Polemic tweet - IFIP Interact 2013
-
Upload
samuel-huron -
Category
Technology
-
view
557 -
download
2
description
Transcript of Polemic tweet - IFIP Interact 2013
PolemicTweet Video Annotation and Analysis
through tagged Tweets
Samuel Huron, Petra Isenberg, Jean Daniel Fekete
06/09/13 IFIP Interact 2013 – Polemic tweet
.
05/09/2013 IFIP Interact 2013 – Polemic tweet
Petra Isenberg INRIA @dr_pi
Raphael Velt IRI @raphv
Yves Marie Haussonne IRI @ymh_work
Authors and Contributors
Samuel Huron INRIA - IRI @cybunk
Jean Daniel Fekete INRIA @jdfaviz
06/09/13 IFIP Interact 2013 – Polemic tweet
At IRI we organize seminars on subjects such as
philosophy, design, and digital cultures. !
SITUATION
05/09/2013 IFIP Interact 2013 – Polemic tweet
05/09/2013 IFIP Interact 2013 – Polemic tweet
SITUATION
05/09/2013
IFIP Interact 2013 – Polemic tweet
Previous process
1. Videotape the seminar
2. Manually annotate and tag
3. Publish the video online and let user annotate
06/09/13 IFIP Interact 2013 – Polemic tweet
PROBLEM
05/09/2013 IFIP Interact 2013 – Polemic tweet
05/09/2013
IFIP Interact 2013 – Polemic tweet
Problem
2. Annotating a video manually is boring and time-consuming
1. Browsing a video after a conference is difficult
3. Tagging and structuring annotations are even more boring
Inspiration: Microblogging activities
05/09/2013
IFIP Interact 2013 – Polemic tweet
Communication devices
Motivation
05/09/2013
IFIP Interact 2013 – Polemic tweet
3. Provide an easily accessible system from annotation to video analysis.
2. Provide a visual backchannel to incite people to tag their tweets.
1. Engage the audience: crowdsource video annotation and tagging by tweet.
A certain type of tag: Sentiments
06/09/13 IFIP Interact 2013 – Polemic tweet
Current approaches to extract sentiments
Human analysis
Natural Language Processing
Our need
Fast Language agnostic Accurate Cheap
06/09/13 IFIP Interact 2013 – Polemic tweet
Why not ask the tweet autor ?
Cost Benefit
- Fast - Language agnostic - Accurate - Cheap, cost is distributed
- Require user effort - Low recall
DESIGN
05/09/2013 IFIP Interact 2013 – Polemic tweet
Design Goals:
05/09/2013 IFIP Interact 2013 – Polemic tweet
1. To crowdsource conference video tagging with structured sentiment metadata.
2. To engage audiences in the tagging process.
3. To visualize annotations for browsing and analyzing the video.
0. Service Design
1. A special syntax to enhance tweets
4. A video player with a visualization
2. A social protocol to organize the event over time
3. A real time visualization to read and write tweets
05/09/2013 IFIP Interact 2013 – Polemic tweet
1. Syntax properties and description:
Green Agreement ++
Red Disagreement --
Yellow References ==
Blue Questions ??
Tag Semantic Color
Simple
Brief
Neutral Easy to parse
Expressive
Unambiguous
Design Rational
2. Social Protocol
05/09/2013 IFIP Interact 2013 – Polemic tweet
A. Before the talk: Instruct the crowd.
B. During the talk: Crowdsource the video tagging with a backchannel.
C. After the talk: Publish on a web video player.
Instruct the crowd
05/09/2013 IFIP Interact 2013 – Polemic tweet
The network access policy
The Twitter hashtag
The website URL
The tags
3. Backchannel: Real Time Visualization
3. Backchannel: Real Time Visualization
3. Backchannel: Real Time Visualization
3. Backchannel: Real Time Visualization
3. Backchannel: Real Time Visualization
3. Backchannel: Real Time Visualization
3. Backchannel: Real Time Visualization
4. Metadata Video Player
http://goo.gl/zyJYCZ
4. Metadata Video Player
http://goo.gl/zyJYCZ
4. Metadata Video Player
http://goo.gl/zyJYCZ
4. Metadata Video Player
http://goo.gl/zyJYCZ
DEPLOYMENT
05/09/2013 IFIP Interact 2013 – Polemic tweet
25 to Attendees per event
05/09/2013 IFIP Interact 2013 – Polemic tweet
27 Events
9088 Tweets recorded
300 1012 Unique Twitter users
Deployment
EVALUATION
05/09/2013 IFIP Interact 2013 – Polemic tweet
05/09/2013 IFIP Interact 2013 – Polemic tweet
Questions
1. Is the system sufficiently engaging?
3. What is the impact of presenting tweets and tags on a web video player?
2. Does the visual backchannel incite people to add tags?
Data Collection
05/09/2013
IFIP Interact 2013 – Polemic tweet
Record tweets sent during the events
Log the user interaction on the web video player
Two web surveys, one for participants, one for organizers
RESULT
IFIP Interact 2013 – Polemic tweet 05/09/2013
Question 1: Is the system sufficiently engaging?
05/09/2013 IFIP Interact 2013 – Polemic tweet
0.2 to 7.94 Tweets per minute
0.12 to 2.13 Tags per minute
40% Tweets using our syntax
35 to 45 % Of all individuals used our syntaxe
05/09/2013
IFIP Interact 2013 – Polemic tweet
Question 1: Is the system sufficiently engaging?
• Type of Audience. (size, culture, equipment, incentive, distribution) • Type of Speaker and Twitter Reaction. • Type of Content. • Observance of the PT Protocol.
Influential factors for engagement
Question 2: Does the visual backchannel incite people to add tags?
05/09/2013
IFIP Interact 2013 – Polemic tweet
05/09/2013
IFIP Interact 2013 – Polemic tweet
Question 3: What is the impact of presenting tweets and tags on a web video player?
05/09/2013
IFIP Interact 2013 – Polemic tweet
Question 3: What is the impact of presenting tweets and tags on a web video player?
Visualization User seek activity
?
05/09/2013
IFIP Interact 2013 – Polemic tweet
Question 3: What is the impact of presenting tweets and tags on a web video player?
TODO: Figures p < 0.1 p < 0.1 p < 0.1
0.1 < p < 0.5 0.1 < p < 0.5 P > 0.1
CONCLUSION
05/09/2013 IFIP Interact 2013 – Polemic tweet
The Evaluation was challenging
05/09/2013
IFIP Interact 2013 – Polemic tweet
Deployed in the wild Long period of time Design change over time Real life users Real life setting
Because
Result!
1.The system engaged the audience to provide data for crowdsourced video tagging.
2. The visual backchannel incited people to tag their tweets and thus provided an annotation structure.
3. The media player augmented with the annotated tweet visualization was considered a significant improvement over traditional video players.
Next steps
05/09/2013
IFIP Interact 2013 – Polemic tweet
As classroom presentations.
Synchronous web seminar.
Public debates, and social TV.
Possible optimizations:
05/09/2013 IFIP Interact 2013 – Polemic tweet
Shared attention. Tag properties. Scalability, user interface design and system.
Subsequent work:
05/09/2013 IFIP Interact 2013 – Polemic tweet
http://goo.gl/c2iqg0
Bubble-TV: Live Visual Feedback for Social TV Broadcast
Visual Sedimentation: Data stream visualization technique
http://goo.gl/KvllnO
User supplied sentiment in tweets
http://goo.gl/XXVzJb
MORE INFOS: + open source + details
THANKS: To people who used the system and people who fund this work:
Thank you !
Contact : [email protected] http://www.cybunk.com Team : http://www.aviz.fr http://iri.centrepompidou.fr
goo.gl/wKG9Sg
THE END
05/09/2013 IFIP Interact 2013 – Polemic tweet
Survey Result
96% (25) of respondents attended at least one conference had already used twitter at conferences ( 7% only for reading)
86% (24) reported familiarity with the PT syntax 21% (6) with the LiveTweet interface 35% (14) with the web video player visualization
timeline.
05/09/2013
WIID: Who Is Interaction Design?
Survey Result
In the survey 14 users reported to know what the Tweet Timeline Visualization is.
05/09/2013
WIID: Who Is Interaction Design?
• 64% (9) of these found that provides useful information • 79% (11) agree or strongly agree that the visualization helps them to browse the video • 86% (12) would recommend PT to a friend.
# to view a part of video with : – many tweets: 57% (8) – positive opinions (++): 29% (4) – negative opinions (–): 43% (6) – questions (??): 21% (3) – references (==): 21% (3)
Cost and benefit of tagging technics
06/09/13 IFIP Interact 2013 – Polemic tweet
- Time consuming - Cost is proportional - Hight recall (100%)
- Mostly targeted at English - Not “off the shelves” - Precision problem - Cost is proportional
- Language agnostic - Accurate
- Fast
Cost Benefit
Mechanical turk
- Language agnostic - Accurate - Fast - Cheap, cost is distributed
- Engage user - Low recall
Natural Language Processing