IBC Paper:
Using machine learning to create personalised Snackable Content

Media Distillery submitted a Technical Paper to the IBC2018 conference, which was reviewed and accepted by a panel of experts. Our paper is published on IBC365 and we had the opportunity to present our paper within the “Cutting-Edge Tech Innovators”-track of the IBC conference programme.

 

Despite having a large amount of media content available, Pay TV services have not been able to offer a user experience similar to OTT and VoD offerings, which can cater to their audiences with short snippets and binge watch possibilities. In order to address this shortcoming, TV providers offer short-form content by manually “cutting” the linear content into VoD assets. However, this is often neither feasible nor a scalable solution. Besides, it is not the only aspect that frustrates consumers: research shows consumers are also struggling to discover new content.

Read the full paper!

Read the full 10-page paper in which we present our platform that utilizes state-of-the-art Machine Learning algorithms for the real-time analysis of thousands of hours of multilingual multimedia content, including television and VoD. These analyses enable us to obtain rich metadata from the content of videos and suggest small chunks of personalised content (”snacks”) to users based on their preferences.

Download full paper