ieee visap bkang

22
TweetProbe A Real-Time Microblog Stream Visualization Byungkyu Kang, George Legrady and Tobias Höllerer FourEyes Lab University of California Santa Barbara

Upload: jay-byungkyu-kang

Post on 01-Nov-2014

310 views

Category:

Education


2 download

DESCRIPTION

TweetProbe : A Real-Time Microblog Stream Visualization Framework

TRANSCRIPT

Page 1: Ieee visap bkang

TweetProbeAReal-TimeMicroblogStreamVisualization

Byungkyu Kang, George Legrady and Tobias HöllererFourEyes Lab

University of CaliforniaSanta Barbara

Page 2: Ieee visap bkang

Motivation

•Microblogs are Valuable Source

- To selectively consume news and information

- To analyze social dynamics

•Scalability Issue

- Difficult to assess and comprehend enormous data

•Temporal Topics

- Majority of contents in microblogs are transient topics

Page 3: Ieee visap bkang

Research Question

•Novel visualization design on real-time microblog stream

- How to effectively visualize transient trending topics?

Page 4: Ieee visap bkang

Related Work

• Social Stream Filtering and Detection

- ‘TwitterMonitor’ takes user feedback (Mathioudakis and Koudas 2010)

- Storyboard based Shared Media Curation (Milicic et al. 2013)

- ‘Catstream’ employes user profiling approach (Esparza et al. 2013)

• Real-time Visualization

- Network Intrusion Detection (Cyber-Security Situational Awareness)

- ‘Tweetping’ Geo-spatial mapping of real-time messages (http://tweeping.net)

- ‘We feel fine’ visualizes emotional web (Kamvar and Harris, 2011)

Page 5: Ieee visap bkang

SystemArchitecture

Back-end Data ProcessingFront-end Visualization Layer

Page 6: Ieee visap bkang

FRONT-END VISUALIZATIONBACK-END DATA PROCESSING

System Architecture

Real-time Real-time Tweet StreamTweet Stream

Tw

itte

r Str

eam

ing

API

UD

P

JSON ParsingExtract Metadata

StatusListener

Text / Metadata Processing

Burst Detection

Sentiment Extraction

Storage

RT TWUPDATE

SORT

tempRT

tempTW

Cache

Loop

#Query

Sentiment Map

Emerging RetweetRanking

Retweet CountRanking

Top HashtagRanking

Page 7: Ieee visap bkang

DesignConsiderations

Page 8: Ieee visap bkang

4 View Modes

Sentiment Map

Emerging Retweet Ranking

Hashtag Ranking

Retweet Count

Ranking

Page 9: Ieee visap bkang

Design - Motivation•Rain Drops

- Stream of Information : Flow in a Continuous Medium (Stream)

- Message : Discontinuous Element in a Flow

Wall paper image is an exerpt from http://www.paqoo.com

““Continuum of DiscontinuityContinuum of Discontinuity””

Page 10: Ieee visap bkang

Logarithmic Timeline

The Histomap of Evolution

The former logarithmic time- line visualization of geologic and human history, by John

B. Sparks (1932)

Logarithmic Timeline

The logarithmic time in TweetProbe shows the original posting time of messages focusing more on recent events

Page 11: Ieee visap bkang

Visualization

Sentiment MapEmerging Retweet RankingRetweet Count RankingHashtag Ranking

Page 12: Ieee visap bkang

Sentiment Map

•Rain-drop Like Message Visualization

- Tweet = Rain drop + Circular Wave

•Potential of Dissemination

- # Follower Defines Drop Size and Duration Time

•Visual Mapping

- Each Drop is Spatially Mapped to Grid

- Color-coded Sentiment Score

Page 13: Ieee visap bkang

Real-time Ranking Visualization

•Main Visual Components

- Sliding animation to reveal emerging retweets.

- Logarithmic timeline to show the ‘freshness’ of messages

EMERGING RETWEET

Transient emerging tweets

TOP-COUNTRETWEET

Top retweets in CDF

EMERGINGHASHTAGS

Transient emerging #hashtags

Page 14: Ieee visap bkang

Emerging vs Top Retweets (1)

•A shows n/∆t

- Easy to detect transient trending message

- Emerging Retweet Ranking

•B shows ∑n

- Cumulative Distribute Function (CDF) of (a)

- Retweet Count Ranking

#m

sg

Time tt

#m

sg

Time tt

A

B

Page 15: Ieee visap bkang

Emerging Retweet Ranking

•Top N emerging retweets

- n/∆t : Number of binned RT within a time-window

•Sliding animation shows transition in rank

•Color-coded with markers in timeline

Page 16: Ieee visap bkang

Retweet Count Ranking

•Top N retweets

- ∑n : Shows top RTs (RT counts in CDF)

• Incoming RTs in real-time

- Shows only alive retweets

Page 17: Ieee visap bkang

Hashtag Ranking

•Top N hashtags

- Emerging topics of messages

- Text size is mapped with its ratio of hashtag count

Page 18: Ieee visap bkang

Example: #royalbaby

#royalbaby22nd of July, 2013

- 900,000 hashtags (#royalbaby)

- 25,300 Tweets/min at peak

- More than 2 million mentions of the news

https://blog.twitter.com/en-gb/2013/royalbaby-0

Page 19: Ieee visap bkang

ConclusionTweetProbe

Page 20: Ieee visap bkang

Conclusion

•Novel visualization design

- Real-time visualization for trending microposts and topics

- Conceptualize ‘Continuum of Discontinuity’

- Metaphoric visual components such as rain drops

- Color-coded sentiment visualization

- Logarithmic timeline with sliding animation

- Catch transient emerging topics using 3 ranking view modes

Page 21: Ieee visap bkang

Research Question Revisited

•Novel visualization design on real-time microblog stream

- How to effectively visualize transient trending topics?

Multi-thread based visualization

Identify emerging messages / hashtags with sentiments

New visual components (rain drop and sliding window)

Page 22: Ieee visap bkang

Thank You!

Come and try TweetProbe@Art Program

Today at 6pmA705