Why We Twitter

1
Why We Twitter?

• Understanding Microblogging Usage and Communities

Akshay Java Tim Finin University of Maryland, Ba
ltimore County
Xiaodan Song Belle Tseng NEC Laboratories Americ
a Inc.
2
What is Twitter?

• Micro-Blogging, Social Networking Service
• Users send updates/tweets via SMS, IM or Web
• Light-weight blogging, short posts
• (140 characters or less)

3
What is Twitter?
Current Status
Twitter post
Friends
Easily share status messages
4
MICRO-BLOGS
5
Ambient Intimacy

• Ambient intimacy is about being able to keep in
  touch with people with a level of regularity and
  intimacy that you wouldnt usually have access
  to, because time and space conspire to make it
  impossible.
• - Leisa Reichelt
• Twitter, Flickr and other Social Media sites.

6
Twitter! Twitter! Twitter!
Disclaimer No association to Twitter Inc/
Obvious corp.
7
Motivation

• Goal Study Micro-blogging usage, user-intentions
  and community structure.
  
• Motivation
• What is the excitement about?
• What is the user-intention in micro-blogging?
• How is this form of communication different?

8
Outline
Why We Twitter?
Micro-blogging Usage
User Intentions
Community-based Intentions
Content-based Intentions
9
Social Media

• Social media describes the online technologies
  and practices that people use to share opinions,
  insights, experiences, perspectives with each
  other.
• Wikipedia 07

10
Social Media

• Social media describes the online technologies
  and practices that people use to share opinions,
  insights, experiences, perspectives and engage
  with each other.
• Examples
• Blogs, Wikis, Flickr, YouTube, Micro-blogs

11
Outline
Why We Twitter?
Micro-blogging Usage
User Intentions

• USAGE
• Popularity of Twitter?
• Is it very different from blogs?
• What is its adoption across the world?

Community-based Intentions
Content-based Intentions
12
Dataset Description

• Constructed by monitoring the Public timeline of
  posts
  
• 2 month period (04/07-05/07)
• 1,348,543 posts
• 76,177 Users
• 829,053 friend relation between them
• Used the Twitter API for accessing user social
  network
  

13
The Twitter Phenomenon

• Twitters popularity increased after winning the
  Web award at SXSW conference, March 2007.

Currently, Twitter is the most popular
micro-blogging tool.
Source ComScore
14
Growth Rate
Dedicated user-base generating new updates/tweets.
Slow down in growth of new users joining the
network.
15
Network Statistics
Degree distributions similar to Blogs, Web
16
Network Statistics
Network Statistics
However, higher reciprocal linking and clustering
coefficient indicates mutual acquaintance.
17
User Retention
User has at least one post in the week
ACTIVE
RETAINED
Active user, who reposts the following week
Shows a continued activity and retention on
Twitter
18
Geographical Spread
Cross Continent Social Network
Social network crosses geographical boundaries
Continental Network Properties
Top Cities Tokyo, NY, SF, Seattle, LA, Chicago,
Toronto, Austin, Singapore, Madrid
Global popularity
Higher reciprocity in Europe and Asia
19
Outline
Why We Twitter?
Micro-blogging Usage
User Intentions

• USER INTENTION
• What are we using Twitter for?
• Are there communities?
• If so, what are the community-level intentions?

Community-based Intentions
Content-based Intentions
20
User Intentions

• Using Link Structure
• Information source
• Such users have a number of followers ( include
  bots like forecast, stock, CNN breaking news,
  etc.)
  
• Information seeker
• Such users may post infrequently, but have a
  number of connections
  
• Friendship relation
• Most users social network is within mutual
  acquaintances
  
• Using Content
• Daily chatter dinner, work,
  movie
  
• Conversations (_at_) Reply to a specific
  person _at_ev
  
• Sharing URLs Sharing URLs through
  tinyURL
  
• Commenting on News Number of automated RSS to
  Twitter bots posting news
  

21
Communities in Twitter
Hubs and Authorities

• First find Hubs and Authorities using HITS
• Consider only bidirectional links
• Clique Percolation Method (CPM) to find
  overlapping communities

A-list bloggers and personalities are on Twitter
Scobleizer, SteveRubel, JasonCalacanis,
SteveJobs
JohnEdwards, BarakObama, et al.
22
Clique Percolation Method (CPM)
Example Gaming Community

• Basic Idea
• Two nodes belong to the same community if they
  can be connected through adjacent k-cliques.

I. Derenyi, G. Palla, and T. Vicsek. Clique
percolation in random networks. Physical Review
Letters, 94160202, 2005. G. Palla, I. Derenyi, I
. Farkas, and T. Vicsek. Uncovering the
overlapping community structure of complex
networks in nature and society. Nature, 435814,
2005.
23
com175 twitter134 just133 like86 good82 tiny
url75 time74 new74 jasona73 going68 day63 do
n61 work58 think56 ll54 scottw54 today52 hka
rthik50 nice49 getting47 got47 really46 yeah
44 need43 watching41 love41 night40 home40
com198 twitter132 just109 tinyurl87 going59
blog56 like55 good51 new50 url50 day49 peopl
e46 time45 today45 google42 don41 think40 ni
ght38 ll38 need35 got33 ireland33 great31 lo
oking29 work29 thanks28 video26
INFORMATION HUB
com93 twitter74 just35 new32 tinyurl29 going
24 ll22 blog21 jaiku21 don21 leo21 flickr21
like19 video18 google18 today18 feeds18 gett
ing16 yeah16 good15 people15
com93 twitter76 tinyurl34 just32 new28 video
26 going24 ll22 jaiku22 blog21 leo21 like19
don19 gamerandy19 yeah18 google17 live16 peo
ple16 got16 know15 time15
com121 twitter76 just50 ustream43 tv42 live
42 today39 hawaii36 day33 new33 time33 good
33 video32 leo30 work30 like28 watching28
tinyurl28
Information Source Communities connected via
Robert Scoble, an A-list blogger
24
Key Terms going222 just218 work17
0 night143 bed140 time139 good137 com130 lost
124 day122 home112 listening111 today100 new
98 got97 gspn92 watching92 kids88 morning81 t
witter79 getting77 tinyurl75 lunch74 like72 p
odcast72 watch71 ready70 tv69 need64 live61
tonight61 trying58 love58 cliff58 dinner56
INFORMATION BRIDGE
Key Terms
just312 com180 work180 time149 listening14
7 home145 going139 day134 got126 today124 goo
d116 bed114 night112 tinyurl97 getting88 podc
ast87 dinner85 watching83 like78 mass78 lunch
72 new72 ll70 tomorrow69 ready64 twitter62 w
orking61 tonight61 morning58 need58 great58 f
inished55 tv54
Information Source, Information Seeker Different
roles in different communities
25
STAR NETWORKS / SMALL CLIQUES
Friendship-relation Small groups among
friends/co-workers
26
Outline
Why We Twitter?
Micro-blogging Usage
User Intentions

• USER INTENTION
• What are the distinctive terms?
• Are there any trends?

Community-based Intentions
Content-based Intentions
27
Wisdom of the Crowds
log-likelihood ratio
Popular topics Activities, Current Events, TV
shows/Entertainment
28
Twitterment
http//twitterment.umbc.edu
Search and Trend analytics on Twittersphere
work
lunch
dinner
coffee
chipotle
lunch
panera
dinner
29
Outlook on Micro-Blogging

• The future is here!
• Twitter,Jaiku,Pownce,FaceBook
• Status message is now public
• Ambient intimacy
• Information sharing
• Thoughts on new applications
• Users can play different roles in different
  communities
  
• Number of updates received can be quite
  overwhelming
  
• New tools and services would benefit from
  allowing greater personalization based on
  user-intentions
  
• e.g. Separating work and friend social network

30
Conclusions

• First study of the Microblogging phenomenon.
• Popularity of Micro-blogging due to the combined
  benefits of
  
• Light-weight blogging
• and the ability to share information in the
  social network.
  
• Main user-intentions
• Information sharing
• Information seeking
• Friendship
• Users generated content includes
• Status updates, daily chatter, sharing
  links/News, etc.
  
• Future Work
• Automatically classifying the different
  intentions.
  
• Finding frequent patterns in community structure.

31

• Thank You!
• Questions?
• Thanks to Twitter Inc. for providing the Twitter
  API.

http//twitter.com/akshayjava
32

• Backup Slides

33
User Intentions