SlideShare a Scribd company logo
1 of 45
Visualising
conversation around
#c4thepromise

Steve Winton, Jenni Lloyd & Edd Parris
Interesting things are afoot in TV Land
The client




That well-known public
service broadcaster

Innovative, and up for
doing this differently
DIKW


        Wisdom


       Knowledge


       Information


          Data
Datacopter!




www.datacopter.com
The programme




The Promise
Highly-sensitive, controversial
Extremists on both sides of the issue
Potentially even damaging to Channel 4’s brand
Trailer




Spoiler alert!
The brief


Demonstrate how Channel 4 is fulfilling its role as a
public service broadcaster

Expose all aspects of the conversation, and not be
dominated by the political/religious elements

Encourage exploration of, and participation in, the online
conversation
We need a mechanic that will show the variety
as well as the volume.
Designs and Prototype


Early designs
Early prototype
Inspiration

title




Could we create a ‘conversation constellation’?
Early designs
Early prototype
How to catch a tweet


Gnip
PuSH (Superfeedr)
Streaming API / Datasift
Polling
Gnip




       Very good, but very expensive
PuSH (Superfeedr)




        Inexpensive

        But, in our tests, failed to deliver
Streaming API / Datasift




         We ♥ streaming

         But, not suitable for this project
Polling



          Old-fashioned, but reliable

          Picks up tweets retrospectively :)

          Pre-moderated, so near real-time
          is good enough
Platform


System architecture
System architecture
Process overview




                   A tweet arrives
Process overview




               We remove all the cruft
Process overview




    Adjectives   Nouns   Verbs   Adverbs


    Hashtags     URLs    Users



                    We use an NLP algorithm
                    to extract phrases and
                    tag the ‘parts of speech’
Process overview




               We build up a mahoosive
               database of
               interconnected phrases
Process overview




               We create a “phrases
               graph” that represents
               the conversation
Process overview




               And a distances matrix
               (phrases that commonly
               occur together are close
               to each other)
Process overview




And then, like looking at towns on a map,
we can identify communities of phrases,
and group them into clusters.
Cheats




         A B start
The app in its natural habitat




                        http://j.mp/twitter-tracker
The app in its natural habitat




                        http://j.mp/twitter-tracker
99 Problems :




The Boss
Bad ideas
Testing
The Boss
Bad ideas




        Initial clustering algorithm took an hour to
        run :

        Catching the long tail

        Refreshing the app at 9pm
Test data




            Hard to predict and design for what people
            will actually talk about
            And so hard to test with meaningful, realistic
            data
Learnings




       Realtime and pre-moderation, not the best of
       friends
       Realtime + NLP + graph analysis is an
       interesting problem to tackle at scale
Learnings




Understanding the nature of the conversation (attention
patterns, responses over time, conversations on the side)
Learnings
anticipation   immersion




preparation    review
Learnings




       Promoting the hashtag on-air works!
Learnings




       Lots of activity during live web chats
What next? For broadcasters




Social TV
Making the most of the ‘second screen’
TV checkins
Social experience + time-shifted viewing
What next? For Datacopter


iOS
Real real-time
Better NLP
Revisit the UX
Contributors, influencers, values
Fitter, healthier and more productive
Thanks! :)




                Any
             questions?
Thanks! :)

You’ve been wonderful x




        Stay in touch?
        Jenni Lloyd / @jennilloyd / jenni.lloyd@nixonmcinnes.co.uk

        Steve Winton / @steveWINton / steve.winton@nixonmcinnes.co.uk

        Edd Parris / @empika / edward.parris@nixonmcinnes.co.uk
Credits

http://www.flickr.com/photos/38063599@N00/2632323465/
http://www.flickr.com/photos/michibertolino/2326851802/
http://www.flickr.com/photos/85791047@N00/5352474332/
http://www.flickr.com/photos/snakphotography/4365066875/
http://www.flickr.com/photos/jeffanddayna/4610127963/
http://www.flickr.com/photos/tmartin/71654890/
http://www.theplace2.ru/archive/river_phoenix/img/kinopoisk_ru_River_P-1.jpg
http://www.flickr.com/photos/marilynjane/482679465/
http://www.flickr.com/photos/sheilaellen/111377949/
http://barrygruff.wordpress.com/2010/11/16/jay-z-99-problems-the-prodigy-remix/
http://www.flickr.com/photos/pasukaru76/4892378102/
http://muppet.wikia.com/
http://www.flickr.com/photos/whatcouldgowrong/4608963722/
http://www.flickr.com/photos/paullikespics/3279094697/
http://www.flickr.com/photos/scissorhands33/3430164569/

More Related Content

Similar to Visualising conversation around #c4thepromise

Beyond SuperPoke: Using social networks to build client trust
Beyond SuperPoke: Using social networks to build client trustBeyond SuperPoke: Using social networks to build client trust
Beyond SuperPoke: Using social networks to build client trust
Jason Pryslak
 
JAZOON'13 - Sven Peters - How to do Kick-Ass Software Development
JAZOON'13 - Sven Peters - How to do Kick-Ass Software DevelopmentJAZOON'13 - Sven Peters - How to do Kick-Ass Software Development
JAZOON'13 - Sven Peters - How to do Kick-Ass Software Development
jazoon13
 

Similar to Visualising conversation around #c4thepromise (20)

Beyond SuperPoke: Using social networks to build client trust
Beyond SuperPoke: Using social networks to build client trustBeyond SuperPoke: Using social networks to build client trust
Beyond SuperPoke: Using social networks to build client trust
 
JAZOON'13 - Sven Peters - How to do Kick-Ass Software Development
JAZOON'13 - Sven Peters - How to do Kick-Ass Software DevelopmentJAZOON'13 - Sven Peters - How to do Kick-Ass Software Development
JAZOON'13 - Sven Peters - How to do Kick-Ass Software Development
 
Make Tools
Make ToolsMake Tools
Make Tools
 
IA and RIA: You know more than you think you do
IA and RIA: You know more than you think you doIA and RIA: You know more than you think you do
IA and RIA: You know more than you think you do
 
Mike davies sentiment_analysis_presentation_backup
Mike davies sentiment_analysis_presentation_backupMike davies sentiment_analysis_presentation_backup
Mike davies sentiment_analysis_presentation_backup
 
AI and Python: Developing a Conversational Interface using Python
AI and Python: Developing a Conversational Interface using PythonAI and Python: Developing a Conversational Interface using Python
AI and Python: Developing a Conversational Interface using Python
 
Catalyze Webcast - Five Myths Of RIA With Laurie Gray - 031808
Catalyze Webcast - Five Myths Of RIA With Laurie Gray - 031808Catalyze Webcast - Five Myths Of RIA With Laurie Gray - 031808
Catalyze Webcast - Five Myths Of RIA With Laurie Gray - 031808
 
The Junior Developer Survival Guide - GDI Ann Arbor 2/10/15
The Junior Developer Survival Guide -  GDI Ann Arbor 2/10/15The Junior Developer Survival Guide -  GDI Ann Arbor 2/10/15
The Junior Developer Survival Guide - GDI Ann Arbor 2/10/15
 
Dream todeployment
Dream todeploymentDream todeployment
Dream todeployment
 
Identify Development Pains and Resolve Them with Idea Flow
Identify Development Pains and Resolve Them with Idea FlowIdentify Development Pains and Resolve Them with Idea Flow
Identify Development Pains and Resolve Them with Idea Flow
 
Understanding Human Conversations with AI
Understanding Human Conversations with AI Understanding Human Conversations with AI
Understanding Human Conversations with AI
 
All in AI: LLM Landscape & RAG in 2024 with Mark Ryan (Google) & Jerry Liu (L...
All in AI: LLM Landscape & RAG in 2024 with Mark Ryan (Google) & Jerry Liu (L...All in AI: LLM Landscape & RAG in 2024 with Mark Ryan (Google) & Jerry Liu (L...
All in AI: LLM Landscape & RAG in 2024 with Mark Ryan (Google) & Jerry Liu (L...
 
The Rise of the DataOps - Dataiku - J On the Beach 2016
The Rise of the DataOps - Dataiku - J On the Beach 2016 The Rise of the DataOps - Dataiku - J On the Beach 2016
The Rise of the DataOps - Dataiku - J On the Beach 2016
 
How To Do Kick-Ass Software Development
How To Do Kick-Ass Software DevelopmentHow To Do Kick-Ass Software Development
How To Do Kick-Ass Software Development
 
We hear you!. Collecting and processing user feedback, for real!
We hear you!. Collecting and processing user feedback, for real!We hear you!. Collecting and processing user feedback, for real!
We hear you!. Collecting and processing user feedback, for real!
 
Designing the Future of Broadcasting
Designing the Future of BroadcastingDesigning the Future of Broadcasting
Designing the Future of Broadcasting
 
How open source is driving DevOps innovation: CloudOpen NA 2015
How open source is driving DevOps innovation: CloudOpen NA 2015How open source is driving DevOps innovation: CloudOpen NA 2015
How open source is driving DevOps innovation: CloudOpen NA 2015
 
The UX Toolbelt for Developers
The UX Toolbelt for DevelopersThe UX Toolbelt for Developers
The UX Toolbelt for Developers
 
Rich User Experience Documentation - Update
Rich User Experience Documentation - UpdateRich User Experience Documentation - Update
Rich User Experience Documentation - Update
 
Extracurricular Swift
Extracurricular SwiftExtracurricular Swift
Extracurricular Swift
 

Recently uploaded

Breaking Down the Flutterwave Scandal What You Need to Know.pdf
Breaking Down the Flutterwave Scandal What You Need to Know.pdfBreaking Down the Flutterwave Scandal What You Need to Know.pdf
Breaking Down the Flutterwave Scandal What You Need to Know.pdf
UK Journal
 

Recently uploaded (20)

ECS 2024 Teams Premium - Pretty Secure
ECS 2024   Teams Premium - Pretty SecureECS 2024   Teams Premium - Pretty Secure
ECS 2024 Teams Premium - Pretty Secure
 
Integrating Telephony Systems with Salesforce: Insights and Considerations, B...
Integrating Telephony Systems with Salesforce: Insights and Considerations, B...Integrating Telephony Systems with Salesforce: Insights and Considerations, B...
Integrating Telephony Systems with Salesforce: Insights and Considerations, B...
 
WebRTC and SIP not just audio and video @ OpenSIPS 2024
WebRTC and SIP not just audio and video @ OpenSIPS 2024WebRTC and SIP not just audio and video @ OpenSIPS 2024
WebRTC and SIP not just audio and video @ OpenSIPS 2024
 
AI presentation and introduction - Retrieval Augmented Generation RAG 101
AI presentation and introduction - Retrieval Augmented Generation RAG 101AI presentation and introduction - Retrieval Augmented Generation RAG 101
AI presentation and introduction - Retrieval Augmented Generation RAG 101
 
PLAI - Acceleration Program for Generative A.I. Startups
PLAI - Acceleration Program for Generative A.I. StartupsPLAI - Acceleration Program for Generative A.I. Startups
PLAI - Acceleration Program for Generative A.I. Startups
 
State of the Smart Building Startup Landscape 2024!
State of the Smart Building Startup Landscape 2024!State of the Smart Building Startup Landscape 2024!
State of the Smart Building Startup Landscape 2024!
 
Portal Kombat : extension du réseau de propagande russe
Portal Kombat : extension du réseau de propagande russePortal Kombat : extension du réseau de propagande russe
Portal Kombat : extension du réseau de propagande russe
 
Continuing Bonds Through AI: A Hermeneutic Reflection on Thanabots
Continuing Bonds Through AI: A Hermeneutic Reflection on ThanabotsContinuing Bonds Through AI: A Hermeneutic Reflection on Thanabots
Continuing Bonds Through AI: A Hermeneutic Reflection on Thanabots
 
1111 ChatGPT Prompts PDF Free Download - Prompts for ChatGPT
1111 ChatGPT Prompts PDF Free Download - Prompts for ChatGPT1111 ChatGPT Prompts PDF Free Download - Prompts for ChatGPT
1111 ChatGPT Prompts PDF Free Download - Prompts for ChatGPT
 
A Business-Centric Approach to Design System Strategy
A Business-Centric Approach to Design System StrategyA Business-Centric Approach to Design System Strategy
A Business-Centric Approach to Design System Strategy
 
Linux Foundation Edge _ Overview of FDO Software Components _ Randy at Intel.pdf
Linux Foundation Edge _ Overview of FDO Software Components _ Randy at Intel.pdfLinux Foundation Edge _ Overview of FDO Software Components _ Randy at Intel.pdf
Linux Foundation Edge _ Overview of FDO Software Components _ Randy at Intel.pdf
 
Overview of Hyperledger Foundation
Overview of Hyperledger FoundationOverview of Hyperledger Foundation
Overview of Hyperledger Foundation
 
Designing for Hardware Accessibility at Comcast
Designing for Hardware Accessibility at ComcastDesigning for Hardware Accessibility at Comcast
Designing for Hardware Accessibility at Comcast
 
How Red Hat Uses FDO in Device Lifecycle _ Costin and Vitaliy at Red Hat.pdf
How Red Hat Uses FDO in Device Lifecycle _ Costin and Vitaliy at Red Hat.pdfHow Red Hat Uses FDO in Device Lifecycle _ Costin and Vitaliy at Red Hat.pdf
How Red Hat Uses FDO in Device Lifecycle _ Costin and Vitaliy at Red Hat.pdf
 
Enterprise Knowledge Graphs - Data Summit 2024
Enterprise Knowledge Graphs - Data Summit 2024Enterprise Knowledge Graphs - Data Summit 2024
Enterprise Knowledge Graphs - Data Summit 2024
 
Behind the Scenes From the Manager's Chair: Decoding the Secrets of Successfu...
Behind the Scenes From the Manager's Chair: Decoding the Secrets of Successfu...Behind the Scenes From the Manager's Chair: Decoding the Secrets of Successfu...
Behind the Scenes From the Manager's Chair: Decoding the Secrets of Successfu...
 
Extensible Python: Robustness through Addition - PyCon 2024
Extensible Python: Robustness through Addition - PyCon 2024Extensible Python: Robustness through Addition - PyCon 2024
Extensible Python: Robustness through Addition - PyCon 2024
 
Breaking Down the Flutterwave Scandal What You Need to Know.pdf
Breaking Down the Flutterwave Scandal What You Need to Know.pdfBreaking Down the Flutterwave Scandal What You Need to Know.pdf
Breaking Down the Flutterwave Scandal What You Need to Know.pdf
 
Choosing the Right FDO Deployment Model for Your Application _ Geoffrey at In...
Choosing the Right FDO Deployment Model for Your Application _ Geoffrey at In...Choosing the Right FDO Deployment Model for Your Application _ Geoffrey at In...
Choosing the Right FDO Deployment Model for Your Application _ Geoffrey at In...
 
FDO for Camera, Sensor and Networking Device – Commercial Solutions from VinC...
FDO for Camera, Sensor and Networking Device – Commercial Solutions from VinC...FDO for Camera, Sensor and Networking Device – Commercial Solutions from VinC...
FDO for Camera, Sensor and Networking Device – Commercial Solutions from VinC...
 

Visualising conversation around #c4thepromise

Editor's Notes

  1. We work for NixonMcInnes, we are a bunch of coders, strategists, designers and thinkers...\n
  2. TV - ripe for innovation\nTV sparks conversation, and always has done\nBUT now there’s an interesting platform to capture that\nNew behaviours emerging\nPeople using Twitter and their social networks to engage around TV programmes\n
  3. Channels\n2-screen\nTime-shifted viewing\n\nA very interesting client to work with, always up for doing new and interesting things, that haven’t been done before\nBrave\nA certain amount of their programming should serve the public interest, educational\n
  4. Applies to broadcaster, and viewer\n
  5. Connecting with the audience at home\nExtending the studio experience to the Twitter audience\nThe audience becomes a part of the show\nA lot to learn from this (for C4) and a lot of interest within C4\n
  6. The Promise\n
  7. http://www.flickr.com/photos/michibertolino/2326851802/\n
  8. \n
  9. Also, pre-moderated!!!\n
  10. \n
  11. Also, pre-moderated!!!\n
  12. \n
  13. \n
  14. \n
  15. Edd next!!!\n
  16. \n
  17. Edd\n
  18. Edd\n
  19. Edd\n
  20. Edd\n
  21. Edd\n
  22. Edd\n
  23. Edd\n\nSteve coming up!\n
  24. Steve\n
  25. Steve\n
  26. Steve\n
  27. Steve\n
  28. Steve\n
  29. Steve\n
  30. Steve\n
  31. ????\nKnown phrases\nTweaking as we went, lots of config options in the db, cuz of the unknown nature of what we would actually get!\n\nSteve\n
  32. Jenni\n
  33. Jenni\n
  34. Edd\n
  35. Edd\n
  36. Edd\n
  37. Edd\n\nJenni coming up!\n\nTesting. Lack of realistic data, volume and content\n
  38. Gaining insight into different behaviour, how people tweet, the language they use, depending on the kind of programming, the time of day (around TX), the types of conversation before during and after TX\n\n\nAnticipation, preparation, reaction, considerations \nMomentum\nHashtag promotion\nPost-TX Web chat\n
  39. Jenni\n
  40. \n
  41. Stemming\nClustering\nGraphs\nRealtime data + NLP is tricky and unpredictable\nRealtime + moderation not so good\nWorks well as an artifact that lives beyond the drama series\nGood response when broadcaster mentions the hashtag at the beginning of the show! Promoting the hashtag works!\n
  42. Stemming\nClustering\nGraphs\nRealtime data + NLP is tricky and unpredictable\nRealtime + moderation not so good\nWorks well as an artifact that lives beyond the drama series\nGood response when broadcaster mentions the hashtag at the beginning of the show! Promoting the hashtag works!\n
  43. Jenni\n
  44. Steve\n
  45. \n
  46. \n
  47. \n