1. Modeling, obtaining and storing
data from social media tools in
Artefact-Actor-Networks
Wolfgang Reinhardt, Tobias Varlemann, Matthias Moi, Adrian Wilke
University of Paderborn (Germany)
Computer Science Education Group
3. Artefact-Actor-Networks
combination of
Social Networks
Artefact Networks
Social Media
E-Mail
Documents
goal
raise awareness about relevant people, topics and objects
Wolfgang Reinhardt, @wollepb, University of Paderborn (Germany)
4. Network in World Wide Web Network of documents Consolidated artefact network I
Document D
B
Website B D
C
Document C A
Website A
(1) (2) (3)
Consolidated artefact network I Network with bookmarks Consolidated artefact network II
Website B
Bookmark E
(1) (2) (3)
Wolfgang Reinhardt, @wollepb, University of Paderborn (Germany)
5. Actor network of company Private actor network Consolidated actor network
Person Y Person Y
Person Z
Person Z
Person X Person X Person X
(1) (2) (3)
Consolidated artefact network II Consolidated actor network
Wolfgang Reinhardt, @wollepb, University of Paderborn (Germany)
7. Where does the data comes from?
strong focus on Social Media tools
Twitter
Delicious
Scribd
SlideShare
Blogs
Wikipedia
Scientific paper
Upload, DBLP, CiteSeer
Wolfgang Reinhardt, @wollepb, University of Paderborn (Germany)
8. How do we extract data?
Java-based backend
<< component >>
Crawling-Block
OSGi-enabled
hot deployment
Jena framework << component >>
DataStore-Block
crawl, store, analyse
crawl and parse
store data << component >>
Analyser-Block
analyse data
Wolfgang Reinhardt, @wollepb, University of Paderborn (Germany)
10. AANBase Web Wiki
linksTo:isRelated
knows
hasPart:isRelated
creationTime
Actor Webartefact WikiArtefact DATA
redirectedFrom
isRelated hasArtefact screenName
DATA
WikiActor DATA
Artefact
hasKeyword
MediaWiki
KeywordValue
Keyword DATA previousVersion:isRelated
nextVersion:isRelated editedArticle:hasArtefact
MediaWikiArtefact MediaWikiActor
hasMediaWikiCategory:hasKeyword
DATA
pageID
oid
userComment
MediaWikiCategory
Dublin Core FOAF
ONTOLOGIES SIOC SWRC
Wolfgang Reinhardt, @wollepb, University of Paderborn (Germany)
11. Semantic relations
ART2 relations
between artefacts
isReplyOf, linksTo, hasPart, isReplyTo, hasComment
ACT2 relations
between actors
isFriendOf, relatesTo, collaboratesWith,
AA relations
between artefacts and actors
creatorOf, contributorOf, discussantOf, forwarderOf, bookmarkerOf
Wolfgang Reinhardt, @wollepb, University of Paderborn (Germany)
13. Used analyzers
Text analyzers
Orchestr8 - Alchemy API
OpenCalais
Semantic similarity
SemSim algorithm
TF-IDF
Cosine similarity
Wolfgang Reinhardt, @wollepb, University of Paderborn (Germany)
14. Applications
that make use of
Artefact-Actor-Networks
Wolfgang Reinhardt, @wollepb, University of Paderborn (Germany)
21. What’s next?
deal with performance issues
1.5M Wikipedia articles & >> 4B RDF triples
Jena & SPARQL = no good
Reasoning & Inferencing of large data sets = ouch
Recommender Systems
Clustering
Advanced semantic similarity
Wolfgang Reinhardt, @wollepb, University of Paderborn (Germany)
22. Thank you for your attention
Wolfgang Reinhardt, @wollepb
University of Paderborn, Germany
Wolfgang Reinhardt, @wollepb, University of Paderborn (Germany)