SlideShare a Scribd company logo
1 of 21
Towards Understanding Crisis Events On
Online Social Networks Through Pictures
IEEE/ACM Conference on Advances in Social Networks
Analysis and Mining (ASONAM), 2017
Prateek Dewan, Anshuman Suri, Varun Bharadhwaj, Aditi Mithal, Ponnurangam Kumaraguru
Precog@IIITD
Indraprastha Institute of Information Technology – Delhi (IIITD)
http://precog.iiitd.edu.in
Who am I?
• PhD student at IIIT-Delhi, India
• 2012 – present
• Masters (Information Security), IIIT-Delhi (2010 – 2012)
• Funded by the Government of India, IIIT-Delhi, IBM, National Internet
eXchange of India (NIXI)…
• Part of Precog@IIITD
• Privacy, eCrime, Online Social Networks, Data Science for Security and Privacy
• Research interests
• Privacy and Security in Online Social Media, Web Security, Machine Learning
• Data Scientist at Apple
2
http://precog.iiitd.edu.in
An example to start…
3
http://precog.iiitd.edu.in
The Human Brain: Images versus text
• Human brain processes images 60,000 times faster than text
4
http://precog.iiitd.edu.in
“A Picture Is Worth A Thousand Words”
• Images are the latest way of communicating on OSNs
• 1.8 billion+ pictures shared on Online Social Networks every day
• Images attract much more attention and engagement as
compared to text
• Tweets with images get 18% more clicks, 150% more retweets
• 93% of most engaging content on Facebook has an image
5
http://precog.iiitd.edu.in
Are we doing enough to "understand" images?
• Most research to analyze social media content focuses on text
• Topics are understood using topic modelling on text
• Sentiment is understood by subjecting textual content to linguistic
techniques
• Is that enough? Does it capture everything?
• Studies related to images are limited to small scale
• Few hundred images manually annotated and analyzed
• What can be done?
• Automated techniques for image summarization using Deep Learning and
Convolutional Neural Networks (CNNs) to scale across large no. of images
• Domain transfer learning: Using existing knowledge in one domain to
understand another domain
• Optical Character Recognition
6
http://precog.iiitd.edu.in
What do we study?
• Crisis event
• Terrorist attacks in Paris, France in November 2015
• Images on Social Networks
• Facebook
• Data collection – Facebook Graph API Search
• #ParisAttacks
• #PrayForParis
7
Unique posts 131,548
Unique users 106,275
Posts with images 75,277
Total images extracted 57,748
Total unique images 15,123
http://precog.iiitd.edu.in
Methodology
• 3-tier pipeline for extracting high level image descriptors
from images
8
Images
Themes
(Inception v3)
Image Sentiment
(DeCAF trained on
SentiBank)
Optical
Character
Recognition
Human
understandable
descriptors
Text Sentiment
(LIWC) +
Topics(TF)
Manual
calibration
Tier 1: Visual Themes
Tier 2: Image Sentiment
Tier 3: Text embedded in images
http://precog.iiitd.edu.in
Tier I: Visual Themes
• ImageNet Large Scale Visual Recognition Challenge (ILSVRC),
2012
• 1.2 million images, 1,000 categories
• Winner: Google’s Inception-v3 (top-1 error: 17.2%)
• 48-layer Deep Convolutional Neural Network
9
http://precog.iiitd.edu.in
Tier I: Visual Themes contd.
• All images labeled using Inception-v3
• Validation:
• Random sample of 2,545 images annotated by 3 human annotators
• 38.87% accuracy (majority voting)
• Manual calibration
• Renamed 7 out of the top 30 (most frequently occurring) labels
• New accuracy: 51.3%
• Why rename? 
10
Bolo Tie
(Inception-v3)
PeaceForParis
(Our dataset)
http://precog.iiitd.edu.in
Tier II: Image Sentiment
• Domain Transfer Learning
• Inception-v3’s last layer retrained using SentiBank
• SentiBank
• Images collected from Flickr using Adjective Noun Pairs (ANPs) as search
query
• ANPs: happy dog, adorable baby, abandoned house
• Weakly labeled dataset of images carrying emotion
• Final training set – 133,108 negative + 305,100 positive sentiment images
• 10-fold random subsampling
• 69.8% accuracy
11
http://precog.iiitd.edu.in
Tier III: Text embedded in images
• Optical Character
Recognition (OCR)
• Tesseract OCR (Python)
• 31,689 images had text
• Manually extracted text
from a random sample of
1,000 images
• Compared with OCR
output using string
similarity metrics
• ~62% accuracy
12
Tesseract output:
No-one thinks that
these people are
representative of
Christians. So why
do so many think
that these people
are representative
of Muslims?
http://precog.iiitd.edu.in
Helix Demo
13
http://precog.iiitd.edu.in
Findings: Top visual themes
14
Label Count Description
Website 12,416 Images of posts, tweets, banners, etc.
Book jacket * 5,383 Posters, banners, etc.
Comic book 3,803 Cartoons, animated posters and memes
Fountain 1,264 Fountain in front of the Louvre museum, other fountains
Envelope * 1,248 Posters, banners, etc.
Suit (clothing) 1,246 People wearing suits, at gatherings etc.
Stage 1,135 Stages during public speeches, mass gathering events, etc.
Candle waxlight 1,021 Lit candles and lamps offering support to victims
Malinois # 995 Police dog that died during the attacks
Scoreboard # 971 Images of sports stadium
http://precog.iiitd.edu.in
Poor quality image content popular on Facebook
15
http://precog.iiitd.edu.in
Image and post text had different topics
• Text embedded in images depicted more negative sentiment
than user generated textual content
16
Text embedded in images User generated text
http://precog.iiitd.edu.in
Findings
• Image sentiment was more positive than text sentiment
17
0
0.1
0.2
0.3
0.4
0.5
0.6
8 24 40 56 72 88 104 120 136 152 168 184 200 216 232 248 264 280
SentimentValue/VolumeFraction
No. of hours after the attacks
Post Text Image Text
Image Volume Fraction
http://precog.iiitd.edu.in
Contrasting sentiment in text and image
18
http://precog.iiitd.edu.in
Contributions
• Insights into the visual side of content during crisis events on
social networks
• Generalizable methodology / pipeline for analyzing large
topical image datasets
19
http://precog.iiitd.edu.in
Limitations
• Object detection technique has limited accuracy
• Retraining is costly; we prefer manual intervention over retraining
• Sentiment portrayed by an image can be subjective
• OCR does not always produce good results
• Missing out on part of the content
20
Thank you!
prateekd@iiitd.ac.in
cerc.iiitd.ac.in

More Related Content

Similar to Understanding Crisis Events Through Social Media Images

M&L 2012 - Scientific Imagery in Higher Education - by Ruth Kerr, Ilaria Merciai
M&L 2012 - Scientific Imagery in Higher Education - by Ruth Kerr, Ilaria MerciaiM&L 2012 - Scientific Imagery in Higher Education - by Ruth Kerr, Ilaria Merciai
M&L 2012 - Scientific Imagery in Higher Education - by Ruth Kerr, Ilaria MerciaiMedia & Learning Conference
 
Digital project planning and pedagogy
Digital project planning and pedagogyDigital project planning and pedagogy
Digital project planning and pedagogylibrarianrafia
 
Promoting and Modeling Digital Citizenship and Responsibility
 Promoting and Modeling Digital Citizenship and Responsibility Promoting and Modeling Digital Citizenship and Responsibility
Promoting and Modeling Digital Citizenship and ResponsibilityE Robertson
 
Digital Literacy Workshop
Digital Literacy Workshop Digital Literacy Workshop
Digital Literacy Workshop Lisa Harris
 
Promoting and modeling digital citizenship and responsibility no wf
 Promoting and modeling digital citizenship and responsibility no wf Promoting and modeling digital citizenship and responsibility no wf
Promoting and modeling digital citizenship and responsibility no wfE Robertson
 
EMMA Summer School - E. Bruno, I. Merciai, M. Tizzani - MOOC Production autho...
EMMA Summer School - E. Bruno, I. Merciai, M. Tizzani - MOOC Production autho...EMMA Summer School - E. Bruno, I. Merciai, M. Tizzani - MOOC Production autho...
EMMA Summer School - E. Bruno, I. Merciai, M. Tizzani - MOOC Production autho...EUmoocs
 
PGCLT(HE) - Supporting students with TEL
PGCLT(HE) - Supporting students with TELPGCLT(HE) - Supporting students with TEL
PGCLT(HE) - Supporting students with TELDr Wayne Barry
 
Shanghai Deep Learning Meetup #1
Shanghai Deep Learning Meetup #1Shanghai Deep Learning Meetup #1
Shanghai Deep Learning Meetup #1Xiaohu ZHU
 
Copyright, E-learning and Digital Literacy: teaching and learning in the digi...
Copyright, E-learning and Digital Literacy: teaching and learning in the digi...Copyright, E-learning and Digital Literacy: teaching and learning in the digi...
Copyright, E-learning and Digital Literacy: teaching and learning in the digi...Jane Secker
 
Mining the Social Web - Lecture 1 - T61.6020 lecture-01-slides
Mining the Social Web - Lecture 1 - T61.6020 lecture-01-slidesMining the Social Web - Lecture 1 - T61.6020 lecture-01-slides
Mining the Social Web - Lecture 1 - T61.6020 lecture-01-slidesMichael Mathioudakis
 
Technology for liberal education: the state of the art
Technology for liberal education: the state of the artTechnology for liberal education: the state of the art
Technology for liberal education: the state of the artBryan Alexander
 
#mytweet via Instagram: Exploring User Behaviour Across Multiple Social Networks
#mytweet via Instagram: Exploring User Behaviour Across Multiple Social Networks#mytweet via Instagram: Exploring User Behaviour Across Multiple Social Networks
#mytweet via Instagram: Exploring User Behaviour Across Multiple Social NetworksBang Hui Lim
 
Social Media in Higher Education - Barriers & Digital Literacy
Social Media in Higher Education - Barriers & Digital LiteracySocial Media in Higher Education - Barriers & Digital Literacy
Social Media in Higher Education - Barriers & Digital LiteracyNigel Robertson
 
Complex Networks: Science, Programming, and Databases
Complex Networks: Science, Programming, and DatabasesComplex Networks: Science, Programming, and Databases
Complex Networks: Science, Programming, and DatabasesS.M. Mahdi Seyednezhad, Ph.D.
 
Lecture 5: Mining, Analysis and Visualisation
Lecture 5: Mining, Analysis and VisualisationLecture 5: Mining, Analysis and Visualisation
Lecture 5: Mining, Analysis and VisualisationMarieke van Erp
 
Digital competence, digital citizen, digital hygiene
Digital competence, digital citizen, digital hygieneDigital competence, digital citizen, digital hygiene
Digital competence, digital citizen, digital hygienePirje Meri
 

Similar to Understanding Crisis Events Through Social Media Images (20)

M&L 2012 - Scientific Imagery in Higher Education - by Ruth Kerr, Ilaria Merciai
M&L 2012 - Scientific Imagery in Higher Education - by Ruth Kerr, Ilaria MerciaiM&L 2012 - Scientific Imagery in Higher Education - by Ruth Kerr, Ilaria Merciai
M&L 2012 - Scientific Imagery in Higher Education - by Ruth Kerr, Ilaria Merciai
 
Digital project planning and pedagogy
Digital project planning and pedagogyDigital project planning and pedagogy
Digital project planning and pedagogy
 
Promoting and Modeling Digital Citizenship and Responsibility
 Promoting and Modeling Digital Citizenship and Responsibility Promoting and Modeling Digital Citizenship and Responsibility
Promoting and Modeling Digital Citizenship and Responsibility
 
Lecture4 Social Web
Lecture4 Social Web Lecture4 Social Web
Lecture4 Social Web
 
#FluxFlow
#FluxFlow#FluxFlow
#FluxFlow
 
Digital Literacy Workshop
Digital Literacy Workshop Digital Literacy Workshop
Digital Literacy Workshop
 
Digital Curation Technology: JHU Summit, October 2015
Digital Curation Technology: JHU Summit, October 2015Digital Curation Technology: JHU Summit, October 2015
Digital Curation Technology: JHU Summit, October 2015
 
Promoting and modeling digital citizenship and responsibility no wf
 Promoting and modeling digital citizenship and responsibility no wf Promoting and modeling digital citizenship and responsibility no wf
Promoting and modeling digital citizenship and responsibility no wf
 
Digital Natives
Digital NativesDigital Natives
Digital Natives
 
EMMA Summer School - E. Bruno, I. Merciai, M. Tizzani - MOOC Production autho...
EMMA Summer School - E. Bruno, I. Merciai, M. Tizzani - MOOC Production autho...EMMA Summer School - E. Bruno, I. Merciai, M. Tizzani - MOOC Production autho...
EMMA Summer School - E. Bruno, I. Merciai, M. Tizzani - MOOC Production autho...
 
PGCLT(HE) - Supporting students with TEL
PGCLT(HE) - Supporting students with TELPGCLT(HE) - Supporting students with TEL
PGCLT(HE) - Supporting students with TEL
 
Shanghai Deep Learning Meetup #1
Shanghai Deep Learning Meetup #1Shanghai Deep Learning Meetup #1
Shanghai Deep Learning Meetup #1
 
Copyright, E-learning and Digital Literacy: teaching and learning in the digi...
Copyright, E-learning and Digital Literacy: teaching and learning in the digi...Copyright, E-learning and Digital Literacy: teaching and learning in the digi...
Copyright, E-learning and Digital Literacy: teaching and learning in the digi...
 
Mining the Social Web - Lecture 1 - T61.6020 lecture-01-slides
Mining the Social Web - Lecture 1 - T61.6020 lecture-01-slidesMining the Social Web - Lecture 1 - T61.6020 lecture-01-slides
Mining the Social Web - Lecture 1 - T61.6020 lecture-01-slides
 
Technology for liberal education: the state of the art
Technology for liberal education: the state of the artTechnology for liberal education: the state of the art
Technology for liberal education: the state of the art
 
#mytweet via Instagram: Exploring User Behaviour Across Multiple Social Networks
#mytweet via Instagram: Exploring User Behaviour Across Multiple Social Networks#mytweet via Instagram: Exploring User Behaviour Across Multiple Social Networks
#mytweet via Instagram: Exploring User Behaviour Across Multiple Social Networks
 
Social Media in Higher Education - Barriers & Digital Literacy
Social Media in Higher Education - Barriers & Digital LiteracySocial Media in Higher Education - Barriers & Digital Literacy
Social Media in Higher Education - Barriers & Digital Literacy
 
Complex Networks: Science, Programming, and Databases
Complex Networks: Science, Programming, and DatabasesComplex Networks: Science, Programming, and Databases
Complex Networks: Science, Programming, and Databases
 
Lecture 5: Mining, Analysis and Visualisation
Lecture 5: Mining, Analysis and VisualisationLecture 5: Mining, Analysis and Visualisation
Lecture 5: Mining, Analysis and Visualisation
 
Digital competence, digital citizen, digital hygiene
Digital competence, digital citizen, digital hygieneDigital competence, digital citizen, digital hygiene
Digital competence, digital citizen, digital hygiene
 

More from IIIT Hyderabad

Responsible & Safe AI Systems at ACM India ROCS at IIT Bombay
Responsible & Safe AI Systems at ACM India ROCS at IIT BombayResponsible & Safe AI Systems at ACM India ROCS at IIT Bombay
Responsible & Safe AI Systems at ACM India ROCS at IIT BombayIIIT Hyderabad
 
International Collaboration: Experiences, Challenges, Success stories
International Collaboration: Experiences, Challenges, Success storiesInternational Collaboration: Experiences, Challenges, Success stories
International Collaboration: Experiences, Challenges, Success storiesIIIT Hyderabad
 
Responsible & Safe AI: #LegalBias #Inconsistency #BiasinLLMs #MultiModalBias
Responsible & Safe AI: #LegalBias #Inconsistency #BiasinLLMs #MultiModalBiasResponsible & Safe AI: #LegalBias #Inconsistency #BiasinLLMs #MultiModalBias
Responsible & Safe AI: #LegalBias #Inconsistency #BiasinLLMs #MultiModalBiasIIIT Hyderabad
 
Identify, Inspect and Intervene Multimodal Fake News
Identify, Inspect and Intervene Multimodal Fake NewsIdentify, Inspect and Intervene Multimodal Fake News
Identify, Inspect and Intervene Multimodal Fake NewsIIIT Hyderabad
 
Data Science for Social Good: #MentalHealth #CodeMix #LegalNLP #AISafety
Data Science for Social Good: #MentalHealth #CodeMix #LegalNLP #AISafetyData Science for Social Good: #MentalHealth #CodeMix #LegalNLP #AISafety
Data Science for Social Good: #MentalHealth #CodeMix #LegalNLP #AISafetyIIIT Hyderabad
 
It is our choices, Harry, that show what we truly are, far more than our abil...
It is our choices, Harry, that show what we truly are, far more than our abil...It is our choices, Harry, that show what we truly are, far more than our abil...
It is our choices, Harry, that show what we truly are, far more than our abil...IIIT Hyderabad
 
Beyond the Surface: A Computational Exploration of Linguistic Ambiguity
Beyond the Surface: A Computational Exploration of Linguistic AmbiguityBeyond the Surface: A Computational Exploration of Linguistic Ambiguity
Beyond the Surface: A Computational Exploration of Linguistic AmbiguityIIIT Hyderabad
 
Data Science for Social Good: #LegalNLP #AlgorithmicBias...
Data Science for Social Good:                      #LegalNLP #AlgorithmicBias...Data Science for Social Good:                      #LegalNLP #AlgorithmicBias...
Data Science for Social Good: #LegalNLP #AlgorithmicBias...IIIT Hyderabad
 
How to Write a (Good) Research Paper
How to Write a (Good) Research Paper How to Write a (Good) Research Paper
How to Write a (Good) Research Paper IIIT Hyderabad
 
Data Science for Social Good: #LegalNLP #AlgorithmicBias
Data Science for Social Good: #LegalNLP #AlgorithmicBiasData Science for Social Good: #LegalNLP #AlgorithmicBias
Data Science for Social Good: #LegalNLP #AlgorithmicBiasIIIT Hyderabad
 
Social Computing Research in India
Social Computing Research in IndiaSocial Computing Research in India
Social Computing Research in IndiaIIIT Hyderabad
 
Social Computing Research in India
Social Computing Research in IndiaSocial Computing Research in India
Social Computing Research in IndiaIIIT Hyderabad
 
Modeling Online User Interactions and their Offline effects on Socio-Technica...
Modeling Online User Interactions and their Offline effects on Socio-Technica...Modeling Online User Interactions and their Offline effects on Socio-Technica...
Modeling Online User Interactions and their Offline effects on Socio-Technica...IIIT Hyderabad
 
Privacy. Winter School on “Topics in Digital Trust”. IIT Bombay
Privacy. Winter School on “Topics in Digital Trust”. IIT BombayPrivacy. Winter School on “Topics in Digital Trust”. IIT Bombay
Privacy. Winter School on “Topics in Digital Trust”. IIT BombayIIIT Hyderabad
 
It is our choices, Harry, that show what we truly are, far more than our abil...
It is our choices, Harry, that show what we truly are, far more than our abil...It is our choices, Harry, that show what we truly are, far more than our abil...
It is our choices, Harry, that show what we truly are, far more than our abil...IIIT Hyderabad
 
It is our choices, Harry, that show what we truly are, far more than our abil...
It is our choices, Harry, that show what we truly are, far more than our abil...It is our choices, Harry, that show what we truly are, far more than our abil...
It is our choices, Harry, that show what we truly are, far more than our abil...IIIT Hyderabad
 
Leveraging Social Media for Financial Advice
Leveraging Social Media for Financial AdviceLeveraging Social Media for Financial Advice
Leveraging Social Media for Financial AdviceIIIT Hyderabad
 
Development of Stress Induction and Detection System to Study its Effect on B...
Development of Stress Induction and Detection System to Study its Effect on B...Development of Stress Induction and Detection System to Study its Effect on B...
Development of Stress Induction and Detection System to Study its Effect on B...IIIT Hyderabad
 
A Framework for Automatic Question Answering in Indian Languages
A Framework for Automatic Question Answering in Indian LanguagesA Framework for Automatic Question Answering in Indian Languages
A Framework for Automatic Question Answering in Indian LanguagesIIIT Hyderabad
 

More from IIIT Hyderabad (20)

Responsible & Safe AI Systems at ACM India ROCS at IIT Bombay
Responsible & Safe AI Systems at ACM India ROCS at IIT BombayResponsible & Safe AI Systems at ACM India ROCS at IIT Bombay
Responsible & Safe AI Systems at ACM India ROCS at IIT Bombay
 
International Collaboration: Experiences, Challenges, Success stories
International Collaboration: Experiences, Challenges, Success storiesInternational Collaboration: Experiences, Challenges, Success stories
International Collaboration: Experiences, Challenges, Success stories
 
Responsible & Safe AI: #LegalBias #Inconsistency #BiasinLLMs #MultiModalBias
Responsible & Safe AI: #LegalBias #Inconsistency #BiasinLLMs #MultiModalBiasResponsible & Safe AI: #LegalBias #Inconsistency #BiasinLLMs #MultiModalBias
Responsible & Safe AI: #LegalBias #Inconsistency #BiasinLLMs #MultiModalBias
 
Identify, Inspect and Intervene Multimodal Fake News
Identify, Inspect and Intervene Multimodal Fake NewsIdentify, Inspect and Intervene Multimodal Fake News
Identify, Inspect and Intervene Multimodal Fake News
 
#ChatGPT #ResponsibleAI
#ChatGPT #ResponsibleAI#ChatGPT #ResponsibleAI
#ChatGPT #ResponsibleAI
 
Data Science for Social Good: #MentalHealth #CodeMix #LegalNLP #AISafety
Data Science for Social Good: #MentalHealth #CodeMix #LegalNLP #AISafetyData Science for Social Good: #MentalHealth #CodeMix #LegalNLP #AISafety
Data Science for Social Good: #MentalHealth #CodeMix #LegalNLP #AISafety
 
It is our choices, Harry, that show what we truly are, far more than our abil...
It is our choices, Harry, that show what we truly are, far more than our abil...It is our choices, Harry, that show what we truly are, far more than our abil...
It is our choices, Harry, that show what we truly are, far more than our abil...
 
Beyond the Surface: A Computational Exploration of Linguistic Ambiguity
Beyond the Surface: A Computational Exploration of Linguistic AmbiguityBeyond the Surface: A Computational Exploration of Linguistic Ambiguity
Beyond the Surface: A Computational Exploration of Linguistic Ambiguity
 
Data Science for Social Good: #LegalNLP #AlgorithmicBias...
Data Science for Social Good:                      #LegalNLP #AlgorithmicBias...Data Science for Social Good:                      #LegalNLP #AlgorithmicBias...
Data Science for Social Good: #LegalNLP #AlgorithmicBias...
 
How to Write a (Good) Research Paper
How to Write a (Good) Research Paper How to Write a (Good) Research Paper
How to Write a (Good) Research Paper
 
Data Science for Social Good: #LegalNLP #AlgorithmicBias
Data Science for Social Good: #LegalNLP #AlgorithmicBiasData Science for Social Good: #LegalNLP #AlgorithmicBias
Data Science for Social Good: #LegalNLP #AlgorithmicBias
 
Social Computing Research in India
Social Computing Research in IndiaSocial Computing Research in India
Social Computing Research in India
 
Social Computing Research in India
Social Computing Research in IndiaSocial Computing Research in India
Social Computing Research in India
 
Modeling Online User Interactions and their Offline effects on Socio-Technica...
Modeling Online User Interactions and their Offline effects on Socio-Technica...Modeling Online User Interactions and their Offline effects on Socio-Technica...
Modeling Online User Interactions and their Offline effects on Socio-Technica...
 
Privacy. Winter School on “Topics in Digital Trust”. IIT Bombay
Privacy. Winter School on “Topics in Digital Trust”. IIT BombayPrivacy. Winter School on “Topics in Digital Trust”. IIT Bombay
Privacy. Winter School on “Topics in Digital Trust”. IIT Bombay
 
It is our choices, Harry, that show what we truly are, far more than our abil...
It is our choices, Harry, that show what we truly are, far more than our abil...It is our choices, Harry, that show what we truly are, far more than our abil...
It is our choices, Harry, that show what we truly are, far more than our abil...
 
It is our choices, Harry, that show what we truly are, far more than our abil...
It is our choices, Harry, that show what we truly are, far more than our abil...It is our choices, Harry, that show what we truly are, far more than our abil...
It is our choices, Harry, that show what we truly are, far more than our abil...
 
Leveraging Social Media for Financial Advice
Leveraging Social Media for Financial AdviceLeveraging Social Media for Financial Advice
Leveraging Social Media for Financial Advice
 
Development of Stress Induction and Detection System to Study its Effect on B...
Development of Stress Induction and Detection System to Study its Effect on B...Development of Stress Induction and Detection System to Study its Effect on B...
Development of Stress Induction and Detection System to Study its Effect on B...
 
A Framework for Automatic Question Answering in Indian Languages
A Framework for Automatic Question Answering in Indian LanguagesA Framework for Automatic Question Answering in Indian Languages
A Framework for Automatic Question Answering in Indian Languages
 

Recently uploaded

An experimental study in using natural admixture as an alternative for chemic...
An experimental study in using natural admixture as an alternative for chemic...An experimental study in using natural admixture as an alternative for chemic...
An experimental study in using natural admixture as an alternative for chemic...Chandu841456
 
Study on Air-Water & Water-Water Heat Exchange in a Finned Tube Exchanger
Study on Air-Water & Water-Water Heat Exchange in a Finned Tube ExchangerStudy on Air-Water & Water-Water Heat Exchange in a Finned Tube Exchanger
Study on Air-Water & Water-Water Heat Exchange in a Finned Tube ExchangerAnamika Sarkar
 
Architect Hassan Khalil Portfolio for 2024
Architect Hassan Khalil Portfolio for 2024Architect Hassan Khalil Portfolio for 2024
Architect Hassan Khalil Portfolio for 2024hassan khalil
 
Indian Dairy Industry Present Status and.ppt
Indian Dairy Industry Present Status and.pptIndian Dairy Industry Present Status and.ppt
Indian Dairy Industry Present Status and.pptMadan Karki
 
Correctly Loading Incremental Data at Scale
Correctly Loading Incremental Data at ScaleCorrectly Loading Incremental Data at Scale
Correctly Loading Incremental Data at ScaleAlluxio, Inc.
 
CCS355 Neural Network & Deep Learning UNIT III notes and Question bank .pdf
CCS355 Neural Network & Deep Learning UNIT III notes and Question bank .pdfCCS355 Neural Network & Deep Learning UNIT III notes and Question bank .pdf
CCS355 Neural Network & Deep Learning UNIT III notes and Question bank .pdfAsst.prof M.Gokilavani
 
Work Experience-Dalton Park.pptxfvvvvvvv
Work Experience-Dalton Park.pptxfvvvvvvvWork Experience-Dalton Park.pptxfvvvvvvv
Work Experience-Dalton Park.pptxfvvvvvvvLewisJB
 
welding defects observed during the welding
welding defects observed during the weldingwelding defects observed during the welding
welding defects observed during the weldingMuhammadUzairLiaqat
 
computer application and construction management
computer application and construction managementcomputer application and construction management
computer application and construction managementMariconPadriquez1
 
Solving The Right Triangles PowerPoint 2.ppt
Solving The Right Triangles PowerPoint 2.pptSolving The Right Triangles PowerPoint 2.ppt
Solving The Right Triangles PowerPoint 2.pptJasonTagapanGulla
 
8251 universal synchronous asynchronous receiver transmitter
8251 universal synchronous asynchronous receiver transmitter8251 universal synchronous asynchronous receiver transmitter
8251 universal synchronous asynchronous receiver transmitterShivangiSharma879191
 
Gurgaon ✡️9711147426✨Call In girls Gurgaon Sector 51 escort service
Gurgaon ✡️9711147426✨Call In girls Gurgaon Sector 51 escort serviceGurgaon ✡️9711147426✨Call In girls Gurgaon Sector 51 escort service
Gurgaon ✡️9711147426✨Call In girls Gurgaon Sector 51 escort servicejennyeacort
 
UNIT III ANALOG ELECTRONICS (BASIC ELECTRONICS)
UNIT III ANALOG ELECTRONICS (BASIC ELECTRONICS)UNIT III ANALOG ELECTRONICS (BASIC ELECTRONICS)
UNIT III ANALOG ELECTRONICS (BASIC ELECTRONICS)Dr SOUNDIRARAJ N
 
IVE Industry Focused Event - Defence Sector 2024
IVE Industry Focused Event - Defence Sector 2024IVE Industry Focused Event - Defence Sector 2024
IVE Industry Focused Event - Defence Sector 2024Mark Billinghurst
 

Recently uploaded (20)

Design and analysis of solar grass cutter.pdf
Design and analysis of solar grass cutter.pdfDesign and analysis of solar grass cutter.pdf
Design and analysis of solar grass cutter.pdf
 
An experimental study in using natural admixture as an alternative for chemic...
An experimental study in using natural admixture as an alternative for chemic...An experimental study in using natural admixture as an alternative for chemic...
An experimental study in using natural admixture as an alternative for chemic...
 
Study on Air-Water & Water-Water Heat Exchange in a Finned Tube Exchanger
Study on Air-Water & Water-Water Heat Exchange in a Finned Tube ExchangerStudy on Air-Water & Water-Water Heat Exchange in a Finned Tube Exchanger
Study on Air-Water & Water-Water Heat Exchange in a Finned Tube Exchanger
 
Architect Hassan Khalil Portfolio for 2024
Architect Hassan Khalil Portfolio for 2024Architect Hassan Khalil Portfolio for 2024
Architect Hassan Khalil Portfolio for 2024
 
Indian Dairy Industry Present Status and.ppt
Indian Dairy Industry Present Status and.pptIndian Dairy Industry Present Status and.ppt
Indian Dairy Industry Present Status and.ppt
 
9953056974 Call Girls In South Ex, Escorts (Delhi) NCR.pdf
9953056974 Call Girls In South Ex, Escorts (Delhi) NCR.pdf9953056974 Call Girls In South Ex, Escorts (Delhi) NCR.pdf
9953056974 Call Girls In South Ex, Escorts (Delhi) NCR.pdf
 
Correctly Loading Incremental Data at Scale
Correctly Loading Incremental Data at ScaleCorrectly Loading Incremental Data at Scale
Correctly Loading Incremental Data at Scale
 
CCS355 Neural Network & Deep Learning UNIT III notes and Question bank .pdf
CCS355 Neural Network & Deep Learning UNIT III notes and Question bank .pdfCCS355 Neural Network & Deep Learning UNIT III notes and Question bank .pdf
CCS355 Neural Network & Deep Learning UNIT III notes and Question bank .pdf
 
Work Experience-Dalton Park.pptxfvvvvvvv
Work Experience-Dalton Park.pptxfvvvvvvvWork Experience-Dalton Park.pptxfvvvvvvv
Work Experience-Dalton Park.pptxfvvvvvvv
 
welding defects observed during the welding
welding defects observed during the weldingwelding defects observed during the welding
welding defects observed during the welding
 
computer application and construction management
computer application and construction managementcomputer application and construction management
computer application and construction management
 
young call girls in Green Park🔝 9953056974 🔝 escort Service
young call girls in Green Park🔝 9953056974 🔝 escort Serviceyoung call girls in Green Park🔝 9953056974 🔝 escort Service
young call girls in Green Park🔝 9953056974 🔝 escort Service
 
POWER SYSTEMS-1 Complete notes examples
POWER SYSTEMS-1 Complete notes  examplesPOWER SYSTEMS-1 Complete notes  examples
POWER SYSTEMS-1 Complete notes examples
 
Solving The Right Triangles PowerPoint 2.ppt
Solving The Right Triangles PowerPoint 2.pptSolving The Right Triangles PowerPoint 2.ppt
Solving The Right Triangles PowerPoint 2.ppt
 
🔝9953056974🔝!!-YOUNG call girls in Rajendra Nagar Escort rvice Shot 2000 nigh...
🔝9953056974🔝!!-YOUNG call girls in Rajendra Nagar Escort rvice Shot 2000 nigh...🔝9953056974🔝!!-YOUNG call girls in Rajendra Nagar Escort rvice Shot 2000 nigh...
🔝9953056974🔝!!-YOUNG call girls in Rajendra Nagar Escort rvice Shot 2000 nigh...
 
8251 universal synchronous asynchronous receiver transmitter
8251 universal synchronous asynchronous receiver transmitter8251 universal synchronous asynchronous receiver transmitter
8251 universal synchronous asynchronous receiver transmitter
 
Gurgaon ✡️9711147426✨Call In girls Gurgaon Sector 51 escort service
Gurgaon ✡️9711147426✨Call In girls Gurgaon Sector 51 escort serviceGurgaon ✡️9711147426✨Call In girls Gurgaon Sector 51 escort service
Gurgaon ✡️9711147426✨Call In girls Gurgaon Sector 51 escort service
 
UNIT III ANALOG ELECTRONICS (BASIC ELECTRONICS)
UNIT III ANALOG ELECTRONICS (BASIC ELECTRONICS)UNIT III ANALOG ELECTRONICS (BASIC ELECTRONICS)
UNIT III ANALOG ELECTRONICS (BASIC ELECTRONICS)
 
IVE Industry Focused Event - Defence Sector 2024
IVE Industry Focused Event - Defence Sector 2024IVE Industry Focused Event - Defence Sector 2024
IVE Industry Focused Event - Defence Sector 2024
 
Exploring_Network_Security_with_JA3_by_Rakesh Seal.pptx
Exploring_Network_Security_with_JA3_by_Rakesh Seal.pptxExploring_Network_Security_with_JA3_by_Rakesh Seal.pptx
Exploring_Network_Security_with_JA3_by_Rakesh Seal.pptx
 

Understanding Crisis Events Through Social Media Images

  • 1. Towards Understanding Crisis Events On Online Social Networks Through Pictures IEEE/ACM Conference on Advances in Social Networks Analysis and Mining (ASONAM), 2017 Prateek Dewan, Anshuman Suri, Varun Bharadhwaj, Aditi Mithal, Ponnurangam Kumaraguru Precog@IIITD Indraprastha Institute of Information Technology – Delhi (IIITD)
  • 2. http://precog.iiitd.edu.in Who am I? • PhD student at IIIT-Delhi, India • 2012 – present • Masters (Information Security), IIIT-Delhi (2010 – 2012) • Funded by the Government of India, IIIT-Delhi, IBM, National Internet eXchange of India (NIXI)… • Part of Precog@IIITD • Privacy, eCrime, Online Social Networks, Data Science for Security and Privacy • Research interests • Privacy and Security in Online Social Media, Web Security, Machine Learning • Data Scientist at Apple 2
  • 4. http://precog.iiitd.edu.in The Human Brain: Images versus text • Human brain processes images 60,000 times faster than text 4
  • 5. http://precog.iiitd.edu.in “A Picture Is Worth A Thousand Words” • Images are the latest way of communicating on OSNs • 1.8 billion+ pictures shared on Online Social Networks every day • Images attract much more attention and engagement as compared to text • Tweets with images get 18% more clicks, 150% more retweets • 93% of most engaging content on Facebook has an image 5
  • 6. http://precog.iiitd.edu.in Are we doing enough to "understand" images? • Most research to analyze social media content focuses on text • Topics are understood using topic modelling on text • Sentiment is understood by subjecting textual content to linguistic techniques • Is that enough? Does it capture everything? • Studies related to images are limited to small scale • Few hundred images manually annotated and analyzed • What can be done? • Automated techniques for image summarization using Deep Learning and Convolutional Neural Networks (CNNs) to scale across large no. of images • Domain transfer learning: Using existing knowledge in one domain to understand another domain • Optical Character Recognition 6
  • 7. http://precog.iiitd.edu.in What do we study? • Crisis event • Terrorist attacks in Paris, France in November 2015 • Images on Social Networks • Facebook • Data collection – Facebook Graph API Search • #ParisAttacks • #PrayForParis 7 Unique posts 131,548 Unique users 106,275 Posts with images 75,277 Total images extracted 57,748 Total unique images 15,123
  • 8. http://precog.iiitd.edu.in Methodology • 3-tier pipeline for extracting high level image descriptors from images 8 Images Themes (Inception v3) Image Sentiment (DeCAF trained on SentiBank) Optical Character Recognition Human understandable descriptors Text Sentiment (LIWC) + Topics(TF) Manual calibration Tier 1: Visual Themes Tier 2: Image Sentiment Tier 3: Text embedded in images
  • 9. http://precog.iiitd.edu.in Tier I: Visual Themes • ImageNet Large Scale Visual Recognition Challenge (ILSVRC), 2012 • 1.2 million images, 1,000 categories • Winner: Google’s Inception-v3 (top-1 error: 17.2%) • 48-layer Deep Convolutional Neural Network 9
  • 10. http://precog.iiitd.edu.in Tier I: Visual Themes contd. • All images labeled using Inception-v3 • Validation: • Random sample of 2,545 images annotated by 3 human annotators • 38.87% accuracy (majority voting) • Manual calibration • Renamed 7 out of the top 30 (most frequently occurring) labels • New accuracy: 51.3% • Why rename?  10 Bolo Tie (Inception-v3) PeaceForParis (Our dataset)
  • 11. http://precog.iiitd.edu.in Tier II: Image Sentiment • Domain Transfer Learning • Inception-v3’s last layer retrained using SentiBank • SentiBank • Images collected from Flickr using Adjective Noun Pairs (ANPs) as search query • ANPs: happy dog, adorable baby, abandoned house • Weakly labeled dataset of images carrying emotion • Final training set – 133,108 negative + 305,100 positive sentiment images • 10-fold random subsampling • 69.8% accuracy 11
  • 12. http://precog.iiitd.edu.in Tier III: Text embedded in images • Optical Character Recognition (OCR) • Tesseract OCR (Python) • 31,689 images had text • Manually extracted text from a random sample of 1,000 images • Compared with OCR output using string similarity metrics • ~62% accuracy 12 Tesseract output: No-one thinks that these people are representative of Christians. So why do so many think that these people are representative of Muslims?
  • 14. http://precog.iiitd.edu.in Findings: Top visual themes 14 Label Count Description Website 12,416 Images of posts, tweets, banners, etc. Book jacket * 5,383 Posters, banners, etc. Comic book 3,803 Cartoons, animated posters and memes Fountain 1,264 Fountain in front of the Louvre museum, other fountains Envelope * 1,248 Posters, banners, etc. Suit (clothing) 1,246 People wearing suits, at gatherings etc. Stage 1,135 Stages during public speeches, mass gathering events, etc. Candle waxlight 1,021 Lit candles and lamps offering support to victims Malinois # 995 Police dog that died during the attacks Scoreboard # 971 Images of sports stadium
  • 15. http://precog.iiitd.edu.in Poor quality image content popular on Facebook 15
  • 16. http://precog.iiitd.edu.in Image and post text had different topics • Text embedded in images depicted more negative sentiment than user generated textual content 16 Text embedded in images User generated text
  • 17. http://precog.iiitd.edu.in Findings • Image sentiment was more positive than text sentiment 17 0 0.1 0.2 0.3 0.4 0.5 0.6 8 24 40 56 72 88 104 120 136 152 168 184 200 216 232 248 264 280 SentimentValue/VolumeFraction No. of hours after the attacks Post Text Image Text Image Volume Fraction
  • 19. http://precog.iiitd.edu.in Contributions • Insights into the visual side of content during crisis events on social networks • Generalizable methodology / pipeline for analyzing large topical image datasets 19
  • 20. http://precog.iiitd.edu.in Limitations • Object detection technique has limited accuracy • Retraining is costly; we prefer manual intervention over retraining • Sentiment portrayed by an image can be subjective • OCR does not always produce good results • Missing out on part of the content 20

Editor's Notes

  1. Whenever you come across such a post on Facebook, what do you notice first? What do you see? Anger in the image? Inference: image > text!
  2. Recently, people have started to look at images on social networks GPUs are cheaper, deep learning is “cool” I thought we should also do something about it
  3. * = renamed # = misinformative
  4. I’d like to go over each one of these to help understand what kind of an impact these can have…