Customizing Semantic Profiling for Digital Advertising
0 likes175 views
The document presents an approach for customizing semantic profiling for digital advertising. It discusses the need for user profiling in a big data context for advertising. Current keyword-based approaches are limited. The presented approach models domain knowledge and uses semantic qualification of user data from sources like Dbpedia to profile users beyond keywords. A practical implementation uses SWRL rules on classified web navigation logs to infer user interests and marketing segments with associated probabilities. Future work includes testing on additional data sets and integrating with a graph database.
Customizing Semantic Profiling for Digital Advertising
- 1. AnaRoxin–ana.roxin@chekcsem.fr–ProjectteamChecksem–LaboratoireElectroniqueInformatiqueetImage(LE2I –UMRCNRS6306)–UniversityofBurgundy Customizing Semantic Profiling for Digital Advertising Ana Roxin - ana-maria.roxin@u-bourgogne.fr October, 28th 2014 LE2I (Laboratory of Informatics, Image and Electronics) - UMR CNRS 6306 University of Burgundy
- 2. AnaRoxin–ana.roxin@chekcsem.fr–ProjectteamChecksem–LaboratoireElectroniqueInformatiqueetImage(LE2I –UMRCNRS6306)–UniversityofBurgundy Agenda General context • Need for user profiling… • … in a Big Data Context… • … for Digital advertising Related work • General trends for Big Data analysis • Limitations for keyword-based approaches Our approach • Domain knowledge modeling • Practical implementation
- 4. AnaRoxin–ana.roxin@chekcsem.fr–ProjectteamChecksem–LaboratoireElectroniqueInformatiqueetImage(LE2I –UMRCNRS6306)–UniversityofBurgundy Need for User Profiling… Language and Localisation ?
- 5. AnaRoxin–ana.roxin@chekcsem.fr–ProjectteamChecksem–LaboratoireElectroniqueInformatiqueetImage(LE2I –UMRCNRS6306)–UniversityofBurgundy … in a Big Data context … Volume • Massive amounts of data have to be treated Velocity • Those data arrive in high speed Variety • Data types and formats are heterogeneous Veracity • Data are not always sound and have to be verified Value • They have an inherent value that can be processed by the application
- 8. AnaRoxin–ana.roxin@chekcsem.fr–ProjectteamChecksem–LaboratoireElectroniqueInformatiqueetImage(LE2I –UMRCNRS6306)–UniversityofBurgundy Re-targeting • Re-confront the user with: • Previously visited content • Very similar contents Web usage mining • Unite profiling efforts across pages • Support dynamic structural changes of a Web site in order to adapt advertisements to the active user Methods for Web advertising
- 9. AnaRoxin–ana.roxin@chekcsem.fr–ProjectteamChecksem–LaboratoireElectroniqueInformatiqueetImage(LE2I –UMRCNRS6306)–UniversityofBurgundy Machine Learning & Statistics • “Richness of data and challenges in their predictive analysis and forecasting” • Stable and scalable techniques: • SVMs, regressions trees, neural networks • Not yet semantic-based techniques… Problems • Underlying data structures • Explicability of results • Context integration Big Data analysis
- 13. AnaRoxin–ana.roxin@chekcsem.fr–ProjectteamChecksem–LaboratoireElectroniqueInformatiqueetImage(LE2I –UMRCNRS6306)–UniversityofBurgundy Other issues Integration and interpretationData • Discover new information sources for knowledge augmentation • Semantic disambiguation for keywords in a given context Unstructured, heterogeneous resourcesUnderstanding • Semantic interpretation and integration of such contents More and more data…Performance • … less and less time for analysis and processing
- 15. AnaRoxin–ana.roxin@chekcsem.fr–ProjectteamChecksem–LaboratoireElectroniqueInformatiqueetImage(LE2I –UMRCNRS6306)–UniversityofBurgundy Modelling domain knowledge • Model expert knowledge • Identify relevant core concepts and their relations • Discard redundant/surplus information Semantic qualification of user data • Semantic disambiguation • Find real-world concepts, not keywords • Exploit additional information sources • Dbpedia, WordNet, Freebase Bridge using SW technologies
- 18. AnaRoxin–ana.roxin@chekcsem.fr–ProjectteamChecksem–LaboratoireElectroniqueInformatiqueetImage(LE2I –UMRCNRS6306)–UniversityofBurgundy Domain specialisation 2 Sporty Mom User(?user), Universe:Sport (?u1), hasLongTermInterestIn(?user, ?u1), hasChilren(?user), isAdult (?user) -> belongsToSegment(?user,”SportyMom”)
- 20. AnaRoxin–ana.roxin@chekcsem.fr–ProjectteamChecksem–LaboratoireElectroniqueInformatiqueetImage(LE2I –UMRCNRS6306)–UniversityofBurgundy Synchronous Asynchronous WP Semantic Qualification Process Population Qualification Knowledge base Web usage data Cookies Log Population Profile Characterization Inference User targeting Practical implementation 1
- 21. AnaRoxin–ana.roxin@chekcsem.fr–ProjectteamChecksem–LaboratoireElectroniqueInformatiqueetImage(LE2I –UMRCNRS6306)–UniversityofBurgundy Practical implementation 2 Weighted user profiling SWRL rules – on weighted classified URLs + navigation information (number of hits, time spent) Weighted marketing segment belonging URL weighted classification Lemma filtering Concept extraction (semantic annotation) Universe similarity computation Web navigation logs parsing URL + navigation information extraction Sporty Mom 80% Geek 20%
- 22. AnaRoxin–ana.roxin@chekcsem.fr–ProjectteamChecksem–LaboratoireElectroniqueInformatiqueetImage(LE2I –UMRCNRS6306)–UniversityofBurgundy Profiling customization Knowledge base browsing Drag ‘n drop SWRL rule creation Corresponding BIDs display and download
- 24. AnaRoxin–ana.roxin@chekcsem.fr–ProjectteamChecksem–LaboratoireElectroniqueInformatiqueetImage(LE2I –UMRCNRS6306)–UniversityofBurgundy Fine tuning • Precise links to external knowledge bases • Semantic distance for mapping webpages to universes • Usage of contextual data (time, location, user agent) in SWRL rules Testing and extension • First benchmarks on partner data: • Real web navigation logs – French websites • Testing on open datasets (Reuters, Leipzig University) • Enable scientific comparison + extend to English • Integration to Stardog graph database Open questions
- 25. AnaRoxin–ana.roxin@chekcsem.fr–ProjectteamChecksem–LaboratoireElectroniqueInformatiqueetImage(LE2I –UMRCNRS6306)–UniversityofBurgundy Presented system • Functional profiling system based on users' web navigation that aims to predict future consumer decisions • Highly customized set of classes to summarize user’s interests as expressed in navigation logs Next steps • Extend the rule base for segment creation to enable more expressive design and segment creation • Extend the ontology with external repositories for more interesting inferences Take away message • Profiling for digital advertising is a necessary, but not an easy task • Semantic Web technologies are an answer to related problems Summary
- 26. AnaRoxin–ana.roxin@chekcsem.fr–ProjectteamChecksem–LaboratoireElectroniqueInformatiqueetImage(LE2I –UMRCNRS6306)–UniversityofBurgundy LE2I – UMR CNRS 6306 – University of Burgundy ana-maria.roxin@u-bourgogne.fr Thank you for your attention. Questions ?