Federating advertisement targeting with Linked Data Sven Lieber , Ben De Meester, Ruben Verborgh and Anastasia Dimou
Federating advertisement targeting with Linked Data Sven Lieber , Ben De Meester, Ruben Verborgh and Anastasia Dimou
An online advertising example Federated querying with EcoDaLo Comparison of different approaches Privacy and ethics considerations 3
Although still relying on an identification mechanism , we improve advertising targeting with decentralized knowledge graphs by reusing existing infrastructure which avoids data sharing .
An online advertising example Federated querying with EcoDaLo Comparison of different approaches Privacy and ethics considerations 5
How does online advertising work? what : promote SEMANTICS conference target : SemWeb researchers between 18 and 60 Campaign format : mobile leaderboard setup Online Behavioral Advertising (OBA) Ad serving Content C
An online advertising example Publisher A Observations what : promote SEMANTICS conference target : SemWeb researchers between 18 and 60 Publisher A format : mobile leaderboard Visitor traits E.g. “ between_18_and_25 ” Ad Combined Data integration C Server data User visiting a website with a mobile device Publisher B X Privacy considerations Visitor traits P u b l i s h X Competitive disadvantage e r O B b s e r v a t i o n s E.g. “ LD_Expert ”
An online advertising example Federated querying with EcoDaLo Comparison of different approaches Privacy and ethics considerations 8
EcoDaLo facts Research in Flanders, Belgium Three complementary funding consortium partners: AdLogix , Pebble Media and Roularta Media Group Partners explaining our solution https://sven-lieber.org/ecodalo-video
An online advertising example Publisher A Observations what : promote SEMANTICS conference target : SemWeb researchers between 18 and 60 Publisher A format : mobile leaderboard Visitor traits E.g. “ between_18_and_25 ” Ad Combined Data integration C Server data User visiting a website with a mobile device Publisher B X Privacy considerations Visitor traits P u b l i s h X Competitive disadvantage e r O B b s e r v a t i o n s E.g. “ LD_Expert ”
Our approach avoids combination of data Publisher A Observations what : promote SEMANTICS conference target : SemWeb researchers between 18 and 60 Publisher A format : mobile leaderboard Visitor traits E.g. “ between_18_and_25 ” Ad Federated C Server Querying User visiting a website with a mobile device Publisher B Only aggregate traits Visitor traits P u b No data is shared l i s h e r O B b s e Exclusivity of traits (and how observed) r v a t i o n s E.g. “ LD_Expert ”
Our solution is based on declarative semantic mappings Publisher A Visitor traits E.g. Common “ between_18_and_25 ” Ad Federated Trait C Server Querying Model (SKOS) Between_18_and_60 includes between_18_and_25 Publisher B Taxonomic relations between SemWeb_Expert and Visitor traits LinkedData_Expert or Ontology_Expert E.g. “ LD_Expert ”
An online advertising example Federated querying with EcoDaLo Comparison of different approaches Privacy and ethics considerations 13
Our solution compared to other approaches Local publisher Global publisher (Data) (Trait) federation integration X Trait quality X Scale X X Exclusive(privacy) X Ease of setup XX XX X Interoperability X X X Maintainability
An online advertising example Federated querying with EcoDaLo Comparison of different approaches Privacy and ethics considerations 15
GDPR-compliant consent needed Which personal data is used for which purpose; third parties ; explicit opt-in Ethical considerations beyond our technical solution EcoDaLo assumes good faith of publishers, ethical guidelines exist which need to be considered
An online advertising example Federated querying with EcoDaLo Comparison of different approaches Privacy and ethics considerations 17
More research on describing and using constraints for querying of decentralized knowledge graphs sven-lieber.org SvenLieber knows.idlab.ugent.be
Recommend
More recommend
