SlideShare a Scribd company logo
1 of 14
MediaEval2012 Social Event Detection Task




Event Detection via LDA for the
   MediaEval2012 SED Task
                 Konstantinos N. Vavliakis
                      Fani A. Tzima
                    Pericles A. Mitkas

  Intelligent Systems and Software Engineering Labgroup
                       http://issel.ee.auth.gr

Information Technologies                              Electrical and Computer
Institutes                                            Engineering Department
Centre for Research and                                  Aristotle University of
Technology - Hellas                                                Thessaloniki

                           Thursday, 4 October 2012
MediaEval2012 Social Event Detection Task



             Social Event Detection at
                 MediaEval 2012
 Goal: Discover social events

 3 Challenges:
   1. Find technical events in Germany
   2. Find all soccer events in Hamburg (Germany)
      and Madrid (Spain)
   3. Find demonstration and protest events of the
      Indignados movement in Madrid


04/10/2012                                                  2
MediaEval2012 Social Event Detection Task



                            Methodology

  Pre-       City                Topic Identification       Event            Event
  processing Classifier                                     Detection        Optimization

   Stemming
      (Porter
     stemmer)
                                                                                Split
    Translate                      Manually Create Topics                      Events
   (using Google                                                              (by location)
     Translate)


   Clean Text         City          Identify      Select      Identify          Merge
    (remove stop   Classifier        Topics      Relevant      Events           Events
     words/html    (tf-idf for      (per city,               (by detecting   (of consecutive
        tags)      each city)      using LDA)
                                                  Topics        peaks)            days)




04/10/2012                                                                               3
MediaEval2012 Social Event Detection Task



                                   Preprocessing
   Clean text by removing html tags and stop words

   Translate non-English words

   Perform stemming using the Porter Stemmer
 E.g.:
Title                             Cleaned Title              English Title               Stemmed
i-wall                            wall                       wall                        wall
2009...
Pallasso trist // Sad Clown       pallasso trist sad clown   clown sad sad clown         clown sad sad clown
Conjunt Monumental de Sant        conjunt monumental         set monumental sant pere    set monument sant pere
Pere de Terrassa                  sant pere terrassa         terrassa                    terrassa
Seagull in the port               seagull port               seagull port                seagul port
Winter doesn't affect the small   winter doesn affect        winter doesn affect small   winter doesn affect small
land of the gnomes - 9/365        small land gnomes          land gnomes                 land gnome
Jan-09                            january                    january                     januari
Tidy chaos - 3/365                tidy chaos                 tidy chaos                  tidi chao
   04/10/2012                                                                                                 4
MediaEval2012 Social Event Detection Task



                  City Classification
5 cities
 TF-IDF values of the terms for each city
 Classified photos according to maximum TF-IDF aggregated value
Users:
 Users can not be in more than 2 cities in the same day
 User statistics
Results:
 4149 non classified photos
 Very good results for city classification, excellent at country level




 04/10/2012                                                               5
MediaEval2012 Social Event Detection Task



                        Topic Identification
                                           Manually Create Topics

        Photos of a                Extract Topics                   Select Relevant
           City            using LDA with Gibbs Sampling                Topics




                      Participation
Concept
                      in Topic
sol                   0.1544
spanish               0.1116
revolution            0.1050
acampada              0.0983
puerta                0.0262
mayo                  0.0243
manifestación         0.0217
….

     04/10/2012                                                                       6
MediaEval2012 Social Event Detection Task


                     Topic Selection
                                 Manually Create Topics

    Photos of a           Extract Topics                  Select Relevant
       City       using LDA with Gibbs Sampling               Topics


 Each photos belongs to many topics
 Select photos containing “indignados” or
  “acampa” and sum their values per topic
 E.g.: PhotoID Topic Participation in                                 Topic   Sum
                                Topic
                                                                       18     456.58
        5776147261     7         0.72                                  49     223.47
        5776147261    14         0.12                                   0      27.13
        5776147261    21         0.08                                   1      24.17
        5776147261     6         0.02                                  22      23.39
        5776147261    25         0.01                            ….
       ….
 04/10/2012                                                                         7
MediaEval2012 Social Event Detection Task



 Event Detection & Optimization
  Event Detection
   Find photos of selected topics
   Count photos per day
   If higher than a threshold add them to a new
    event

  Event Optimization
   Merge events happening in consecutive
    days
   Split events by geolocation distance

04/10/2012                                                 8
MediaEval2012 Social Event Detection Task


         Results - C1: Technical events in Germany
          Precision      Recall      F-Measure      NMI
100                                                               94.9
 90
       80.98                                                           84.58
 80                                                           76.29
                                                                         0.724
 70
                                                                                 63.35
 60                                                                                         0.578
                                                                                    50.98
 50
                         40.52             35.85
 40
               31.1                                25.31
 30                               26.26
                                                       0.16
 20

 10

  0
        Selected/Total    Selected/Total   Selected/Total         Manual            Manual
            Topics:           Topics:          Topics:             Topic             Topic
             2/50              6/50             8/50

      04/10/2012                                                                             9
MediaEval2012 Social Event Detection Task


       Results – C2: Soccer Events in Hamburg/Madrid
          Precision      Recall      F-Measure     NMI                            93.49
100                                                                 93.49
                         86.67             91.21                88.18   90.76 88.18         0.847
 90                                                84
                                  81.78                                     0.85
        75.72 77.67                                     0.768
 80

 70

 60

 50

 40

 30

 20

 10

  0
        Selected/Total    Selected/Total   Selected/Total           Manual         Manual
            Topics:           Topics:          Topics:               Topic          Topic
             1/50             1/100            1/100

      04/10/2012                                                                          10
MediaEval2012 Social Event Detection Task


        Results – C3: Protest Events of Indignados
          Precision      Recall      F-Measure     NMI
100                                                            90.78              90.78
                         90.76             86.59 85.38      88.91               88.91
 90
        88.53                                                          89.83
                84.29             86.11
 80                                                                      73.8
 70

 60

 50

 40
                                                    0.33                                  0.347
 30

 20

 10

  0
        Selected/Total    Selected/Total   Selected/Total       Manual             Manual
            Topics:           Topics:          Topics:           Topic              Topic
            5/100             5/100             3/50

      04/10/2012                                                                          11
MediaEval2012 Social Event Detection Task



                   Conclusions
 Effective and generalized methodology

 The selection of topics is the key

 Topics created by LDA close to manual topic’s results

 Really good precision

 Stemming may improve (slightly) the results

 Problems in “vague” topics


04/10/2012                                                 12
MediaEval2012 Social Event Detection Task



       Relevant and Future Work

 Automatically detect all events from a dataset using
 detected topics

 Dynamic merging of topics

 The concept of important event
 is socially defined -> Personalized detection


04/10/2012                                                13
MediaEval2012 Social Event Detection Task




        Thank You!

                         Email: kvavliak@issel.ee.auth.gr
04/10/2012                                               14

More Related Content

Viewers also liked

Violence Detection in Video by Large Scale Multi-Scale Local Binary Pattern D...
Violence Detection in Video by Large Scale Multi-Scale Local Binary Pattern D...Violence Detection in Video by Large Scale Multi-Scale Local Binary Pattern D...
Violence Detection in Video by Large Scale Multi-Scale Local Binary Pattern D...
MediaEval2012
 
LIG at MediaEval 2012 affect task: use of a generic method
LIG at MediaEval 2012 affect task: use of a generic methodLIG at MediaEval 2012 affect task: use of a generic method
LIG at MediaEval 2012 affect task: use of a generic method
MediaEval2012
 
תחרות אלוף הידע
תחרות אלוף הידעתחרות אלוף הידע
תחרות אלוף הידע
sabal1
 
Brave New Task: Musiclef Multimodal Music Tagging
Brave New Task: Musiclef Multimodal Music TaggingBrave New Task: Musiclef Multimodal Music Tagging
Brave New Task: Musiclef Multimodal Music Tagging
MediaEval2012
 
Search and Hyperlinking Task at MediaEval 2012
Search and Hyperlinking Task at MediaEval 2012Search and Hyperlinking Task at MediaEval 2012
Search and Hyperlinking Task at MediaEval 2012
MediaEval2012
 
DCU Search Runs at MediaEval 2012: Search and Hyperlinking Task
DCU Search Runs at MediaEval 2012: Search and Hyperlinking TaskDCU Search Runs at MediaEval 2012: Search and Hyperlinking Task
DCU Search Runs at MediaEval 2012: Search and Hyperlinking Task
MediaEval2012
 
MediaEval 2012 Opening
MediaEval 2012 OpeningMediaEval 2012 Opening
MediaEval 2012 Opening
MediaEval2012
 
How INRIA identifies Geographic Location of a Video
How INRIA identifies Geographic Location of a VideoHow INRIA identifies Geographic Location of a Video
How INRIA identifies Geographic Location of a Video
MediaEval2012
 
MediaEval 2012 Visual Privacy Task: Privacy and Intelligibility through Pixel...
MediaEval 2012 Visual Privacy Task: Privacy and Intelligibility through Pixel...MediaEval 2012 Visual Privacy Task: Privacy and Intelligibility through Pixel...
MediaEval 2012 Visual Privacy Task: Privacy and Intelligibility through Pixel...
MediaEval2012
 
Violent Scenes Detection with Large, Brute-forced Acoustic and Visual Feature...
Violent Scenes Detection with Large, Brute-forced Acoustic and Visual Feature...Violent Scenes Detection with Large, Brute-forced Acoustic and Visual Feature...
Violent Scenes Detection with Large, Brute-forced Acoustic and Visual Feature...
MediaEval2012
 
The MediaEval 2012 Affect Task: Violent Scenes Detectio
The MediaEval 2012 Affect Task: Violent Scenes DetectioThe MediaEval 2012 Affect Task: Violent Scenes Detectio
The MediaEval 2012 Affect Task: Violent Scenes Detectio
MediaEval2012
 

Viewers also liked (17)

Violence Detection in Video by Large Scale Multi-Scale Local Binary Pattern D...
Violence Detection in Video by Large Scale Multi-Scale Local Binary Pattern D...Violence Detection in Video by Large Scale Multi-Scale Local Binary Pattern D...
Violence Detection in Video by Large Scale Multi-Scale Local Binary Pattern D...
 
LIG at MediaEval 2012 affect task: use of a generic method
LIG at MediaEval 2012 affect task: use of a generic methodLIG at MediaEval 2012 affect task: use of a generic method
LIG at MediaEval 2012 affect task: use of a generic method
 
תחרות אלוף הידע
תחרות אלוף הידעתחרות אלוף הידע
תחרות אלוף הידע
 
John Richards: My Life Lessons As An Entrepreneur
John Richards: My Life Lessons As An EntrepreneurJohn Richards: My Life Lessons As An Entrepreneur
John Richards: My Life Lessons As An Entrepreneur
 
The Deck by Phil Polstra GrrCON2012
The Deck by Phil Polstra GrrCON2012The Deck by Phil Polstra GrrCON2012
The Deck by Phil Polstra GrrCON2012
 
Brave New Task: Musiclef Multimodal Music Tagging
Brave New Task: Musiclef Multimodal Music TaggingBrave New Task: Musiclef Multimodal Music Tagging
Brave New Task: Musiclef Multimodal Music Tagging
 
Search and Hyperlinking Task at MediaEval 2012
Search and Hyperlinking Task at MediaEval 2012Search and Hyperlinking Task at MediaEval 2012
Search and Hyperlinking Task at MediaEval 2012
 
DCU Search Runs at MediaEval 2012: Search and Hyperlinking Task
DCU Search Runs at MediaEval 2012: Search and Hyperlinking TaskDCU Search Runs at MediaEval 2012: Search and Hyperlinking Task
DCU Search Runs at MediaEval 2012: Search and Hyperlinking Task
 
MediaEval 2012 Opening
MediaEval 2012 OpeningMediaEval 2012 Opening
MediaEval 2012 Opening
 
How INRIA identifies Geographic Location of a Video
How INRIA identifies Geographic Location of a VideoHow INRIA identifies Geographic Location of a Video
How INRIA identifies Geographic Location of a Video
 
MediaEval 2012 Visual Privacy Task: Privacy and Intelligibility through Pixel...
MediaEval 2012 Visual Privacy Task: Privacy and Intelligibility through Pixel...MediaEval 2012 Visual Privacy Task: Privacy and Intelligibility through Pixel...
MediaEval 2012 Visual Privacy Task: Privacy and Intelligibility through Pixel...
 
Mentor Strategy Session: Business Plan and Video
Mentor Strategy Session: Business Plan and VideoMentor Strategy Session: Business Plan and Video
Mentor Strategy Session: Business Plan and Video
 
Secrets of Storytelling by Candace Klein
Secrets of Storytelling by Candace KleinSecrets of Storytelling by Candace Klein
Secrets of Storytelling by Candace Klein
 
Thotcon2013
Thotcon2013Thotcon2013
Thotcon2013
 
Live pitch event
Live pitch eventLive pitch event
Live pitch event
 
Violent Scenes Detection with Large, Brute-forced Acoustic and Visual Feature...
Violent Scenes Detection with Large, Brute-forced Acoustic and Visual Feature...Violent Scenes Detection with Large, Brute-forced Acoustic and Visual Feature...
Violent Scenes Detection with Large, Brute-forced Acoustic and Visual Feature...
 
The MediaEval 2012 Affect Task: Violent Scenes Detectio
The MediaEval 2012 Affect Task: Violent Scenes DetectioThe MediaEval 2012 Affect Task: Violent Scenes Detectio
The MediaEval 2012 Affect Task: Violent Scenes Detectio
 

Similar to Event Detection via LDA for the MediaEval2012 SED Task

Eclispe daytoulouse combining the power of eclipse with android_fr_1024_768_s...
Eclispe daytoulouse combining the power of eclipse with android_fr_1024_768_s...Eclispe daytoulouse combining the power of eclipse with android_fr_1024_768_s...
Eclispe daytoulouse combining the power of eclipse with android_fr_1024_768_s...
Mathias Seguy
 
ECIR 2013 Keynote - Time for Events
ECIR 2013 Keynote - Time for EventsECIR 2013 Keynote - Time for Events
ECIR 2013 Keynote - Time for Events
mor
 

Similar to Event Detection via LDA for the MediaEval2012 SED Task (7)

Eclispe daytoulouse combining the power of eclipse with android_fr_1024_768_s...
Eclispe daytoulouse combining the power of eclipse with android_fr_1024_768_s...Eclispe daytoulouse combining the power of eclipse with android_fr_1024_768_s...
Eclispe daytoulouse combining the power of eclipse with android_fr_1024_768_s...
 
ECIR 2013 Keynote - Time for Events
ECIR 2013 Keynote - Time for EventsECIR 2013 Keynote - Time for Events
ECIR 2013 Keynote - Time for Events
 
IntelliGO semantic similarity measure for Gene Ontology annotations
IntelliGO semantic similarity measure for Gene Ontology annotationsIntelliGO semantic similarity measure for Gene Ontology annotations
IntelliGO semantic similarity measure for Gene Ontology annotations
 
Android L and Wear overview
Android L and Wear overviewAndroid L and Wear overview
Android L and Wear overview
 
Android L and So Much More Webinar Slides
Android L and So Much More Webinar SlidesAndroid L and So Much More Webinar Slides
Android L and So Much More Webinar Slides
 
Android Code Camp 2012 - eng
Android Code Camp 2012 - engAndroid Code Camp 2012 - eng
Android Code Camp 2012 - eng
 
Is the Past. Is the Future. Is the Browser.
Is the Past. Is the Future. Is the Browser.Is the Past. Is the Future. Is the Browser.
Is the Past. Is the Future. Is the Browser.
 

More from MediaEval2012

A Multimodal Approach for Video Geocoding
A Multimodal Approach for   Video Geocoding A Multimodal Approach for   Video Geocoding
A Multimodal Approach for Video Geocoding
MediaEval2012
 
CUNI at MediaEval 2012: Search and Hyperlinking Task
CUNI at MediaEval 2012: Search and Hyperlinking TaskCUNI at MediaEval 2012: Search and Hyperlinking Task
CUNI at MediaEval 2012: Search and Hyperlinking Task
MediaEval2012
 
Ghent University-IBBT at MediaEval 2012 Search and Hyperlinking: Semantic Sim...
Ghent University-IBBT at MediaEval 2012 Search and Hyperlinking: Semantic Sim...Ghent University-IBBT at MediaEval 2012 Search and Hyperlinking: Semantic Sim...
Ghent University-IBBT at MediaEval 2012 Search and Hyperlinking: Semantic Sim...
MediaEval2012
 
Brave New Task: User Account Matching
Brave New Task: User Account MatchingBrave New Task: User Account Matching
Brave New Task: User Account Matching
MediaEval2012
 
The CLEF Initiative From 2010 to 2012 and Onwards
The CLEF Initiative From 2010 to 2012 and OnwardsThe CLEF Initiative From 2010 to 2012 and Onwards
The CLEF Initiative From 2010 to 2012 and Onwards
MediaEval2012
 
Overview of MediaEval 2012 Visual Privacy Task
Overview of MediaEval 2012 Visual Privacy TaskOverview of MediaEval 2012 Visual Privacy Task
Overview of MediaEval 2012 Visual Privacy Task
MediaEval2012
 
MediaEval 2012 Visual Privacy Task: Applying Transform-domain Scrambling to A...
MediaEval 2012 Visual Privacy Task: Applying Transform-domain Scrambling to A...MediaEval 2012 Visual Privacy Task: Applying Transform-domain Scrambling to A...
MediaEval 2012 Visual Privacy Task: Applying Transform-domain Scrambling to A...
MediaEval2012
 
Technicolor/INRIA/Imperial College London at the MediaEval 2012 Violent Scene...
Technicolor/INRIA/Imperial College London at the MediaEval 2012 Violent Scene...Technicolor/INRIA/Imperial College London at the MediaEval 2012 Violent Scene...
Technicolor/INRIA/Imperial College London at the MediaEval 2012 Violent Scene...
MediaEval2012
 
NII, Japan at MediaEval 2012 Violent Scenes Detection Affect Task
NII, Japan at MediaEval 2012 Violent Scenes Detection Affect TaskNII, Japan at MediaEval 2012 Violent Scenes Detection Affect Task
NII, Japan at MediaEval 2012 Violent Scenes Detection Affect Task
MediaEval2012
 
ARF @ MediaEval 2012: An Uninformed Approach to Violence Detection in Hollywo...
ARF @ MediaEval 2012: An Uninformed Approach to Violence Detection in Hollywo...ARF @ MediaEval 2012: An Uninformed Approach to Violence Detection in Hollywo...
ARF @ MediaEval 2012: An Uninformed Approach to Violence Detection in Hollywo...
MediaEval2012
 
The Shanghai-Hongkong Team at MediaEval2012: Violent Scene Detection Using Tr...
The Shanghai-Hongkong Team at MediaEval2012: Violent Scene Detection Using Tr...The Shanghai-Hongkong Team at MediaEval2012: Violent Scene Detection Using Tr...
The Shanghai-Hongkong Team at MediaEval2012: Violent Scene Detection Using Tr...
MediaEval2012
 
UNICAMP-UFMG at MediaEval 2012: Genre Tagging Task
UNICAMP-UFMG at MediaEval 2012: Genre Tagging TaskUNICAMP-UFMG at MediaEval 2012: Genre Tagging Task
UNICAMP-UFMG at MediaEval 2012: Genre Tagging Task
MediaEval2012
 
TUD at MediaEval 2012 genre tagging task: Multi-modality video categorization...
TUD at MediaEval 2012 genre tagging task: Multi-modality video categorization...TUD at MediaEval 2012 genre tagging task: Multi-modality video categorization...
TUD at MediaEval 2012 genre tagging task: Multi-modality video categorization...
MediaEval2012
 
ARF @ MediaEval 2012: Multimodal Video Classification
ARF @ MediaEval 2012: Multimodal Video ClassificationARF @ MediaEval 2012: Multimodal Video Classification
ARF @ MediaEval 2012: Multimodal Video Classification
MediaEval2012
 
TUB @ MediaEval 2012 Tagging Task: Feature Selection Methods for Bag-of-(visu...
TUB @ MediaEval 2012 Tagging Task: Feature Selection Methods for Bag-of-(visu...TUB @ MediaEval 2012 Tagging Task: Feature Selection Methods for Bag-of-(visu...
TUB @ MediaEval 2012 Tagging Task: Feature Selection Methods for Bag-of-(visu...
MediaEval2012
 
KIT at MediaEval 2012 – Content–based Genre Classification with Visual Cues
KIT at MediaEval 2012 – Content–based Genre Classification with Visual CuesKIT at MediaEval 2012 – Content–based Genre Classification with Visual Cues
KIT at MediaEval 2012 – Content–based Genre Classification with Visual Cues
MediaEval2012
 
Overview of the MediaEval 2012 Tagging Task
Overview of the MediaEval 2012 Tagging TaskOverview of the MediaEval 2012 Tagging Task
Overview of the MediaEval 2012 Tagging Task
MediaEval2012
 
CUHK System for the Spoken Web Search task at Mediaeval 2012
CUHK System for the Spoken Web Search task at Mediaeval 2012CUHK System for the Spoken Web Search task at Mediaeval 2012
CUHK System for the Spoken Web Search task at Mediaeval 2012
MediaEval2012
 

More from MediaEval2012 (20)

Closing
ClosingClosing
Closing
 
A Multimodal Approach for Video Geocoding
A Multimodal Approach for   Video Geocoding A Multimodal Approach for   Video Geocoding
A Multimodal Approach for Video Geocoding
 
CUNI at MediaEval 2012: Search and Hyperlinking Task
CUNI at MediaEval 2012: Search and Hyperlinking TaskCUNI at MediaEval 2012: Search and Hyperlinking Task
CUNI at MediaEval 2012: Search and Hyperlinking Task
 
Ghent University-IBBT at MediaEval 2012 Search and Hyperlinking: Semantic Sim...
Ghent University-IBBT at MediaEval 2012 Search and Hyperlinking: Semantic Sim...Ghent University-IBBT at MediaEval 2012 Search and Hyperlinking: Semantic Sim...
Ghent University-IBBT at MediaEval 2012 Search and Hyperlinking: Semantic Sim...
 
Brave New Task: User Account Matching
Brave New Task: User Account MatchingBrave New Task: User Account Matching
Brave New Task: User Account Matching
 
The CLEF Initiative From 2010 to 2012 and Onwards
The CLEF Initiative From 2010 to 2012 and OnwardsThe CLEF Initiative From 2010 to 2012 and Onwards
The CLEF Initiative From 2010 to 2012 and Onwards
 
Overview of MediaEval 2012 Visual Privacy Task
Overview of MediaEval 2012 Visual Privacy TaskOverview of MediaEval 2012 Visual Privacy Task
Overview of MediaEval 2012 Visual Privacy Task
 
MediaEval 2012 Visual Privacy Task: Applying Transform-domain Scrambling to A...
MediaEval 2012 Visual Privacy Task: Applying Transform-domain Scrambling to A...MediaEval 2012 Visual Privacy Task: Applying Transform-domain Scrambling to A...
MediaEval 2012 Visual Privacy Task: Applying Transform-domain Scrambling to A...
 
mevd2012 esra_
 mevd2012 esra_ mevd2012 esra_
mevd2012 esra_
 
Technicolor/INRIA/Imperial College London at the MediaEval 2012 Violent Scene...
Technicolor/INRIA/Imperial College London at the MediaEval 2012 Violent Scene...Technicolor/INRIA/Imperial College London at the MediaEval 2012 Violent Scene...
Technicolor/INRIA/Imperial College London at the MediaEval 2012 Violent Scene...
 
NII, Japan at MediaEval 2012 Violent Scenes Detection Affect Task
NII, Japan at MediaEval 2012 Violent Scenes Detection Affect TaskNII, Japan at MediaEval 2012 Violent Scenes Detection Affect Task
NII, Japan at MediaEval 2012 Violent Scenes Detection Affect Task
 
ARF @ MediaEval 2012: An Uninformed Approach to Violence Detection in Hollywo...
ARF @ MediaEval 2012: An Uninformed Approach to Violence Detection in Hollywo...ARF @ MediaEval 2012: An Uninformed Approach to Violence Detection in Hollywo...
ARF @ MediaEval 2012: An Uninformed Approach to Violence Detection in Hollywo...
 
The Shanghai-Hongkong Team at MediaEval2012: Violent Scene Detection Using Tr...
The Shanghai-Hongkong Team at MediaEval2012: Violent Scene Detection Using Tr...The Shanghai-Hongkong Team at MediaEval2012: Violent Scene Detection Using Tr...
The Shanghai-Hongkong Team at MediaEval2012: Violent Scene Detection Using Tr...
 
UNICAMP-UFMG at MediaEval 2012: Genre Tagging Task
UNICAMP-UFMG at MediaEval 2012: Genre Tagging TaskUNICAMP-UFMG at MediaEval 2012: Genre Tagging Task
UNICAMP-UFMG at MediaEval 2012: Genre Tagging Task
 
TUD at MediaEval 2012 genre tagging task: Multi-modality video categorization...
TUD at MediaEval 2012 genre tagging task: Multi-modality video categorization...TUD at MediaEval 2012 genre tagging task: Multi-modality video categorization...
TUD at MediaEval 2012 genre tagging task: Multi-modality video categorization...
 
ARF @ MediaEval 2012: Multimodal Video Classification
ARF @ MediaEval 2012: Multimodal Video ClassificationARF @ MediaEval 2012: Multimodal Video Classification
ARF @ MediaEval 2012: Multimodal Video Classification
 
TUB @ MediaEval 2012 Tagging Task: Feature Selection Methods for Bag-of-(visu...
TUB @ MediaEval 2012 Tagging Task: Feature Selection Methods for Bag-of-(visu...TUB @ MediaEval 2012 Tagging Task: Feature Selection Methods for Bag-of-(visu...
TUB @ MediaEval 2012 Tagging Task: Feature Selection Methods for Bag-of-(visu...
 
KIT at MediaEval 2012 – Content–based Genre Classification with Visual Cues
KIT at MediaEval 2012 – Content–based Genre Classification with Visual CuesKIT at MediaEval 2012 – Content–based Genre Classification with Visual Cues
KIT at MediaEval 2012 – Content–based Genre Classification with Visual Cues
 
Overview of the MediaEval 2012 Tagging Task
Overview of the MediaEval 2012 Tagging TaskOverview of the MediaEval 2012 Tagging Task
Overview of the MediaEval 2012 Tagging Task
 
CUHK System for the Spoken Web Search task at Mediaeval 2012
CUHK System for the Spoken Web Search task at Mediaeval 2012CUHK System for the Spoken Web Search task at Mediaeval 2012
CUHK System for the Spoken Web Search task at Mediaeval 2012
 

Event Detection via LDA for the MediaEval2012 SED Task

  • 1. MediaEval2012 Social Event Detection Task Event Detection via LDA for the MediaEval2012 SED Task Konstantinos N. Vavliakis Fani A. Tzima Pericles A. Mitkas Intelligent Systems and Software Engineering Labgroup http://issel.ee.auth.gr Information Technologies Electrical and Computer Institutes Engineering Department Centre for Research and Aristotle University of Technology - Hellas Thessaloniki Thursday, 4 October 2012
  • 2. MediaEval2012 Social Event Detection Task Social Event Detection at MediaEval 2012  Goal: Discover social events  3 Challenges: 1. Find technical events in Germany 2. Find all soccer events in Hamburg (Germany) and Madrid (Spain) 3. Find demonstration and protest events of the Indignados movement in Madrid 04/10/2012 2
  • 3. MediaEval2012 Social Event Detection Task Methodology Pre- City Topic Identification Event Event processing Classifier Detection Optimization Stemming (Porter stemmer) Split Translate Manually Create Topics Events (using Google (by location) Translate) Clean Text City Identify Select Identify Merge (remove stop Classifier Topics Relevant Events Events words/html (tf-idf for (per city, (by detecting (of consecutive tags) each city) using LDA) Topics peaks) days) 04/10/2012 3
  • 4. MediaEval2012 Social Event Detection Task Preprocessing  Clean text by removing html tags and stop words  Translate non-English words  Perform stemming using the Porter Stemmer  E.g.: Title Cleaned Title English Title Stemmed i-wall wall wall wall 2009... Pallasso trist // Sad Clown pallasso trist sad clown clown sad sad clown clown sad sad clown Conjunt Monumental de Sant conjunt monumental set monumental sant pere set monument sant pere Pere de Terrassa sant pere terrassa terrassa terrassa Seagull in the port seagull port seagull port seagul port Winter doesn't affect the small winter doesn affect winter doesn affect small winter doesn affect small land of the gnomes - 9/365 small land gnomes land gnomes land gnome Jan-09 january january januari Tidy chaos - 3/365 tidy chaos tidy chaos tidi chao 04/10/2012 4
  • 5. MediaEval2012 Social Event Detection Task City Classification 5 cities  TF-IDF values of the terms for each city  Classified photos according to maximum TF-IDF aggregated value Users:  Users can not be in more than 2 cities in the same day  User statistics Results:  4149 non classified photos  Very good results for city classification, excellent at country level 04/10/2012 5
  • 6. MediaEval2012 Social Event Detection Task Topic Identification Manually Create Topics Photos of a Extract Topics Select Relevant City using LDA with Gibbs Sampling Topics Participation Concept in Topic sol 0.1544 spanish 0.1116 revolution 0.1050 acampada 0.0983 puerta 0.0262 mayo 0.0243 manifestación 0.0217 …. 04/10/2012 6
  • 7. MediaEval2012 Social Event Detection Task Topic Selection Manually Create Topics Photos of a Extract Topics Select Relevant City using LDA with Gibbs Sampling Topics  Each photos belongs to many topics  Select photos containing “indignados” or “acampa” and sum their values per topic E.g.: PhotoID Topic Participation in Topic Sum Topic 18 456.58 5776147261 7 0.72 49 223.47 5776147261 14 0.12 0 27.13 5776147261 21 0.08 1 24.17 5776147261 6 0.02 22 23.39 5776147261 25 0.01 …. …. 04/10/2012 7
  • 8. MediaEval2012 Social Event Detection Task Event Detection & Optimization Event Detection  Find photos of selected topics  Count photos per day  If higher than a threshold add them to a new event Event Optimization  Merge events happening in consecutive days  Split events by geolocation distance 04/10/2012 8
  • 9. MediaEval2012 Social Event Detection Task Results - C1: Technical events in Germany Precision Recall F-Measure NMI 100 94.9 90 80.98 84.58 80 76.29 0.724 70 63.35 60 0.578 50.98 50 40.52 35.85 40 31.1 25.31 30 26.26 0.16 20 10 0 Selected/Total Selected/Total Selected/Total Manual Manual Topics: Topics: Topics: Topic Topic 2/50 6/50 8/50 04/10/2012 9
  • 10. MediaEval2012 Social Event Detection Task Results – C2: Soccer Events in Hamburg/Madrid Precision Recall F-Measure NMI 93.49 100 93.49 86.67 91.21 88.18 90.76 88.18 0.847 90 84 81.78 0.85 75.72 77.67 0.768 80 70 60 50 40 30 20 10 0 Selected/Total Selected/Total Selected/Total Manual Manual Topics: Topics: Topics: Topic Topic 1/50 1/100 1/100 04/10/2012 10
  • 11. MediaEval2012 Social Event Detection Task Results – C3: Protest Events of Indignados Precision Recall F-Measure NMI 100 90.78 90.78 90.76 86.59 85.38 88.91 88.91 90 88.53 89.83 84.29 86.11 80 73.8 70 60 50 40 0.33 0.347 30 20 10 0 Selected/Total Selected/Total Selected/Total Manual Manual Topics: Topics: Topics: Topic Topic 5/100 5/100 3/50 04/10/2012 11
  • 12. MediaEval2012 Social Event Detection Task Conclusions  Effective and generalized methodology  The selection of topics is the key  Topics created by LDA close to manual topic’s results  Really good precision  Stemming may improve (slightly) the results  Problems in “vague” topics 04/10/2012 12
  • 13. MediaEval2012 Social Event Detection Task Relevant and Future Work  Automatically detect all events from a dataset using detected topics  Dynamic merging of topics  The concept of important event is socially defined -> Personalized detection 04/10/2012 13
  • 14. MediaEval2012 Social Event Detection Task Thank You! Email: kvavliak@issel.ee.auth.gr 04/10/2012 14