SlideShare ist ein Scribd-Unternehmen logo
1 von 26
Downloaden Sie, um offline zu lesen
Information Propagation and Extraction
from Twitter
Dr. Matteo Magnani – University of Bologna
Dr. Luca Rossi – University of Urbino Carlo Bo




http://larica.uniurb.it/sigsna
Focus of the talk: INTERDISCIPLINARITY

          Computer scientist             Sociologist
The Computer Scientist's perspective
The Social Scientist's perspective
The Social Scientist's perspective
Outline
●   Extracting information from Twitter.
●   Studying information propagation on Twitter.
●   Beyond Twitter: multi-layer networks.
From Tweet retrieval…

                   BLA
          BLA             BLA
                                 BLA    BLA   BLA


          BLA
                    BLA
                           BLA

                                       BLA
From Tweet retrieval… to Conversation Retrieval

                   BLA
          BLA                 BLA
                                        BLA        BLA   BLA


          BLA
                     BLA
                                BLA

                                                  BLA
Conversation Retrieval System

  Some basic problems:
●
  Off-line and on-line conversations are different.
●
  What is a conversation on Twitter?

 Ranking parameters:
●
  text relevance
●
  popularity of users
●
  popularity of messages
●
  timeliness
●
  non-verbal signals
   ●
     (style, emoticons, density)
Conversation Retrieval System Architecture
(Demo of the system – on line)
Evaluation


Topic: Chilean mining accident
user evaluation of:
●
  Google search (a),
●
  Conversation Retrieval with high popularity (b),
●
  Conversation Retrieval with high density (c)
(x: score, y: number of votes)




        (a)                       (b)                (c)
Evaluation


Topic: Death of former Italian President (Francesco Cossiga)
user evaluation of:
●
  Google search (a),
●
  Conversation Retrieval with high popularity (b),
●
  Conversation Retrieval with high density (c)
(x: score, y: number of votes)




    (a)                    (b)                  (c)
Information propagation: epidemiological model
Information propagation: epidemiological model
Information propagation: epidemiological model
Information propagation in a socio-technical context




●
  Are we sure people have been exposed?
●
  What about information persistence?
●
  Users may (explicitely or implicitly) decide to propagate information.




 TWO STEPS:
1) Identify propagation paths
2) Interpret the results -> patterns




                                                               Older posts
TWO STEPS:
1) Identify propagation paths
2) Interpret the results -> patterns




                                   Case study: Mike Bongiorno's death (Italian TV Anchorman)
TWO STEPS:
1) Identify propagation paths
2) Interpret the results -> patterns




                                   Case study: Mike Bongiorno's death (Italian TV Anchorman)
TWO STEPS:
1) Identify propagation paths
2) Interpret the results -> patterns




                                   Case study: Mike Bongiorno's death (Italian TV Anchorman)
TWO STEPS:                                      Mike passed away!
1) Identify propagation paths
2) Interpret the results    patterns                          How has television
                                                              changed?




                                       Bye granpa Mike!




                                  Case study: Mike Bongiorno's death (Italian TV Anchorman)
7 top commented threads about Mike’s death




                            Case study: Mike Bongiorno's death (Italian TV Anchorman)
Rescue operations for 33 Chilean Miners (Oct. 2010)

Global breaking news, data collected on Twitter and FriendFeed




  Twitter conversation on the Miners’s
  rescue. It is possible to see how local
  national communities still exist.
Users belong to several networks at the same time!

Knowledge of other networks is essential also to study
internal Twitter dynamics.
ML model for multi-networks




User C: Degree dentrality                   User C: Degree dentrality
3 (net 1) and 3 (net 2)                     2 (net 1) and 2 (net 2)


      However, in the second (RHS) system user C is connected to more people!
Information Propagation and Extraction
from Twitter
Dr. Matteo Magnani – University of Bologna
Dr. Luca Rossi – University of Urbino Carlo Bo




http://larica.uniurb.it/sigsna

Weitere ähnliche Inhalte

Ähnlich wie Twitter information extraction and propagation: an interdisciplinary view

Kdd12 tutorial-inf-part-i
Kdd12 tutorial-inf-part-iKdd12 tutorial-inf-part-i
Kdd12 tutorial-inf-part-iLaks Lakshmanan
 
Friendfeed breaking news: death of a public figure
Friendfeed breaking news: death of a public figureFriendfeed breaking news: death of a public figure
Friendfeed breaking news: death of a public figureMatteo Magnani
 
Information spreading in FriendFeed
Information spreading in FriendFeedInformation spreading in FriendFeed
Information spreading in FriendFeedLuca Rossi
 
CMCs 1st ProDoc School seminar
CMCs 1st ProDoc School seminarCMCs 1st ProDoc School seminar
CMCs 1st ProDoc School seminarSara Vannini
 
Generational "we sense" in a networked space
Generational "we sense" in a networked spaceGenerational "we sense" in a networked space
Generational "we sense" in a networked spaceGiovanni Boccia Artieri
 
T3CON09 Dallas - EXT:community
T3CON09 Dallas - EXT:communityT3CON09 Dallas - EXT:community
T3CON09 Dallas - EXT:communityIngo Renner
 

Ähnlich wie Twitter information extraction and propagation: an interdisciplinary view (9)

Kdd12 tutorial-inf-part-i
Kdd12 tutorial-inf-part-iKdd12 tutorial-inf-part-i
Kdd12 tutorial-inf-part-i
 
Friendfeed breaking news: death of a public figure
Friendfeed breaking news: death of a public figureFriendfeed breaking news: death of a public figure
Friendfeed breaking news: death of a public figure
 
Information spreading in FriendFeed
Information spreading in FriendFeedInformation spreading in FriendFeed
Information spreading in FriendFeed
 
CMCs 1st ProDoc School seminar
CMCs 1st ProDoc School seminarCMCs 1st ProDoc School seminar
CMCs 1st ProDoc School seminar
 
Super Social Everybody
Super Social EverybodySuper Social Everybody
Super Social Everybody
 
Socializing BOINC
Socializing BOINCSocializing BOINC
Socializing BOINC
 
Generational "we sense" in a networked space
Generational "we sense" in a networked spaceGenerational "we sense" in a networked space
Generational "we sense" in a networked space
 
Broker Bots: Analyzing automated activity during High Impact Events on Twitter
Broker Bots: Analyzing automated activity during High Impact Events on TwitterBroker Bots: Analyzing automated activity during High Impact Events on Twitter
Broker Bots: Analyzing automated activity during High Impact Events on Twitter
 
T3CON09 Dallas - EXT:community
T3CON09 Dallas - EXT:communityT3CON09 Dallas - EXT:community
T3CON09 Dallas - EXT:community
 

Kürzlich hochgeladen

Are Multi-Cloud and Serverless Good or Bad?
Are Multi-Cloud and Serverless Good or Bad?Are Multi-Cloud and Serverless Good or Bad?
Are Multi-Cloud and Serverless Good or Bad?Mattias Andersson
 
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
 
"LLMs for Python Engineers: Advanced Data Analysis and Semantic Kernel",Oleks...
"LLMs for Python Engineers: Advanced Data Analysis and Semantic Kernel",Oleks..."LLMs for Python Engineers: Advanced Data Analysis and Semantic Kernel",Oleks...
"LLMs for Python Engineers: Advanced Data Analysis and Semantic Kernel",Oleks...Fwdays
 
Dev Dives: Streamline document processing with UiPath Studio Web
Dev Dives: Streamline document processing with UiPath Studio WebDev Dives: Streamline document processing with UiPath Studio Web
Dev Dives: Streamline document processing with UiPath Studio WebUiPathCommunity
 
Ensuring Technical Readiness For Copilot in Microsoft 365
Ensuring Technical Readiness For Copilot in Microsoft 365Ensuring Technical Readiness For Copilot in Microsoft 365
Ensuring Technical Readiness For Copilot in Microsoft 3652toLead Limited
 
"Debugging python applications inside k8s environment", Andrii Soldatenko
"Debugging python applications inside k8s environment", Andrii Soldatenko"Debugging python applications inside k8s environment", Andrii Soldatenko
"Debugging python applications inside k8s environment", Andrii SoldatenkoFwdays
 
Connect Wave/ connectwave Pitch Deck Presentation
Connect Wave/ connectwave Pitch Deck PresentationConnect Wave/ connectwave Pitch Deck Presentation
Connect Wave/ connectwave Pitch Deck PresentationSlibray Presentation
 
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
 
From Family Reminiscence to Scholarly Archive .
From Family Reminiscence to Scholarly Archive .From Family Reminiscence to Scholarly Archive .
From Family Reminiscence to Scholarly Archive .Alan Dix
 
"ML in Production",Oleksandr Bagan
"ML in Production",Oleksandr Bagan"ML in Production",Oleksandr Bagan
"ML in Production",Oleksandr BaganFwdays
 
What's New in Teams Calling, Meetings and Devices March 2024
What's New in Teams Calling, Meetings and Devices March 2024What's New in Teams Calling, Meetings and Devices March 2024
What's New in Teams Calling, Meetings and Devices March 2024Stephanie Beckett
 
Story boards and shot lists for my a level piece
Story boards and shot lists for my a level pieceStory boards and shot lists for my a level piece
Story boards and shot lists for my a level piececharlottematthew16
 
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
 
Nell’iperspazio con Rocket: il Framework Web di Rust!
Nell’iperspazio con Rocket: il Framework Web di Rust!Nell’iperspazio con Rocket: il Framework Web di Rust!
Nell’iperspazio con Rocket: il Framework Web di Rust!Commit University
 
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
 
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
 
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
 
New from BookNet Canada for 2024: BNC CataList - Tech Forum 2024
New from BookNet Canada for 2024: BNC CataList - Tech Forum 2024New from BookNet Canada for 2024: BNC CataList - Tech Forum 2024
New from BookNet Canada for 2024: BNC CataList - Tech Forum 2024BookNet Canada
 
DevEX - reference for building teams, processes, and platforms
DevEX - reference for building teams, processes, and platformsDevEX - reference for building teams, processes, and platforms
DevEX - reference for building teams, processes, and platformsSergiu Bodiu
 
Developer Data Modeling Mistakes: From Postgres to NoSQL
Developer Data Modeling Mistakes: From Postgres to NoSQLDeveloper Data Modeling Mistakes: From Postgres to NoSQL
Developer Data Modeling Mistakes: From Postgres to NoSQLScyllaDB
 

Kürzlich hochgeladen (20)

Are Multi-Cloud and Serverless Good or Bad?
Are Multi-Cloud and Serverless Good or Bad?Are Multi-Cloud and Serverless Good or Bad?
Are Multi-Cloud and Serverless Good or Bad?
 
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
 
"LLMs for Python Engineers: Advanced Data Analysis and Semantic Kernel",Oleks...
"LLMs for Python Engineers: Advanced Data Analysis and Semantic Kernel",Oleks..."LLMs for Python Engineers: Advanced Data Analysis and Semantic Kernel",Oleks...
"LLMs for Python Engineers: Advanced Data Analysis and Semantic Kernel",Oleks...
 
Dev Dives: Streamline document processing with UiPath Studio Web
Dev Dives: Streamline document processing with UiPath Studio WebDev Dives: Streamline document processing with UiPath Studio Web
Dev Dives: Streamline document processing with UiPath Studio Web
 
Ensuring Technical Readiness For Copilot in Microsoft 365
Ensuring Technical Readiness For Copilot in Microsoft 365Ensuring Technical Readiness For Copilot in Microsoft 365
Ensuring Technical Readiness For Copilot in Microsoft 365
 
"Debugging python applications inside k8s environment", Andrii Soldatenko
"Debugging python applications inside k8s environment", Andrii Soldatenko"Debugging python applications inside k8s environment", Andrii Soldatenko
"Debugging python applications inside k8s environment", Andrii Soldatenko
 
Connect Wave/ connectwave Pitch Deck Presentation
Connect Wave/ connectwave Pitch Deck PresentationConnect Wave/ connectwave Pitch Deck Presentation
Connect Wave/ connectwave Pitch Deck Presentation
 
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
 
From Family Reminiscence to Scholarly Archive .
From Family Reminiscence to Scholarly Archive .From Family Reminiscence to Scholarly Archive .
From Family Reminiscence to Scholarly Archive .
 
"ML in Production",Oleksandr Bagan
"ML in Production",Oleksandr Bagan"ML in Production",Oleksandr Bagan
"ML in Production",Oleksandr Bagan
 
What's New in Teams Calling, Meetings and Devices March 2024
What's New in Teams Calling, Meetings and Devices March 2024What's New in Teams Calling, Meetings and Devices March 2024
What's New in Teams Calling, Meetings and Devices March 2024
 
Story boards and shot lists for my a level piece
Story boards and shot lists for my a level pieceStory boards and shot lists for my a level piece
Story boards and shot lists for my a level piece
 
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
 
Nell’iperspazio con Rocket: il Framework Web di Rust!
Nell’iperspazio con Rocket: il Framework Web di Rust!Nell’iperspazio con Rocket: il Framework Web di Rust!
Nell’iperspazio con Rocket: il Framework Web di Rust!
 
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
 
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
 
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
 
New from BookNet Canada for 2024: BNC CataList - Tech Forum 2024
New from BookNet Canada for 2024: BNC CataList - Tech Forum 2024New from BookNet Canada for 2024: BNC CataList - Tech Forum 2024
New from BookNet Canada for 2024: BNC CataList - Tech Forum 2024
 
DevEX - reference for building teams, processes, and platforms
DevEX - reference for building teams, processes, and platformsDevEX - reference for building teams, processes, and platforms
DevEX - reference for building teams, processes, and platforms
 
Developer Data Modeling Mistakes: From Postgres to NoSQL
Developer Data Modeling Mistakes: From Postgres to NoSQLDeveloper Data Modeling Mistakes: From Postgres to NoSQL
Developer Data Modeling Mistakes: From Postgres to NoSQL
 

Twitter information extraction and propagation: an interdisciplinary view

  • 1. Information Propagation and Extraction from Twitter Dr. Matteo Magnani – University of Bologna Dr. Luca Rossi – University of Urbino Carlo Bo http://larica.uniurb.it/sigsna
  • 2. Focus of the talk: INTERDISCIPLINARITY Computer scientist Sociologist
  • 6. Outline ● Extracting information from Twitter. ● Studying information propagation on Twitter. ● Beyond Twitter: multi-layer networks.
  • 7. From Tweet retrieval… BLA BLA BLA BLA BLA BLA BLA BLA BLA BLA
  • 8. From Tweet retrieval… to Conversation Retrieval BLA BLA BLA BLA BLA BLA BLA BLA BLA BLA
  • 9. Conversation Retrieval System Some basic problems: ● Off-line and on-line conversations are different. ● What is a conversation on Twitter? Ranking parameters: ● text relevance ● popularity of users ● popularity of messages ● timeliness ● non-verbal signals ● (style, emoticons, density)
  • 11. (Demo of the system – on line)
  • 12. Evaluation Topic: Chilean mining accident user evaluation of: ● Google search (a), ● Conversation Retrieval with high popularity (b), ● Conversation Retrieval with high density (c) (x: score, y: number of votes) (a) (b) (c)
  • 13. Evaluation Topic: Death of former Italian President (Francesco Cossiga) user evaluation of: ● Google search (a), ● Conversation Retrieval with high popularity (b), ● Conversation Retrieval with high density (c) (x: score, y: number of votes) (a) (b) (c)
  • 17. Information propagation in a socio-technical context ● Are we sure people have been exposed? ● What about information persistence? ● Users may (explicitely or implicitly) decide to propagate information. TWO STEPS: 1) Identify propagation paths 2) Interpret the results -> patterns Older posts
  • 18. TWO STEPS: 1) Identify propagation paths 2) Interpret the results -> patterns Case study: Mike Bongiorno's death (Italian TV Anchorman)
  • 19. TWO STEPS: 1) Identify propagation paths 2) Interpret the results -> patterns Case study: Mike Bongiorno's death (Italian TV Anchorman)
  • 20. TWO STEPS: 1) Identify propagation paths 2) Interpret the results -> patterns Case study: Mike Bongiorno's death (Italian TV Anchorman)
  • 21. TWO STEPS: Mike passed away! 1) Identify propagation paths 2) Interpret the results patterns How has television changed? Bye granpa Mike! Case study: Mike Bongiorno's death (Italian TV Anchorman)
  • 22. 7 top commented threads about Mike’s death Case study: Mike Bongiorno's death (Italian TV Anchorman)
  • 23. Rescue operations for 33 Chilean Miners (Oct. 2010) Global breaking news, data collected on Twitter and FriendFeed Twitter conversation on the Miners’s rescue. It is possible to see how local national communities still exist.
  • 24. Users belong to several networks at the same time! Knowledge of other networks is essential also to study internal Twitter dynamics.
  • 25. ML model for multi-networks User C: Degree dentrality User C: Degree dentrality 3 (net 1) and 3 (net 2) 2 (net 1) and 2 (net 2) However, in the second (RHS) system user C is connected to more people!
  • 26. Information Propagation and Extraction from Twitter Dr. Matteo Magnani – University of Bologna Dr. Luca Rossi – University of Urbino Carlo Bo http://larica.uniurb.it/sigsna