Sociosemiotic Recommendations
Considerations on the Meaning of the Netflix Recommendation System's Viewing Suggestions
Abstract
This article reflects on how Netflix's recommendation system works. More specifically, it asks whether the audiovisual contents suggested by the algorithms of the well-known American company to its customers, on the basis of the mechanised study of their viewing preferences, really appear interesting and meaningful. In order to provide an answer, a sociosemiotic survey was carried out, partly in the field and partly at the desk, based on twenty interviews with some Netflix users and on the analysis of some TV series they watched, among those reported by the streaming platform. The study highlighted some issues related to the labelling system of such contents, an activity that is, after all, carried out by human beings, who instruct machines. In this regard, some solutions are suggested to make the criteria for classifying audiovisual products in general more effective, so as to improve the performance of the algorithms and the services of all those companies or institutions that, like Netflix, use recommendation systems to interact with us.
This journal provides immediate open access to its content on the principle that making research freely available to the public supports a greater global exchange of knowledge.
DigitCult is open access gold. Articles are published under a Creative Commons Attribution (CC BY-NC 4.0) licence to support maximum dissemination and use.
With the licence CC-BY, authors retain the copyright, allowing anyone to download, reuse, re-print, modify, distribute and/or copy their contribution. The work must be properly attributed to its author.
It is not necessary to ask further permissions both to author or journal board.