emotions experiences and social media
play

Emotions, Experiences and Social Media Maarten de Rijke University - PowerPoint PPT Presentation

Emotions, Experiences and Social Media Maarten de Rijke University of Amsterdam 1 Another perspective Standards, infrastructure as seen by an academic research group Intelligent information access Content-based matching


  1. Emotions, Experiences and Social Media Maarten de Rijke University of Amsterdam 1

  2. Another perspective • Standards, infrastructure as seen by an academic research group • Intelligent information access • Content-based matching • Additional features (recency, authoritativeness, novelty, opinionatedness, …) • Combine content-based and additional features • Presentation 2 2

  3. Research strategy Experiment Theory Application 3 3

  4. Why? Online lives 4 4

  5. What? 5 5

  6. What? Providing access to all Finding experiences to parliamentary data in inform creation of new Europe products Linking archives News archives meet Social media video archives meet … analysis Reputation management: identifying and tracking stakeholders Enrichment through linking Open data initiatives Real-time impact A web of applications prediction Learning from Computational Religious studies implicit feedback humanities and social sciences Multilingual log file analysis Medical anthropology Interest machine E-discovery Governmental Email search Communication science Detecting Aggregated entity radicalization Chronobiology search Entity mining 5 5

  7. Political Mashup • Aggregating parliamentary data • Debates, debate structure • “Semantification” • Linking to video broadcasts, twitter, blogs, party programs • Tracking topic ownership from parliament to social media and back 6

  8. CoSyne • Translate between wiki pages • Identify changes in one page • Find gaps in other, target pages • Translate material to be inserted in gaps • Insert translated material in gaps 7

  9. The mood of the web • Mood annotated blogs • Real-time mood tracking and prediction • MoodViews (2005-2009) • Moodgrapher: follow • Moodteller: predict • Moodsignals: explain • Moodspotter: discover associations • Analyzing ‘old’ data: chronobiology 8 8

  10. The mood of the web • Mood annotated blogs • Real-time mood tracking and prediction • MoodViews (2005-2009) • Moodgrapher: follow • Moodteller: predict • Moodsignals: explain • Moodspotter: discover associations • Analyzing ‘old’ data: chronobiology http://www.moodviews.com 8 8

  11. The mood of the web • Mood annotated blogs • Real-time mood tracking and prediction • MoodViews (2005-2009) • Moodgrapher: follow • Moodteller: predict • Moodsignals: explain • Moodspotter: discover associations • Analyzing ‘old’ data: chronobiology http://www.moodviews.com 8 8

  12. The mood of the web • Mood annotated blogs • Real-time mood tracking and prediction • MoodViews (2005-2009) • Moodgrapher: follow • Moodteller: predict • Moodsignals: explain • Moodspotter: discover associations • Analyzing ‘old’ data: chronobiology http://www.moodviews.com 8 8

  13. The mood of the web • Mood annotated blogs • Real-time mood tracking and prediction • MoodViews (2005-2009) • Moodgrapher: follow • Moodteller: predict • Moodsignals: explain • Moodspotter: discover associations • Analyzing ‘old’ data: chronobiology http://www.moodviews.com 8 8

  14. The mood of the web Original data versus Trend 2 ratio of blog posts labeled with STRESSED 1.8 • Mood annotated blogs 1.6 • Real-time mood tracking and prediction 1.4 1.2 • MoodViews (2005-2009) 1 0.8 • Moodgrapher: follow 0.6 • Moodteller: predict 0.4 • Moodsignals: explain 0.2 06/03/05 08/01/05 10/01/05 12/01/05 02/01/06 04/01/06 • Moodspotter: discover associations • Analyzing ‘old’ data: chronobiology http://www.moodviews.com 8 8

  15. Ingredients • Search engine technologies • Content extraction • Language technologies • Semistructured data technologies • Scaleable distributed processing 9 9

  16. Development strategy • We are scientists , developers , users at the same time and we have external partners • Agile vs standards? • Let a 1000 flowers bloom? 10 10

  17. vs. 11

  18. Fietstas Text analysis service (NL, EN) Fietstas Fietstas Inspector Fietstas Web API Programmer API Inspect document XMLRPC or REST Python annotations direct document upload documents file by file or in batches Fietstas Sscrape WWW Fietstas web scraper for RSS feeds or sites Fietstas worker Fietstas worker Fietstas worker Stemming, NEN, Stemming, NEN, Stemming, NEN, NER, term cloud NER, term cloud NER, term cloud aggregation, ... aggregation, ... aggregation, ... 12 12

  19. • A look from the lab • Social media as a “societal thermometer” • Many opportunities for public-private collaborations • Infrastructure for supporting these collaborations 13

  20. • Based on joint work with • Krisztian Balog, Wouter Bolsterlee, Breyten Ernsting, Valentin Jijkoun, Fons Laan, Maarten Marx, Gilad Mishne, Christof Monz, Daan Odijk, Ork de Rooij, Manos Tsagkias, Andrei Vishneuski 14

Recommend


More recommend