Extracting Media Items from Multiple Social Networks

50 %
50 %
Information about Extracting Media Items from Multiple Social Networks
Technology

Published on October 29, 2012

Author: troncy

Source: slideshare.net

Description

Presentation given at the International Workshop on Socially-Aware Multimedia at ACM Multimedia 2012, October 2012, Nara, Japan

What Fresh Media Are You LookingFor? Extracting Media Items from Multiple Social Networks Giuseppe Rizzo1, Thomas Steiner2, Raphaël Troncy1, Ruben Verborgh3, José Luis Redondo Garcia1 and Rik Van de Walle3 <raphael.troncy@eurecom.fr> / @rtroncy 1 EURECOM, France 2 Google & University Politècnica de Catalunya, Spain 3 IBBT Ghent, Belgium

Conferences and natural disaster 29/10/2012 - International Workshop on Socially-Aware Multimedia at ACM Multimedia 2012, Nara, Japan -2

29/10/2012 - International Workshop on Socially-Aware Multimedia at ACM Multimedia 2012, Nara, Japan -3

29/10/2012 - International Workshop on Socially-Aware Multimedia at ACM Multimedia 2012, Nara, Japan -4

29/10/2012 - International Workshop on Socially-Aware Multimedia at ACM Multimedia 2012, Nara, Japan -5

29/10/2012 - International Workshop on Socially-Aware Multimedia at ACM Multimedia 2012, Nara, Japan -6

Some definitions Media Item: a photo or a video that is shared on a social network Micropost: a text status message that can optionally accompany a media item Social Network: an online service that focuses on building and reflecting social relationships among people sharing interests or activities  Media Sharing Platforms: emphasis on sharing media but blurred boundaries with social networks since users are encouraged to react on media content (like, comment, favorite, etc.) 29/10/2012 - International Workshop on Socially-Aware Multimedia at ACM Multimedia 2012, Nara, Japan -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 applications to host them  Example: Twitter before the introduction of native photo support 29/10/2012 - International Workshop on Socially-Aware Multimedia at ACM Multimedia 2012, Nara, Japan -8

Media Collector (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) 29/10/2012 - International Workshop on Socially-Aware Multimedia at ACM Multimedia 2012, Nara, Japan -9

Deep link Permalink Clean text for NLP processing Aggregate view of ALL social interactions 12 Social Networks29/10/2012 - International Workshop on Socially-Aware Multimedia at ACM Multimedia 2012, Nara, Japan - 10

Media Finder 29/10/2012 - International Workshop on Socially-Aware Multimedia at ACM Multimedia 2012, Nara, Japan - 11

Evaluation (1/3) 9 events occurring between 10 and 19 January 2012  Assad speech, CES Las Vegas, Costa Concordia Disaster, Cut the Rope Launch, Dixville Notch, Free mobile launch, Blackout SOPA, Ubuntu TV launch, Christian Wulff case  448 images + 143 videos  Photo-Sweeper CBIR-based image duplication detection software Dataset heterogeneity:  Leaderboard banner (728x90) to a standard 3.1 mega pixels (2048x1536) cell phone photo … no quadratic bitmaps shrinking  Hard problem!  Best settings for each event, no generic configuration, in order to limit the number of duplicate misses and false positives 29/10/2012 - International Workshop on Socially-Aware Multimedia at ACM Multimedia 2012, Nara, Japan - 12

Evaluation (2/3) User study to compare the relevance and illustrativeness of the media galleries One event: Google IO (“google i/o” + “io12”) http://en.wikipedia.org/wiki/Google_io Three systems:  Media Finder, Twitter Gallery, Teleportd 7 participants (6 male, 1 female) in 2 groups MediaFinder Teleportd Twitter Google i/o 108 (49%) 20 (9%) 96 (44%) io12 69 (37%) 20 (10%) 98 (53%) 29/10/2012 - International Workshop on Socially-Aware Multimedia at ACM Multimedia 2012, Nara, Japan - 13

Evaluation (3/3) Q1: How illustrative this gallery is for this event? Q2: How visually diverse this gallery is for this event? Lickert 7-scale: result http://goo.gl/QzSM6 + http://goo.gl/7ov6Q google i/o io12 relevance Q1 Q2 relevance Q1 Q2Media 0,28 2,35 2,72 0,21 2,05 2,24FinderTeleportd 0,05 0,30 0,37 0,04 0,35 0,59Twitter 0,28 2,64 2,64 0,34 3,44 2,91 29/10/2012 - International Workshop on Socially-Aware Multimedia at ACM Multimedia 2012, Nara, Japan - 14

Demo: Grid view 29/10/2012 - International Workshop on Socially-Aware Multimedia at ACM Multimedia 2012, Nara, Japan - 15

Demo: Timeline view 29/10/2012 - International Workshop on Socially-Aware Multimedia at ACM Multimedia 2012, Nara, Japan - 16

Conclusion Fresh media available on social networks  Ignored by general search engines …  … but ideal for building stories of events of our life Media Server: a NodeJS server collecting media items shared on social networks Media Finder: a client-server architecture that generates views of those media items http://mediafinder.eurecom.fr/ 29/10/2012 - International Workshop on Socially-Aware Multimedia at ACM Multimedia 2012, Nara, Japan - 17

Future Work Image de-duplication:  Simple off-the-shelf tools using color, texture and shape (Ramaiah and Mohan, IEEE RAICS’11) Named Entity Recognition:  NERD: http://nerd.eurecom.fr/ Clustering and Storyfying:  Source and Temporal clustering  Visual clustering  Semantic clustering: using named entities extracted in microposts 29/10/2012 - International Workshop on Socially-Aware Multimedia at ACM Multimedia 2012, Nara, Japan - 18

http://www.slideshare.net/troncy29/10/2012 - International Workshop on Socially-Aware Multimedia at ACM Multimedia 2012, Nara, Japan - 19

Add a comment

Related presentations

Related pages

Extracting Media Items from Multiple Social Networks ...

1. What Fresh Media Are You LookingFor? Extracting Media Items from Multiple Social Networks Giuseppe Rizzo1, Thomas Steiner2 ...
Read more

What Fresh Media Are You Looking For? Extracting Media ...

Extracting Media Items from Multiple Social Networks. by Giuseppe Rizzo, Thomas Steiner, ... Extracting Media Items from Multiple Social Networks, in: ...
Read more

What fresh media are you looking ? for Extracting media ...

... formats of different social networks, while putting media items in correspondence with ... for Extracting media items from multiple social ...
Read more

What Fresh Media Are You Looking For? Retrieving Media ...

spread over multiple social networks. ... task of extracting media from social networks in ... types of support of media items with social networks:
Read more

What Fresh Media Are You Looking For? Extracting Media ...

Extracting Media Items from Multiple Social Networks on ResearchGate, ... One of the problems is that media are spread over multiple social networks.
Read more

What fresh media are you looking for? Extracting media ...

What fresh media are you looking for? Extracting media items from multiple social networks Guiseppe Rizzo, Thomas Steiner, Raphael Troncy, Ruben Verborgh ...
Read more

Patent US20130263018 - Extracting media content from ...

Systems and methods are disclosed for extracting media content from social ... media content items ... social media networks that ...
Read more

Mapping Implicit Processes: Extracting Social Networks ...

... EXTRACTING SOCIAL NETWORKS FROM DIGITAL CORPORAM. H. BealsShef f ield Hallam University@ ... Extracting Media Items from Multiple Social Networks.
Read more

What fresh media are you looking ? for Extracting media ...

One of the problems is that media are spread over multiple social networks. ... These media items can be used for the automatic generation of visual ...
Read more