also logged all results. In short, our bots demonstrated the ability (at least sometimes) to continuously play tracks, indicating that the Spotify business model can be tampered with. Using a single virtual machine — hidden behind only one proxy IP — the results of the intervention hence stipulate that it is possible to automatically play tracks for thousands of repetitions that exceeds the royalty rule.

Place, publisher, year, edition, pages
2018. Vol. 12, no 1
National Category
Media Studies
Identifiers
URN: urn:nbn:se:umu:diva-147699OAI: oai:DiVA.org:umu-147699DiVA, id: diva2:1205665
Funder
Swedish Research Council, 2013-1139Available from: 2018-05-14 Created: 2018-05-14 Last updated: 2018-06-09Bibliographically approved

Open Access in DiVA

fulltext(955 kB)32 downloads
File information
File name FULLTEXT02.pdfFile size 955 kBChecksum SHA-512
d7adf0130d03f121f63e8ce317ba5886d3f1eb1abc29a57f202a43ede65f82ed0155cd6f093b760f4b22d9c0aa937e05c9953d27ed7a3c4a45cbdbf56cb17c22
Type fulltextMimetype application/pdf

Other links

URL

Authority records BETA

Pelle, SnickarsMähler, Roger

Search in DiVA

By author/editor
Pelle, SnickarsMähler, Roger
By organisation
Department of culture and media studiesHumlab
In the same journal
Digital Humanities Quarterly
Media Studies

Search outside of DiVA

GoogleGoogle Scholar
Total: 32 downloads
The number of downloads is the sum of all downloads of full texts. It may include eg previous versions that are now no longer available

urn-nbn

Altmetric score

urn-nbn
Total: 140 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf