Mining Big Data and Open Knowledge Sources to develop transparent and serendipitous content-based adaptive systems
Upcoming SlideShare
Loading in...5
×
 

Mining Big Data and Open Knowledge Sources to develop transparent and serendipitous content-based adaptive systems

on

  • 565 views

World Summit on Big Data and Organization Design - Paris

World Summit on Big Data and Organization Design - Paris

Statistics

Views

Total Views
565
Views on SlideShare
565
Embed Views
0

Actions

Likes
0
Downloads
7
Comments
1

0 Embeds 0

No embeds

Accessibility

Categories

Upload Details

Uploaded via as Adobe PDF

Usage Rights

© All Rights Reserved

Report content

Flagged as inappropriate Flag as inappropriate
Flag as inappropriate

Select your reason for flagging this presentation as inappropriate.

Cancel
  • Full Name Full Name Comment goes here.
    Are you sure you want to
    Your message goes here
    Processing…
Post Comment
Edit your comment

Mining Big Data and Open Knowledge Sources to develop transparent and serendipitous content-based adaptive systems Mining Big Data and Open Knowledge Sources to develop transparent and serendipitous content-based adaptive systems Presentation Transcript

  • Mining Big Data and OpenKnowledge Sources to developtransparent and serendipitouscontent-based adaptive systemsCataldo Musto, Giovanni Semeraro, Fedelucio Narducci
  • state of the art.C.Musto, G.Semeraro - Mining Big Data and Open Knowledge Sources to develop transparent and serendipitouscontent-based adaptive systems - World Summit on Big Data and Organization Design, Paris, 16-17 May 2013
  • our research: personalizationC.Musto, G.Semeraro - Mining Big Data and Open Knowledge Sources to develop transparent and serendipitouscontent-based adaptive systems - World Summit on Big Data and Organization Design, Paris, 16-17 May 2013
  • Recommender SystemsRelevant items (movies, news, books, etc.) are pushed to theuser according to her preferences or her needs.C.Musto, G.Semeraro - Mining Big Data and Open Knowledge Sources to develop transparent and serendipitouscontent-based adaptive systems - World Summit on Big Data and Organization Design, Paris, 16-17 May 2013
  • Amazon.comRecommendationsC.Musto, G.Semeraro - Mining Big Data and Open Knowledge Sources to develop transparent and serendipitouscontent-based adaptive systems - World Summit on Big Data and Organization Design, Paris, 16-17 May 2013
  • current recommendation technologies share threeimportant drawbacks.C.Musto, G.Semeraro - Mining Big Data and Open Knowledge Sources to develop transparent and serendipitouscontent-based adaptive systems - World Summit on Big Data and Organization Design, Paris, 16-17 May 2013
  • (1) training is a bottleneck.C.Musto, G.Semeraro - Mining Big Data and Open Knowledge Sources to develop transparent and serendipitouscontent-based adaptive systems - World Summit on Big Data and Organization Design, Paris, 16-17 May 2013
  • need forexplicitinformationaboutuser interests.C.Musto, G.Semeraro - Mining Big Data and Open Knowledge Sources to develop transparent and serendipitouscontent-based adaptive systems - World Summit on Big Data and Organization Design, Paris, 16-17 May 2013
  • (2) recsys are black boxes.C.Musto, G.Semeraro - Mining Big Data and Open Knowledge Sources to develop transparent and serendipitouscontent-based adaptive systems - World Summit on Big Data and Organization Design, Paris, 16-17 May 2013
  • (3) suggestions are not surprising.C.Musto, G.Semeraro - Mining Big Data and Open Knowledge Sources to develop transparent and serendipitouscontent-based adaptive systems - World Summit on Big Data and Organization Design, Paris, 16-17 May 2013
  • exploiting big data to build a novel generationof content-based adaptive systemssolutionC.Musto, G.Semeraro - Mining Big Data and Open Knowledge Sources to develop transparent and serendipitouscontent-based adaptive systems - World Summit on Big Data and Organization Design, Paris, 16-17 May 2013
  • current work.C.Musto, G.Semeraro - Mining Big Data and Open Knowledge Sources to develop transparent and serendipitouscontent-based adaptive systems - World Summit on Big Data and Organization Design, Paris, 16-17 May 2013near future work.
  • C.Musto, G.Semeraro - Mining Big Data and Open Knowledge Sources to develop transparent and serendipitouscontent-based adaptive systems - World Summit on Big Data and Organization Design, Paris, 16-17 May 2013
  • big data.C.Musto, G.Semeraro - Mining Big Data and Open Knowledge Sources to develop transparent and serendipitouscontent-based adaptive systems - World Summit on Big Data and Organization Design, Paris, 16-17 May 2013
  • InformationOverloadwe can handle 126 bits of informationwe deal with 393 bits of informationratio: more than 3x(Source: Adrian C.Ott,The 24-hour customer)consequence:C.Musto, G.Semeraro - Mining Big Data and Open Knowledge Sources to develop transparent and serendipitouscontent-based adaptive systems - World Summit on Big Data and Organization Design, Paris, 16-17 May 2013
  • Information OverloadC.Musto, G.Semeraro - Mining Big Data and Open Knowledge Sources to develop transparent and serendipitouscontent-based adaptive systems - World Summit on Big Data and Organization Design, Paris, 16-17 May 2013
  • Big Data: obstacle oropportunity?C.Musto, G.Semeraro - Mining Big Data and Open Knowledge Sources to develop transparent and serendipitouscontent-based adaptive systems - World Summit on Big Data and Organization Design, Paris, 16-17 May 2013
  • cornestone 1C.Musto, G.Semeraro - Mining Big Data and Open Knowledge Sources to develop transparent and serendipitouscontent-based adaptive systems - World Summit on Big Data and Organization Design, Paris, 16-17 May 2013exploit social media tomodel userpreferences.
  • social media are an opportunityprovide information about user preferencesC.Musto, G.Semeraro - Mining Big Data and Open Knowledge Sources to develop transparent and serendipitouscontent-based adaptive systems - World Summit on Big Data and Organization Design, Paris, 16-17 May 2013
  • exampleuser preferences in music from FacebookC.Musto, G.Semeraro - Mining Big Data and Open Knowledge Sources to develop transparent and serendipitouscontent-based adaptive systems - World Summit on Big Data and Organization Design, Paris, 16-17 May 2013
  • implicit preferencesC.Musto, G.Semeraro - Mining Big Data and Open Knowledge Sources to develop transparent and serendipitouscontent-based adaptive systems - World Summit on Big Data and Organization Design, Paris, 16-17 May 2013example
  • Play.meplaylistMost popular songs of the artists extracted from Last.fm (as well asthose added through the enrichment) are proposed to the user.C.Musto, G.Semeraro - Mining Big Data and Open Knowledge Sources to develop transparent and serendipitouscontent-based adaptive systems - World Summit on Big Data and Organization Design, Paris, 16-17 May 2013
  • MyusicrecommendationsC.Musto, G.Semeraro - Mining Big Data and Open Knowledge Sources to develop transparent and serendipitouscontent-based adaptive systems - World Summit on Big Data and Organization Design, Paris, 16-17 May 2013
  • cornestone 2exploit entity linking algorithmsto make user profiles moretransparent and LOD-awareC.Musto, G.Semeraro - Mining Big Data and Open Knowledge Sources to develop transparent and serendipitouscontent-based adaptive systems - World Summit on Big Data and Organization Design, Paris, 16-17 May 2013
  • MyFeedsRSS recommendationsC.Musto, G.Semeraro - Mining Big Data and Open Knowledge Sources to develop transparent and serendipitouscontent-based adaptive systems - World Summit on Big Data and Organization Design, Paris, 16-17 May 2013
  • MyFeedstransparent user preferencesC.Musto, G.Semeraro - Mining Big Data and Open Knowledge Sources to develop transparent and serendipitouscontent-based adaptive systems - World Summit on Big Data and Organization Design, Paris, 16-17 May 2013extracted from Facebook.
  • MyFeedstransparent user preferencesC.Musto, G.Semeraro - Mining Big Data and Open Knowledge Sources to develop transparent and serendipitouscontent-based adaptive systems - World Summit on Big Data and Organization Design, Paris, 16-17 May 2013further processing
  • MyFeedsentity linking algorithmsC.Musto, G.Semeraro - Mining Big Data and Open Knowledge Sources to develop transparent and serendipitouscontent-based adaptive systems - World Summit on Big Data and Organization Design, Paris, 16-17 May 2013• They map free text with structuredinformation• Wikipedia pages or DBpedia nodes• examples• Tag.me ,Wikipedia Miner, DBpediaSpotlight, etc.
  • Tag.meextracts the Wikipedia pages the content refers to.C.Musto, G.Semeraro - Mining Big Data and Open Knowledge Sources to develop transparent and serendipitouscontent-based adaptive systems - World Summit on Big Data and Organization Design, Paris, 16-17 May 2013
  • Linked Open Data CloudStructured(RDF)representationof the informationstored in Wikipedia.C.Musto, G.Semeraro - Mining Big Data and Open Knowledge Sources to develop transparent and serendipitouscontent-based adaptive systems - World Summit on Big Data and Organization Design, Paris, 16-17 May 2013
  • Linked Open Data CloudProfiles basedon Tag.me areLOD-awareC.Musto, G.Semeraro - Mining Big Data and Open Knowledge Sources to develop transparent and serendipitouscontent-based adaptive systems - World Summit on Big Data and Organization Design, Paris, 16-17 May 2013
  • cornestone 3C.Musto, G.Semeraro - Mining Big Data and Open Knowledge Sources to develop transparent and serendipitouscontent-based adaptive systems - World Summit on Big Data and Organization Design, Paris, 16-17 May 2013exploit open knowledge sourcesto make recommendationtechniques more serendipitous.
  • ‘in vitro’ experimentsWatchmi plug-indeveloped by Aprico.tvC.Musto, G.Semeraro - Mining Big Data and Open Knowledge Sources to develop transparent and serendipitouscontent-based adaptive systems - World Summit on Big Data and Organization Design, Paris, 16-17 May 2013
  • From BOW to eBOWGiven a description of a TV show, we exploit ESA toobtain an enhanced representationThe original set of features is enriched with the set ofWikipedia articles related the most with theTV showC.Musto, G.Semeraro - Mining Big Data and Open Knowledge Sources to develop transparent and serendipitouscontent-based adaptive systems - World Summit on Big Data and Organization Design, Paris, 16-17 May 2013
  • TV SHOWRad an RadDie besten Duelle der MotoGP(Wheel to wheelThe best duels in the MotoGP)Wikipedia(Articles(großer&preis&von&italien&(motorrad)&großer&preis&von&malaysia&(motorrad)&großer&preis&von&tschechien&(motorrad)&scuderia&ferrari&valen8no&rossi&motorrad9wm9saison&2005&motorrad9wm9saison&2006&max&biaggi&großer&preis&der&usa&(motorrad)&motorrad9wm9saison&2008&rad&(heraldik)&loris&capirossi&shin’ya&nakano&motogp&exampleFrom BOW to eBOWC.Musto, G.Semeraro - Mining Big Data and Open Knowledge Sources to develop transparent and serendipitouscontent-based adaptive systems - World Summit on Big Data and Organization Design, Paris, 16-17 May 2013
  • challenges.C.Musto, G.Semeraro - Mining Big Data and Open Knowledge Sources to develop transparent and serendipitouscontent-based adaptive systems - World Summit on Big Data and Organization Design, Paris, 16-17 May 2013issues.recommendations.
  • Challenges and IssuesC.Musto, G.Semeraro - Mining Big Data and Open Knowledge Sources to develop transparent and serendipitouscontent-based adaptive systems - World Summit on Big Data and Organization Design, Paris, 16-17 May 2013• Main challenge and issue:• data representation and data filtering• How to exploit these novel data sylos?• What information is relevant for personalization?• What kind of processing do data need?• Which one is the best representation?• Do reasoning techniques improve profiles transparency andpersonalization accuracy?• Do people accept the exploitation of these data?• How to model the context?
  • RecommendationsC.Musto, G.Semeraro - Mining Big Data and Open Knowledge Sources to develop transparent and serendipitouscontent-based adaptive systems - World Summit on Big Data and Organization Design, Paris, 16-17 May 2013• Cornerstones• Social media-based user profiling• LOD-aware user profiles• Open Knowledge Sources for Serendipitous Encounters• Recommendations• Promote the LOD initiative, to publish data in a structuredform, to enable reasoning on the information• Make data sylos interconnected• To design applications able to properly model, manage andexploit the big amount of data coming from social media.
  • questions?Cataldo Musto, Ph.D. - cataldo.musto@uniba.it