ReTV provides novel information services to cope with a rapidly changing digital media landscape that continuously redefines the demands and expectations of TV viewers. Online video keeps gaining momentum. This digital shift requires broadcasters to evolve into multi-channel content publishers. In addition to their broadcasts, they need to manage their own Web applications, integrate content with third-party Web platforms such as YouTube and Zattoo, engage users and stakeholders via social networking platforms such as Facebook and Twitter, offer streams via mobile channels, manage SmartTV apps, and make their vast archives available in digital form.
Trans-Vector Platform (TVP)
ReTV provides the Trans-Vector Platform (TVP) for broadcasters and their content partners (archives, OTT services, etc.) to obtain deep insights into how their media content is being engaged with, and by whom. Highly scalable recommendation and prediction services will allow them to better manage and re-purpose content assets across established and emerging channels (= media vectors), and keep broadcasters competitive in the digital TV environment, attracting more viewers to their channels and ultimately generating more value from their content – whether through maximizing reach or engagement.
The TVP will provide these stakeholders with the ability to “publish to all media vectors with the effort of one”. It will empower broadcasters and brands to continuously measure and predict the success of their content and advertisements in terms of reach and audience engagement across vectors, allowing them to optimize decision making processes.
Content Processing Workflow
ReTV aims to provide media organizations with the following key functions:
- Collect an integrated repository of media assets from internal and external media vectors (media organizations’ own news archives, blogs, digital content streams from various social media platforms, etc.).
- Annotate these assets with extracted metadata such as keywords, sentiment and the referenced geographic locations, which are a prerequisite for the subsequent prediction and enhancement steps.
- Measure and visualize audience and content metrics from previously published assets (e.g. broadcast TV).
- Predict future topics of interest as well as the success of re-purposed content based on these metrics, in terms of both reach and engagement.
- Enhance existing assets according to the predictions, determining which content should be re-used and in what form it should be re-purposed.
- Schedule when the playout/distribution should take place.
- Publish re-purposed content and targeted ads to an array of vectors.
webLyzard leads the ReTV system integration, leveraging its existing portfolio of visual analytics components and expanding the predictive capabilities of its Web Intelligence platform. A flexible and highly scalable API framework will facilitate the integration of additional vectors as they emerge. Once re-purposed content is distributed across vectors based on ReTV recommendations, the continued gathering of content and audience metrics for this re-purposed content strengthens the analytic models. This in turn triggers a new cycle of content re-purposing, in a virtuous circle that helps media organizations to optimize the distribution of their content assets.
The ReTV Innovation Action is funded within the EU Horizon 2020 Programme, carried out from 01 Jan 2018 to 31 Dec 2020. Business partners webLyzard and Genistat will design, implement and exploit the ReTV software and services. The technical partners Vrije Universiteit Amsterdam (VUA), MODUL Technology (MT) and the Centre for Research and Technology Hellas (CERTH) will provide functional components, together with the know-how for their integration. The use case partners include Rundfunk Berlin-Brandenburg (RBB), a public European broadcaster with a significant audience, and the Netherlands Institute for Sound and Vision (NISV), a comprehensive audiovisual digital archive.
- Scharl, A., Hubmann-Haidvogel, A., Jones, A., Fischl, D., Kamolov, R., Weichselbraun, A. and Rafelsberger, W. (2016). “Analyzing the Public Discourse on Works of Fiction – Automatic Emotion Detection in Online Media Coverage about HBO’s Game of Thrones“, Information Processing & Management, 52(1): 129-138 [Best Paper Award – Honorable Mention].
- Scharl, A., Weichselbraun, A., Göbel, M., Rafelsberger, W. and Kamolov, R. (2016). “Scalable Knowledge Extraction and Visualization for Web Intelligence“, 49th Hawaii International Conference on System Sciences (HICSS-2016). Kauai, USA: IEEE Press. 3749-3757 [Best Paper Award].