MediaFinder: Collect, Enrich and Visualize Media Memes Shared by the Crowd

100 %
0 %
Information about MediaFinder: Collect, Enrich and Visualize Media Memes Shared by the Crowd
Technology

Published on May 16, 2013

Author: troncy

Source: slideshare.net

Description

"MediaFinder: Collect, Enrich and Visualize Media Memes Shared by the Crowd", talk given at the 2nd Real Time Analysis and Mining of Social Streams Workshop (RAMSS) colocated with WWW 2013, Rio de Janeiro, Brazil

MediaFinder: Collect, Enrichand Visualize Media MemesShared by the CrowdRaphaël Troncyraphael.troncy@eurecom.fr / @rtroncy

Conferences and natural disaster14/05/2013 Real-Time Analysis and Mining of Social Streams (RAMSS) - Rio de Janeiro - 2

- 314/05/2013 Real-Time Analysis and Mining of Social Streams (RAMSS) - Rio de Janeiro

- 414/05/2013 Real-Time Analysis and Mining of Social Streams (RAMSS) - Rio de Janeiro

- 514/05/2013 Real-Time Analysis and Mining of Social Streams (RAMSS) - Rio de Janeiro

- 614/05/2013 Real-Time Analysis and Mining of Social Streams (RAMSS) - Rio de Janeiro

Social Media: some definitions Media Item: a photo or a video that is shared ona social network Micropost: a text status message that canoptionally accompany a media item Social Network: an online service that focuseson building and reflecting social relationshipsamong people sharing interests or activitiesMedia Sharing Platforms: emphasis on sharing mediabut blurred boundaries with social networks since usersare encouraged to react on media content(like, comment, favorite, etc.)Real-Time Analysis and Mining of Social Streams (RAMSS) - Rio de Janeiro14/05/2013 - 7

Social networks and media items First-order support: Posting requires the inclusion of a media item Example: Flickr, YouTube Second-order support: Possibility to post media items but also text-only messages Example: Facebook Third-order support: No direct support for media items but rely on third party applicationsto host them Example: Twitter before the introduction of native photo supportReal-Time Analysis and Mining of Social Streams (RAMSS) - Rio de Janeiro14/05/2013 - 8

Media Server Composition of media item extractors (12 SNs) Rely on search APIs + a fix 30s timeout window to provide results Fallback on screen scraping when necessary (Twitter ecosystem) Implemented as a NodeJS server Serialize results in a common schema (JSON)Real-Time Analysis and Mining of Social Streams (RAMSS) - Rio de Janeiro14/05/2013 - 9

14/05/2013 Real-Time Analysis and Mining of Social Streams (RAMSS) - Rio de Janeiro - 10Deep linkPermalinkClean text for NLPprocessingAggregate view of ALLsocial interactions12 Social Networks

Media Finder (www2013)14/05/2013 Real-Time Analysis and Mining of Social Streams (RAMSS) - Rio de Janeiro - 11

Media Finder (zooming on media items)14/05/2013 Real-Time Analysis and Mining of Social Streams (RAMSS) - Rio de Janeiro - 12

Media Finder (timeline view)14/05/2013 Real-Time Analysis and Mining of Social Streams (RAMSS) - Rio de Janeiro - 13

Named Entities are Pivotal Standalone softwareGATEStanford CoreNLPTemis Web APIshttp://nerd.eurecom.fr/14/05/2013 Real-Time Analysis and Mining of Social Streams (RAMSS) - Rio de Janeiro - 14

What is NERD?REST API2ontology1UI31 http://nerd.eurecom.fr/ontology2 http://nerd.eurecom.fr/api/application.wadl3 http://nerd.eurecom.frThe NERD ontology has beenintegrated in the NIF project,a EU FP7 in the context of theLOD2: Creating Knowledgeout of Interlinked Data14/05/2013 Real-Time Analysis and Mining of Social Streams (RAMSS) - Rio de Janeiro - 15

NERD REST API14/05/2013 Real-Time Analysis and Mining of Social Streams (RAMSS) - Rio de Janeiro - 16GET,POST,PUT,DELETE/document/user/annotation/{extractor}/extraction/evaluation...JSON/RDF*“entities” : [{“entity”: “Tim Berners-Lee” ,“type”: “Person” ,“uri”: "http://dbpedia.org/resource/Tim_berners_lee",“nerdType”: "http://nerd.eurecom.fr/ontology#Person",“startChar”: 30,“endChar”: 45,“confidence”: 1,“relevance”: 0.5}]Rizzo G., Troncy R. (2012), NERD: A Framework for Unifying Named Entity Recognition and Disambiguation Web ExtractionTools. In: European chapter of the Association for Computational Linguistics (EACL12), Avignon, France.

Media Finder Architecture Media items harvesting using the Media Serverhttp://eventmedia.eurecom.fr/media-server/search/{combined}/{term}https://github.com/vuknje/media-server (@tomayac fork) Image near de-duplicationDCT signature on image and video frame,Hamming distance between image pairs Clustering and disambiguationNamed Entity Extraction using NERDTopic Generation using LDA14/05/2013 Real-Time Analysis and Mining of Social Streams (RAMSS) - Rio de Janeiro - 17

Media Finder (named entities clustering)14/05/2013 Real-Time Analysis and Mining of Social Streams (RAMSS) - Rio de Janeiro - 18

Media Finder (zooming in a cluster)14/05/2013 Real-Time Analysis and Mining of Social Streams (RAMSS) - Rio de Janeiro - 19

Media Finder Live Topic Generation from Event StreamsMeet us at WWW 2013 Demo Sessionhttp://www.youtube.com/watch?v=8iRiwz7cDYY14/05/2013 Real-Time Analysis and Mining of Social Streams (RAMSS) - Rio de Janeiro - 20

Tracking an event: Italian Election Repeated queries over a period of timeWe have tracked and analyzed media posts tagged aselezioni2013 from 2013-02-26 to 2013-03-03Cron job: every 30 minutes over the 6 daysSlice the data in 24 hours slots Research questions:Can we re-create the news headlines? Storyboarding:http://mediafinder.eurecom.fr/story/elezioni201314/05/2013 Real-Time Analysis and Mining of Social Streams (RAMSS) - Rio de Janeiro - 21

Tracking an event: Italian Election Dataset:~16501 microposts containing (duplicate) media items~21087 Named Entities extracted ClusteringNER and LDAGenerate Bag of Entities (BOE) disambiguated with aDBpedia URI Examples:Monti, Bersani, Italia, Berlusconi, Grillo, Stelle14/05/2013 Real-Time Analysis and Mining of Social Streams (RAMSS) - Rio de Janeiro - 22

Tracking an event: Italian Election Tracking and Analyzing The 2013 Italian ElectionTo appear at ESWC 2013 Demo Sessionhttp://www.youtube.com/watch?v=jIMdnwMoWnk14/05/2013 Real-Time Analysis and Mining of Social Streams (RAMSS) - Rio de Janeiro - 23

Take Home Message Media Server / Media Finder:Aggregating fresh social media itemsMaking sense of media collection for video hyper-linking NERD platform for extracting key information Vision: adoption of semantic multimediatechnologies will foster a European market formedia fragment re-purposing and re-selling Sneak preview:Interact with a Kinect and discover enriched hypervideohttp://www.youtube.com/watch?v=4mSC685AG7k14/05/2013 Real-Time Analysis and Mining of Social Streams (RAMSS) - Rio de Janeiro - 24

Credits Vuk Milicic … interaction designer Giuseppe Rizzo … NERD guru José Luis Redondo Garcia … triplification andclustering Thomas Steiner … Media Server original code14/05/2013 Real-Time Analysis and Mining of Social Streams (RAMSS) - Rio de Janeiro - 25

http://www.slideshare.net/troncy14/05/2013 Real-Time Analysis and Mining of Social Streams (RAMSS) - Rio de Janeiro - 26

Add a comment

Related presentations

Presentación que realice en el Evento Nacional de Gobierno Abierto, realizado los ...

In this presentation we will describe our experience developing with a highly dyna...

Presentation to the LITA Forum 7th November 2014 Albuquerque, NM

Un recorrido por los cambios que nos generará el wearabletech en el futuro

Um paralelo entre as novidades & mercado em Wearable Computing e Tecnologias Assis...

Microsoft finally joins the smartwatch and fitness tracker game by introducing the...

Related pages

MediaFinder: Collect, Enrich and Visualize Media Memes ...

MediaFinder: Collect, Enrich and Visualize Media Memes Shared by the Crowd Raphaël Troncy, Vuk Milicic, Giuseppe Rizzo and José Luis Redondo García
Read more

MediaFinder: Collect, Enrich and Visualize Media Memes ...

MediaFinder: Collect, Enrich and Visualize Media Memes Shared by the Crowd
Read more

MediaFinder: collect, enrich and visualize media memes ...

MediaFinder: collect, enrich and visualize media memes shared by the crowd on ResearchGate, the professional network for scientists.
Read more

MediaFinder: Collect, enrich and visualize media memes ...

Home › Publications › MediaFinder: Collect, enrich and visualize media ... ollect, enrich and visualize media memes shared by the crowd}, author ...
Read more

MediaFinder: Collect, enrich and visualize media memes ...

MediaFinder: Collect, enrich and visualize ... , title = {{M}edia{F}inder: {C}ollect, enrich and visualize media memes shared by the crowd ...
Read more

Multimedia Communications Research Presentation

– Enrich events with media ... Event-centric Interfaces for Interacting with Media ... Enrich and Visualize Media Memes shared by the Crowd – MediaFinder:
Read more

Pierre Letessier - Citations - ResearchGate - Share and ...

Citations. Sorted by: Recently ... Fouille au Corps des Media Français: ... MediaFinder: collect, enrich and visualize media memes shared by the crowd .
Read more

NERD: Named Entity Recognition and Disambiguation

MediaFinder: Collect, Enrich and Visualize Media Memes Shared by the Crowd. In ( WWW'13) 2nd International Workshop on Real-Time Analysis and Mining of ...
Read more