SlideShare uma empresa Scribd logo
1 de 16
Detection and Extracting of Emergency
          Knowledge from Twitter Streams

         Bernhard Klein, Xabier Laiseca, Diego Casado-
        Mansilla, Diego Lopez-de-Ipiña and Alejandro Prada
                             Nespral
6th International Conference on Ubiquitous Computing and Ambient Intelligence
     Session 10: Key application domains: eEmergency, eLearning, eTraining
                               5. December, 2012



                                           Social
                                           Awareness
                                           Based
                                           Emergency
                                           Situation
                                           Solver

     UCAmI 2012                     B. Klein                      1/17
Outline


1. Problem Description
2. Research Field
3. Architecture of Analysis Tool
4. Semantic Social Network Analysis
5. Recent Advances
6. Conclusions




  UCAmI 2012             B. Klein     2/17
Objective


   Trends Detection  Event Knowledge Extraction
     ≠ Counting of Keywords
      Aggregation + Interpretation of post content!


   Problems:
        Big data
        Noisy + short posts
        Real-time support




     UCAmI 2012                B. Klein                3/17
Twitter Examples

► Good    examples:

► Bad   examples:




► Crawling     reality:




  UCAmI 2012              B. Klein   4/17
Research Field
                                           • SensePlace2
     • Hacer and Muraki, 2011              • TweetTracker
     • Sudha et al., 2011                  • Twitcident
                                            Emergency
         Corpus Analysis                    Support
                                            Tools



                           Microblogging



   SNA-Techniques                          Clustering-Techniques
• Mendozza et al., 2010
                                           • Becker et al, 2011
                                           • Marcus et al, 2011
                        NLP-Techniques     • Pohl et al, 2012
                    • Sudha et al, 2011
                    • Abel et al, 2011

       UCAmI 2012                            B. Klein              5/17
SABESS Web system




 UCAmI 2012    B. Klein   6/17
Opensource Implementation
              • Emergency message filter based on emergency taxonomy
              • Language filter e.g. english or spanish
              • Slang reduction (punctation + letter repititions)




 UCAmI 2012                B. Klein                       7/17
Social Network Analysis

► Objective:   Filtering after tweet credibility




  UCAmI 2012                B. Klein               8/17
Observed Problems

   “Slow” Graph Calculations
     Replace   betweeness centrality with user data
       a) followers count ~ influence
       b) friend count ~ knowledge access
       c) number of posts ~ experience


   “Sparse” Social Network
     Replace  SNA with Sentiment Analysis:
       Punctation-, letter- and word repititions
        Tweet credibility < Informative tweet!
          (see also Sudha et al., 2011)



    UCAmI 2012                            B. Klein     9/17
Natural language procesing

► Objective:   Content enrichment




                        • Big Improvement with “slang reduction” !!

  UCAmI 2012              B. Klein                         10/17
Other Knowledge Sources

   Hierarchical Knowledge Structure
    1. Textual location
       a) Named Entity Location
       b) Regular Expression e.g. address
          (Requires reverse coding!)
    2. Tweet metadata
       a) GPS tagged tweets
       b) Place tagged tweets
          (Author location can be different!)
    3. User profile data
       a) Home location                    Increasing reliability!



    UCAmI 2012                   B. Klein                  11/17
Recent Advances: Event Detection

► Objective:     Group tweets into emergency events

   How to describe an emergency event?
       Emergency type, location (range), time (progress),
        person/organization data, text descriptions, number of
        tweets
       Global reporting standard “Common Alert Protocol”.

   Example:




    UCAmI 2012                 B. Klein               12/17
Recent Advances: Clustering

► Incremental         DBSCAN

                            SANDY HURRICANE RELIEF VOLUNTEER EFFORTS
                            SANDY HURRICANE VICTIMS VOLUNTEER
                            SANDY HURRICANE VICTIMS VOLUNTEER EFFORT GRASSROOTS
                            SANDY HURRICANE VICTIMS VOLUNTEER NEWS EFFORT GRASSROOTS
Sandy, 180                  SANDY HURRICANE VICTIMS POLICE
Fukuschima, 170             SANDY HURRICANE VICTIMS RELIEF
….                          SANDY HURRICANE VICTIMS             Locations:
Ambulance, 80               SANDY HURRICANE VICTIMS RELIEF DISASTER PrincetonHall
                                                                e.g.
…..                         SANDY HURRICANE RELIEF
                            SANDY HURRICANE RELIEF
                            SANDY HURRICANE RELIEF DISASTER
                            SANDY VOLUNTEER

Online
                                                                        Conversations:
Dictionary                                                              ConversationID=83
                  Hashtags:
                  #TylerPerryFire
                                           Attachments:
                                           http://t.co/kqF7Xy8t




    UCAmI 2012                             B. Klein                                13/17
Common Alert Protocol

  Whenever clusters become modified,
  generate new alert message??
                                            Alert



                                CAP
                                Info
                                            Place




                                            Urls,
                                            Figs
      Cluster of tweets


 UCAmI 2012                      B. Klein           14/17
Conclusions

   Real-time analysis of noisy tweets
    ► Big data problem, 2 phase analysis
        Emergency message filtering
        Slang and language filtering
    ► Semantic Social Network Analysis
        POS/Noun tags, NER/Location tags
        Community centrality/follower count tags
    ► Tweet clustering
        Group tweets after hashtags, attachments and
         conversations
        Group tweets after emergency specific keywords
    ► Common Alert Protocol

    UCAmI 2012              B. Klein              15/17
Contact:       Bernhard Klein,
                     Email: bernhard.klein@deusto.es
                     Deusto Intitute of Technology,
                     University of Deusto,
 th International Conference on Ubiquitous Computing and Ambient Intelligence
6
                     Avda. Universidades, 24 | 48007 Bilbao |
       Session 10: Key application domains: eEmergency, eLearning, eTraining
                     Spain        5. December, 2012




     UCAmI 2012                    B. Klein                    16/17

Mais conteúdo relacionado

Semelhante a UCAmI 2012 - Detection and Extracting of Emergency Knowledge from Twitter Streams

From Research to Applications: What Can We Extract with Social Media Sensing?
From Research to Applications: What Can We Extract with Social Media Sensing?From Research to Applications: What Can We Extract with Social Media Sensing?
From Research to Applications: What Can We Extract with Social Media Sensing?Yiannis Kompatsiaris
 
Identifying and Responding to Emerging Technologies
Identifying and Responding to Emerging TechnologiesIdentifying and Responding to Emerging Technologies
Identifying and Responding to Emerging Technologieslisbk
 
A Virtuous Cycle of Semantics and Participation
A Virtuous Cycle of Semantics and ParticipationA Virtuous Cycle of Semantics and Participation
A Virtuous Cycle of Semantics and ParticipationDavide Eynard
 
"AI" for Blockchain Security (Case Study: Cosmos)
"AI" for Blockchain Security (Case Study: Cosmos)"AI" for Blockchain Security (Case Study: Cosmos)
"AI" for Blockchain Security (Case Study: Cosmos)npinto
 
Open Science Data Cloud - CCA 11
Open Science Data Cloud - CCA 11Open Science Data Cloud - CCA 11
Open Science Data Cloud - CCA 11Robert Grossman
 
Module 1 - Data Around Us .pptx
Module 1 - Data Around Us .pptxModule 1 - Data Around Us .pptx
Module 1 - Data Around Us .pptxesta2310819
 
Evolution of Open at University of Michigan
Evolution of Open at University of MichiganEvolution of Open at University of Michigan
Evolution of Open at University of MichiganKathleen Ludewig Omollo
 
NYAI #27: Cognitive Architecture & Natural Language Processing w/ Dr. Catheri...
NYAI #27: Cognitive Architecture & Natural Language Processing w/ Dr. Catheri...NYAI #27: Cognitive Architecture & Natural Language Processing w/ Dr. Catheri...
NYAI #27: Cognitive Architecture & Natural Language Processing w/ Dr. Catheri...Maryam Farooq
 
CSCW in Times of Social Media
CSCW in Times of Social MediaCSCW in Times of Social Media
CSCW in Times of Social MediaHendrik Drachsler
 
Shaping future research environments: digital challenges and opportunities
Shaping future research environments: digital challenges and opportunitiesShaping future research environments: digital challenges and opportunities
Shaping future research environments: digital challenges and opportunitiesJisc
 
Everbridge Webinar - Ten Years After 9/11
Everbridge Webinar - Ten Years After 9/11Everbridge Webinar - Ten Years After 9/11
Everbridge Webinar - Ten Years After 9/11Everbridge, Inc.
 
May 2009
May 2009May 2009
May 2009linioti
 
Content Architecture for Rapid Knowledge Reuse-congility2011
Content Architecture for Rapid Knowledge Reuse-congility2011Content Architecture for Rapid Knowledge Reuse-congility2011
Content Architecture for Rapid Knowledge Reuse-congility2011Don Day
 
ACM ICPC Regional Finals Talk re: drop.io, privacy, entrepreneurship by sam l...
ACM ICPC Regional Finals Talk re: drop.io, privacy, entrepreneurship by sam l...ACM ICPC Regional Finals Talk re: drop.io, privacy, entrepreneurship by sam l...
ACM ICPC Regional Finals Talk re: drop.io, privacy, entrepreneurship by sam l...sam lessin
 
Future of AI: Blockchain and Deep Learning
Future of AI: Blockchain and Deep LearningFuture of AI: Blockchain and Deep Learning
Future of AI: Blockchain and Deep LearningMelanie Swan
 
ACS Summer Institute - Emerging Roles of Librarians - 14_0731
ACS Summer Institute - Emerging Roles of Librarians - 14_0731ACS Summer Institute - Emerging Roles of Librarians - 14_0731
ACS Summer Institute - Emerging Roles of Librarians - 14_0731jeffreylancaster
 
Credibility and Relevance of User-Generated Content on Crisis Events
Credibility and Relevance of User-Generated Content on Crisis EventsCredibility and Relevance of User-Generated Content on Crisis Events
Credibility and Relevance of User-Generated Content on Crisis Eventsfoostermann
 
Planning and Managing Digital Library & Archive Projects
Planning and Managing Digital Library & Archive ProjectsPlanning and Managing Digital Library & Archive Projects
Planning and Managing Digital Library & Archive Projectsac2182
 
ICRH Winter Institute Strand 4 Day 1 - Building Narratives with Digital Objects
ICRH Winter Institute Strand 4 Day 1 - Building Narratives with Digital ObjectsICRH Winter Institute Strand 4 Day 1 - Building Narratives with Digital Objects
ICRH Winter Institute Strand 4 Day 1 - Building Narratives with Digital ObjectsShawn Day
 

Semelhante a UCAmI 2012 - Detection and Extracting of Emergency Knowledge from Twitter Streams (20)

From Research to Applications: What Can We Extract with Social Media Sensing?
From Research to Applications: What Can We Extract with Social Media Sensing?From Research to Applications: What Can We Extract with Social Media Sensing?
From Research to Applications: What Can We Extract with Social Media Sensing?
 
Identifying and Responding to Emerging Technologies
Identifying and Responding to Emerging TechnologiesIdentifying and Responding to Emerging Technologies
Identifying and Responding to Emerging Technologies
 
A Virtuous Cycle of Semantics and Participation
A Virtuous Cycle of Semantics and ParticipationA Virtuous Cycle of Semantics and Participation
A Virtuous Cycle of Semantics and Participation
 
"AI" for Blockchain Security (Case Study: Cosmos)
"AI" for Blockchain Security (Case Study: Cosmos)"AI" for Blockchain Security (Case Study: Cosmos)
"AI" for Blockchain Security (Case Study: Cosmos)
 
Open Science Data Cloud - CCA 11
Open Science Data Cloud - CCA 11Open Science Data Cloud - CCA 11
Open Science Data Cloud - CCA 11
 
Module 1 - Data Around Us .pptx
Module 1 - Data Around Us .pptxModule 1 - Data Around Us .pptx
Module 1 - Data Around Us .pptx
 
Evolution of Open at University of Michigan
Evolution of Open at University of MichiganEvolution of Open at University of Michigan
Evolution of Open at University of Michigan
 
NYAI #27: Cognitive Architecture & Natural Language Processing w/ Dr. Catheri...
NYAI #27: Cognitive Architecture & Natural Language Processing w/ Dr. Catheri...NYAI #27: Cognitive Architecture & Natural Language Processing w/ Dr. Catheri...
NYAI #27: Cognitive Architecture & Natural Language Processing w/ Dr. Catheri...
 
CSCW in Times of Social Media
CSCW in Times of Social MediaCSCW in Times of Social Media
CSCW in Times of Social Media
 
Shaping future research environments: digital challenges and opportunities
Shaping future research environments: digital challenges and opportunitiesShaping future research environments: digital challenges and opportunities
Shaping future research environments: digital challenges and opportunities
 
Everbridge Webinar - Ten Years After 9/11
Everbridge Webinar - Ten Years After 9/11Everbridge Webinar - Ten Years After 9/11
Everbridge Webinar - Ten Years After 9/11
 
May 2009
May 2009May 2009
May 2009
 
Content Architecture for Rapid Knowledge Reuse-congility2011
Content Architecture for Rapid Knowledge Reuse-congility2011Content Architecture for Rapid Knowledge Reuse-congility2011
Content Architecture for Rapid Knowledge Reuse-congility2011
 
ACM ICPC Regional Finals Talk re: drop.io, privacy, entrepreneurship by sam l...
ACM ICPC Regional Finals Talk re: drop.io, privacy, entrepreneurship by sam l...ACM ICPC Regional Finals Talk re: drop.io, privacy, entrepreneurship by sam l...
ACM ICPC Regional Finals Talk re: drop.io, privacy, entrepreneurship by sam l...
 
Future of AI: Blockchain and Deep Learning
Future of AI: Blockchain and Deep LearningFuture of AI: Blockchain and Deep Learning
Future of AI: Blockchain and Deep Learning
 
The Commons
The CommonsThe Commons
The Commons
 
ACS Summer Institute - Emerging Roles of Librarians - 14_0731
ACS Summer Institute - Emerging Roles of Librarians - 14_0731ACS Summer Institute - Emerging Roles of Librarians - 14_0731
ACS Summer Institute - Emerging Roles of Librarians - 14_0731
 
Credibility and Relevance of User-Generated Content on Crisis Events
Credibility and Relevance of User-Generated Content on Crisis EventsCredibility and Relevance of User-Generated Content on Crisis Events
Credibility and Relevance of User-Generated Content on Crisis Events
 
Planning and Managing Digital Library & Archive Projects
Planning and Managing Digital Library & Archive ProjectsPlanning and Managing Digital Library & Archive Projects
Planning and Managing Digital Library & Archive Projects
 
ICRH Winter Institute Strand 4 Day 1 - Building Narratives with Digital Objects
ICRH Winter Institute Strand 4 Day 1 - Building Narratives with Digital ObjectsICRH Winter Institute Strand 4 Day 1 - Building Narratives with Digital Objects
ICRH Winter Institute Strand 4 Day 1 - Building Narratives with Digital Objects
 

Último

TeamStation AI System Report LATAM IT Salaries 2024
TeamStation AI System Report LATAM IT Salaries 2024TeamStation AI System Report LATAM IT Salaries 2024
TeamStation AI System Report LATAM IT Salaries 2024Lonnie McRorey
 
Unleash Your Potential - Namagunga Girls Coding Club
Unleash Your Potential - Namagunga Girls Coding ClubUnleash Your Potential - Namagunga Girls Coding Club
Unleash Your Potential - Namagunga Girls Coding ClubKalema Edgar
 
Advanced Test Driven-Development @ php[tek] 2024
Advanced Test Driven-Development @ php[tek] 2024Advanced Test Driven-Development @ php[tek] 2024
Advanced Test Driven-Development @ php[tek] 2024Scott Keck-Warren
 
Connect Wave/ connectwave Pitch Deck Presentation
Connect Wave/ connectwave Pitch Deck PresentationConnect Wave/ connectwave Pitch Deck Presentation
Connect Wave/ connectwave Pitch Deck PresentationSlibray Presentation
 
SAP Build Work Zone - Overview L2-L3.pptx
SAP Build Work Zone - Overview L2-L3.pptxSAP Build Work Zone - Overview L2-L3.pptx
SAP Build Work Zone - Overview L2-L3.pptxNavinnSomaal
 
Powerpoint exploring the locations used in television show Time Clash
Powerpoint exploring the locations used in television show Time ClashPowerpoint exploring the locations used in television show Time Clash
Powerpoint exploring the locations used in television show Time Clashcharlottematthew16
 
Anypoint Exchange: It’s Not Just a Repo!
Anypoint Exchange: It’s Not Just a Repo!Anypoint Exchange: It’s Not Just a Repo!
Anypoint Exchange: It’s Not Just a Repo!Manik S Magar
 
Transcript: New from BookNet Canada for 2024: BNC CataList - Tech Forum 2024
Transcript: New from BookNet Canada for 2024: BNC CataList - Tech Forum 2024Transcript: New from BookNet Canada for 2024: BNC CataList - Tech Forum 2024
Transcript: New from BookNet Canada for 2024: BNC CataList - Tech Forum 2024BookNet Canada
 
TrustArc Webinar - How to Build Consumer Trust Through Data Privacy
TrustArc Webinar - How to Build Consumer Trust Through Data PrivacyTrustArc Webinar - How to Build Consumer Trust Through Data Privacy
TrustArc Webinar - How to Build Consumer Trust Through Data PrivacyTrustArc
 
How to write a Business Continuity Plan
How to write a Business Continuity PlanHow to write a Business Continuity Plan
How to write a Business Continuity PlanDatabarracks
 
WordPress Websites for Engineers: Elevate Your Brand
WordPress Websites for Engineers: Elevate Your BrandWordPress Websites for Engineers: Elevate Your Brand
WordPress Websites for Engineers: Elevate Your Brandgvaughan
 
DevoxxFR 2024 Reproducible Builds with Apache Maven
DevoxxFR 2024 Reproducible Builds with Apache MavenDevoxxFR 2024 Reproducible Builds with Apache Maven
DevoxxFR 2024 Reproducible Builds with Apache MavenHervé Boutemy
 
Hyperautomation and AI/ML: A Strategy for Digital Transformation Success.pdf
Hyperautomation and AI/ML: A Strategy for Digital Transformation Success.pdfHyperautomation and AI/ML: A Strategy for Digital Transformation Success.pdf
Hyperautomation and AI/ML: A Strategy for Digital Transformation Success.pdfPrecisely
 
Human Factors of XR: Using Human Factors to Design XR Systems
Human Factors of XR: Using Human Factors to Design XR SystemsHuman Factors of XR: Using Human Factors to Design XR Systems
Human Factors of XR: Using Human Factors to Design XR SystemsMark Billinghurst
 
Vertex AI Gemini Prompt Engineering Tips
Vertex AI Gemini Prompt Engineering TipsVertex AI Gemini Prompt Engineering Tips
Vertex AI Gemini Prompt Engineering TipsMiki Katsuragi
 
Designing IA for AI - Information Architecture Conference 2024
Designing IA for AI - Information Architecture Conference 2024Designing IA for AI - Information Architecture Conference 2024
Designing IA for AI - Information Architecture Conference 2024Enterprise Knowledge
 
Commit 2024 - Secret Management made easy
Commit 2024 - Secret Management made easyCommit 2024 - Secret Management made easy
Commit 2024 - Secret Management made easyAlfredo García Lavilla
 
H2O.ai CEO/Founder: Sri Ambati Keynote at Wells Fargo Day
H2O.ai CEO/Founder: Sri Ambati Keynote at Wells Fargo DayH2O.ai CEO/Founder: Sri Ambati Keynote at Wells Fargo Day
H2O.ai CEO/Founder: Sri Ambati Keynote at Wells Fargo DaySri Ambati
 
Search Engine Optimization SEO PDF for 2024.pdf
Search Engine Optimization SEO PDF for 2024.pdfSearch Engine Optimization SEO PDF for 2024.pdf
Search Engine Optimization SEO PDF for 2024.pdfRankYa
 

Último (20)

TeamStation AI System Report LATAM IT Salaries 2024
TeamStation AI System Report LATAM IT Salaries 2024TeamStation AI System Report LATAM IT Salaries 2024
TeamStation AI System Report LATAM IT Salaries 2024
 
Unleash Your Potential - Namagunga Girls Coding Club
Unleash Your Potential - Namagunga Girls Coding ClubUnleash Your Potential - Namagunga Girls Coding Club
Unleash Your Potential - Namagunga Girls Coding Club
 
Advanced Test Driven-Development @ php[tek] 2024
Advanced Test Driven-Development @ php[tek] 2024Advanced Test Driven-Development @ php[tek] 2024
Advanced Test Driven-Development @ php[tek] 2024
 
Connect Wave/ connectwave Pitch Deck Presentation
Connect Wave/ connectwave Pitch Deck PresentationConnect Wave/ connectwave Pitch Deck Presentation
Connect Wave/ connectwave Pitch Deck Presentation
 
SAP Build Work Zone - Overview L2-L3.pptx
SAP Build Work Zone - Overview L2-L3.pptxSAP Build Work Zone - Overview L2-L3.pptx
SAP Build Work Zone - Overview L2-L3.pptx
 
Powerpoint exploring the locations used in television show Time Clash
Powerpoint exploring the locations used in television show Time ClashPowerpoint exploring the locations used in television show Time Clash
Powerpoint exploring the locations used in television show Time Clash
 
Anypoint Exchange: It’s Not Just a Repo!
Anypoint Exchange: It’s Not Just a Repo!Anypoint Exchange: It’s Not Just a Repo!
Anypoint Exchange: It’s Not Just a Repo!
 
Transcript: New from BookNet Canada for 2024: BNC CataList - Tech Forum 2024
Transcript: New from BookNet Canada for 2024: BNC CataList - Tech Forum 2024Transcript: New from BookNet Canada for 2024: BNC CataList - Tech Forum 2024
Transcript: New from BookNet Canada for 2024: BNC CataList - Tech Forum 2024
 
TrustArc Webinar - How to Build Consumer Trust Through Data Privacy
TrustArc Webinar - How to Build Consumer Trust Through Data PrivacyTrustArc Webinar - How to Build Consumer Trust Through Data Privacy
TrustArc Webinar - How to Build Consumer Trust Through Data Privacy
 
How to write a Business Continuity Plan
How to write a Business Continuity PlanHow to write a Business Continuity Plan
How to write a Business Continuity Plan
 
DMCC Future of Trade Web3 - Special Edition
DMCC Future of Trade Web3 - Special EditionDMCC Future of Trade Web3 - Special Edition
DMCC Future of Trade Web3 - Special Edition
 
WordPress Websites for Engineers: Elevate Your Brand
WordPress Websites for Engineers: Elevate Your BrandWordPress Websites for Engineers: Elevate Your Brand
WordPress Websites for Engineers: Elevate Your Brand
 
DevoxxFR 2024 Reproducible Builds with Apache Maven
DevoxxFR 2024 Reproducible Builds with Apache MavenDevoxxFR 2024 Reproducible Builds with Apache Maven
DevoxxFR 2024 Reproducible Builds with Apache Maven
 
Hyperautomation and AI/ML: A Strategy for Digital Transformation Success.pdf
Hyperautomation and AI/ML: A Strategy for Digital Transformation Success.pdfHyperautomation and AI/ML: A Strategy for Digital Transformation Success.pdf
Hyperautomation and AI/ML: A Strategy for Digital Transformation Success.pdf
 
Human Factors of XR: Using Human Factors to Design XR Systems
Human Factors of XR: Using Human Factors to Design XR SystemsHuman Factors of XR: Using Human Factors to Design XR Systems
Human Factors of XR: Using Human Factors to Design XR Systems
 
Vertex AI Gemini Prompt Engineering Tips
Vertex AI Gemini Prompt Engineering TipsVertex AI Gemini Prompt Engineering Tips
Vertex AI Gemini Prompt Engineering Tips
 
Designing IA for AI - Information Architecture Conference 2024
Designing IA for AI - Information Architecture Conference 2024Designing IA for AI - Information Architecture Conference 2024
Designing IA for AI - Information Architecture Conference 2024
 
Commit 2024 - Secret Management made easy
Commit 2024 - Secret Management made easyCommit 2024 - Secret Management made easy
Commit 2024 - Secret Management made easy
 
H2O.ai CEO/Founder: Sri Ambati Keynote at Wells Fargo Day
H2O.ai CEO/Founder: Sri Ambati Keynote at Wells Fargo DayH2O.ai CEO/Founder: Sri Ambati Keynote at Wells Fargo Day
H2O.ai CEO/Founder: Sri Ambati Keynote at Wells Fargo Day
 
Search Engine Optimization SEO PDF for 2024.pdf
Search Engine Optimization SEO PDF for 2024.pdfSearch Engine Optimization SEO PDF for 2024.pdf
Search Engine Optimization SEO PDF for 2024.pdf
 

UCAmI 2012 - Detection and Extracting of Emergency Knowledge from Twitter Streams

  • 1. Detection and Extracting of Emergency Knowledge from Twitter Streams Bernhard Klein, Xabier Laiseca, Diego Casado- Mansilla, Diego Lopez-de-Ipiña and Alejandro Prada Nespral 6th International Conference on Ubiquitous Computing and Ambient Intelligence Session 10: Key application domains: eEmergency, eLearning, eTraining 5. December, 2012 Social Awareness Based Emergency Situation Solver UCAmI 2012 B. Klein 1/17
  • 2. Outline 1. Problem Description 2. Research Field 3. Architecture of Analysis Tool 4. Semantic Social Network Analysis 5. Recent Advances 6. Conclusions UCAmI 2012 B. Klein 2/17
  • 3. Objective  Trends Detection  Event Knowledge Extraction ≠ Counting of Keywords  Aggregation + Interpretation of post content!  Problems:  Big data  Noisy + short posts  Real-time support UCAmI 2012 B. Klein 3/17
  • 4. Twitter Examples ► Good examples: ► Bad examples: ► Crawling reality: UCAmI 2012 B. Klein 4/17
  • 5. Research Field • SensePlace2 • Hacer and Muraki, 2011 • TweetTracker • Sudha et al., 2011 • Twitcident Emergency Corpus Analysis Support Tools Microblogging SNA-Techniques Clustering-Techniques • Mendozza et al., 2010 • Becker et al, 2011 • Marcus et al, 2011 NLP-Techniques • Pohl et al, 2012 • Sudha et al, 2011 • Abel et al, 2011 UCAmI 2012 B. Klein 5/17
  • 6. SABESS Web system UCAmI 2012 B. Klein 6/17
  • 7. Opensource Implementation • Emergency message filter based on emergency taxonomy • Language filter e.g. english or spanish • Slang reduction (punctation + letter repititions) UCAmI 2012 B. Klein 7/17
  • 8. Social Network Analysis ► Objective: Filtering after tweet credibility UCAmI 2012 B. Klein 8/17
  • 9. Observed Problems  “Slow” Graph Calculations  Replace betweeness centrality with user data a) followers count ~ influence b) friend count ~ knowledge access c) number of posts ~ experience  “Sparse” Social Network  Replace SNA with Sentiment Analysis: Punctation-, letter- and word repititions Tweet credibility < Informative tweet! (see also Sudha et al., 2011) UCAmI 2012 B. Klein 9/17
  • 10. Natural language procesing ► Objective: Content enrichment • Big Improvement with “slang reduction” !! UCAmI 2012 B. Klein 10/17
  • 11. Other Knowledge Sources  Hierarchical Knowledge Structure 1. Textual location a) Named Entity Location b) Regular Expression e.g. address (Requires reverse coding!) 2. Tweet metadata a) GPS tagged tweets b) Place tagged tweets (Author location can be different!) 3. User profile data a) Home location Increasing reliability! UCAmI 2012 B. Klein 11/17
  • 12. Recent Advances: Event Detection ► Objective: Group tweets into emergency events  How to describe an emergency event?  Emergency type, location (range), time (progress), person/organization data, text descriptions, number of tweets  Global reporting standard “Common Alert Protocol”.  Example: UCAmI 2012 B. Klein 12/17
  • 13. Recent Advances: Clustering ► Incremental DBSCAN SANDY HURRICANE RELIEF VOLUNTEER EFFORTS SANDY HURRICANE VICTIMS VOLUNTEER SANDY HURRICANE VICTIMS VOLUNTEER EFFORT GRASSROOTS SANDY HURRICANE VICTIMS VOLUNTEER NEWS EFFORT GRASSROOTS Sandy, 180 SANDY HURRICANE VICTIMS POLICE Fukuschima, 170 SANDY HURRICANE VICTIMS RELIEF …. SANDY HURRICANE VICTIMS Locations: Ambulance, 80 SANDY HURRICANE VICTIMS RELIEF DISASTER PrincetonHall e.g. ….. SANDY HURRICANE RELIEF SANDY HURRICANE RELIEF SANDY HURRICANE RELIEF DISASTER SANDY VOLUNTEER Online Conversations: Dictionary ConversationID=83 Hashtags: #TylerPerryFire Attachments: http://t.co/kqF7Xy8t UCAmI 2012 B. Klein 13/17
  • 14. Common Alert Protocol Whenever clusters become modified, generate new alert message?? Alert CAP Info Place Urls, Figs Cluster of tweets UCAmI 2012 B. Klein 14/17
  • 15. Conclusions  Real-time analysis of noisy tweets ► Big data problem, 2 phase analysis  Emergency message filtering  Slang and language filtering ► Semantic Social Network Analysis  POS/Noun tags, NER/Location tags  Community centrality/follower count tags ► Tweet clustering  Group tweets after hashtags, attachments and conversations  Group tweets after emergency specific keywords ► Common Alert Protocol UCAmI 2012 B. Klein 15/17
  • 16. Contact: Bernhard Klein, Email: bernhard.klein@deusto.es Deusto Intitute of Technology, University of Deusto, th International Conference on Ubiquitous Computing and Ambient Intelligence 6 Avda. Universidades, 24 | 48007 Bilbao | Session 10: Key application domains: eEmergency, eLearning, eTraining Spain 5. December, 2012 UCAmI 2012 B. Klein 16/17