Content Meets Interest - Contextual Ad Targeting
May 28th 2018 10:20 - 10:40
Established procedures for online ad targeting are currently being disrupted by two independent developments. The globally increasing tendency for political populism and media criticsm have raised the sensitivity of strong brands to avoid misplacement of their own campaigns in negative and compromising contexts (“Bad Ads”). On the other hand, ad targeting is mainly based on behavioral targeting techniques that heavily rely on (cookie-based) user profiling. This practice is threatened by legal restrictions raised by European GDPR – a globally effective regulation initiative for personal data protection.
The talk will showcase a solution for real-time contextual targeting that is exploiting the full power of cognitive computing to match campaigns to online users real interest. The approach abandons tracking of third party data and at the same time increases the precision of ad targeting on real semantic level – beyond what can be achieved with keyword based methods.
The talk will illustrate by selected real campaigns what additional value natural language understanding gives to both online users and advertisers.
One distinguished feature is taking into account actual trends and changes in the users’ perception of online content – depending on current trends like crises, scandals or other kinds of hot topics. The audience will get an understanding of how different technologies like deep learning, classification and concept recognition are combined to realize an optimal user experience.