On the Quest for Changing Knowledge. Capturing emerging entities from social media. WebScience 2016 DDI
Download as PPTX, PDF0 likes1,573 views
The document discusses the challenges and methodologies surrounding the formalization and extraction of emerging knowledge using social media and data mining techniques. It highlights the significance of domain experts in discovering valuable information while addressing biases in knowledge sources. The authors present experimental findings on strategies for knowledge enrichment and conclude with a call to integrate data-driven innovation with knowledge development.
On the Quest for Changing Knowledge. Capturing emerging entities from social media. WebScience 2016 DDI
- 1. On the Quest for Changing Knowledge Marco Brambilla, Stefano Ceri, Florian Daniel, Emanuele Della Valle @marcobrambi
- 3. Innovation requires Precise To the point Up-to-date Domain-specific information
- 4. There are more things In heaven and earth, Horatio, Than are dreamt of in your philosophy. Shakespeare (Hamlet Act 1, scene 5)
- 5. From Data to Wisdom
- 6. Formalizing new knowledge is hard Only high frequency emerges The long tail challenge
- 7. Knowledge Extraction Text mining Semantic Web Search and recommendation systems No specific care for emerging knowledge
- 8. Heaven and Heart How to peer through an effective window on real world? Social media, our blessing and curse Domain experts matter
- 9. Can we use social networks to discover emerging knowledge?
- 10. Beware the streetlamp effect The bias of the source The bias of the observer
- 11. Famous Emerging
- 13. Overview
- 14. Knowledge Enrichment Setting HF Entity1 HF Entity5 HF Entity2 HF Entity4 HF Entity3 LF Entity1 ?? LF Entity2 LF Entity4 LF Entity3 ?? High Frequency Entities Low Frequency Entities ?? ?? ???? ?? Type1 Type11 Type2 Type111 Instances Types <<instanceof>> <<instanceof>> <<instanceof>> <<instanceof>> <<instanceof>> <<instanceof>> ?? ?? ?? ?? ?? Seed Entity Seed Type Type of interest Legend Expert inputs Enrichment problems Property2 Relations HF - LF entities Relations LF - LF entities Typing of LF entities Extraction of new LF entities Property1 ?? ?? ?? Finding attribute values
- 16. Domain Types Types selected by the experts Relevant for the domain
- 17. Seed characterization Selected by the expert Belonging to an expert type Thoroughly Described # @ a w
- 18. Social Media Sourcing Content coming from the seeds’ accounts
- 19. Candidate Selection Potentially any entity extracted from the social streams Resulting in huge sets of candidates # @ a w ♥
- 20. Candidate Typing
- 21. Candidate Pruning Initial pruning of candidates based on TF-DF:= df * tf / (N – df +1) (*) variant of TF-IDF that does not discount document frequency because we are actually happy about frequent appearance (we don’t look for information entropy!)
- 23. Candidate Vector Space Purely syntactic Semantic: Based on entity extraction / DBpedia Based on deep learning on images / ClarifAI
- 25. Example Analysis
- 27. 4,400 strategies evaluated 44 alternative feature vectors (12 basic features and 32 aggregations) 9 different weighting values for aggregations 5 levels of recall for entity extraction 3 different distances
- 28. Pruning Phase From 4,400 down to 10 strategies Eliminating the less relevant parameters
- 29. Italian Fashion Brands Precision @5 = 0.2 Increasing # seeds reduces precision
- 30. Australian Writers – 22 seeds Precision @5 = 0.8
- 31. Innovative Painters – 21 seeds Precision @5 = 0.6
- 32. Twitter vs. Instagram P@5 = 1.0 P@5 = 0.8 vs.
- 33. Fashion: Twitter + Instagram &
- 34. & Writers: Twitter + Instagram Prec. = 1
- 35. Conclusion It’s about time to build innovation based on data and build knowledge based on innovation Harvesting can be iterative
- 36. On the Quest for Changing Knowledge contact us Marco Brambilla, @marcobrambi, marco.brambilla@polimi.it http://datascience.deib.polimi.it