Sentiance and VRT transform the TV viewing experience using context-awareness
Algorithms build personalized and context-aware television viewing experiences, based on the context and behavior of viewers
05 FEBRUARY 2015, ANTWERP, BELGIUM
SummaryBased on the joint-research done with Belgium's national broadcasting agency, VRT, Sentiance launches context-aware recommendations technology that influences the television experience, based on the context and mood of a viewer. This context-aware technology provides media recommender systems a level of behavioral intelligence that make TV viewing experiences even more personal, relevant and engaging.
Both partners deliberately moved out of a traditional lab setting to study real world TV experiences in the home environment, measuring mood and access context using popular and affordable consumer wearables. Therefore, the insights generated and algorithms developed are easily transferable to existing and new products and apps, to make the everyday media consumption experience mood- and context aware.
The project studied how to adapt linear broadcast schedules to the average weekly biorhythm of the TV audience and introduce novel personalization practices based on context items as moments, mood, viewing audience, need states etc. These personalized schedules can then be applied to linear, as well as time shifted, and on-demand content recommendations.
Research that aims to go beyond content, and into context
“Our research highlights the necessity of moving beyond content, taking context into account and, ultimately, focusing on personal needs fulfilled by media moments”, explains Koen Willaert, Affective Computing expert at Sentiance.
Each TV experience fulfils certain needs, such as staying up to date, learning, empathizing with others, etc. These psychological concepts are called "need states" and are hard to capture in the wild, however they determine what content fits best for a given TV moment.
Our research found that certain needs correlate strongly with contextual cues that can be captured via wearables or smartphones, such as mood or the presence of other people. These cues can be ‘sensed’ by the Sentiance technology and help to grasp and better understand a fitting TV moment.
These cues can be ‘sensed’ by the Sentiance technology and help to grasp and better understand a fitting TV moment.
One of the key insights is that understanding the context and mood of one, or more, viewers in real-time is a critical component in maximizing the engagement of the viewing experience.
"For example, when a father with his son are in front of the TV during a rainy Sunday afternoon, it might be more opportune to focus more on his son for making a fitting movie recommendation, knowing the father will be non-engaged anyway", explains Koen.
We have found that these contextual cues are far more important than traditional clustering of past viewing preferences to make recommendations. For these TV moments it is still a challenge as how to recommend content that fits best. As only content engagement is not the primary goal, one needs to take a maximum of contextual cues into account to enable real time and context-aware engagement.
Introducing context-aware recommender technology
Once you know why someone turns on the TV, it becomes much easier to suggest to them exactly the content they want to see.
"When the Empathic project started, I thought empathic technologies were 20 years from practical use, today, 2 years later, Sentiance brings them to the market", says Dieter Boen, Head of VRT O&I.
This level of context-awareness is being offered in partnerships with media recommender system companies worldwide. A first partnership has been signed with ImpressTV, and more are underway.
"When the Empathic project started I thought empathic technologies were 20 years from practical use, today, 2 years later, Sentiance brings them to the market." Dieter Boen, Head of VRT O&I
"One of the key insights is that understanding the context and mood of one, or more, viewers in real-time is a critical component in maximizing the engagement of the viewing experience." Koen Willaert, Affective Computing for Sentiance
Download PDFDownload PDF
Powering the IOU - Internet of You
Sentiance is a data science company that uses artificial intelligence and machine learning algorithms to analyze IOT sensor data in order to create a deep understanding of human behavior and context. Sentiance's clients use the platform to create new products and services that turn the Internet of Things into the Internet of You.