The Spread of Media Content through the Blogosphere

1
The Spread of Media Content through the
Blogosphere
TU Berlin Deutsche Telekom Lab
Flash Floods and Ripples
Meeyoung Cha
Juan A. Navarro Max Planck Institute for Software
Systems (MPI-SWS)
Hamed Haddadi
ICWSM Data Challenge 2009
2
Motivation

• Blogs play a significant role in todays Internet
  culture
• Blogs are used for information propagation
  purposes
• Discuss political issues
• Review new products and online contents
• Form communities and special interest groups
• Increasingly, media content is shared through
  blogs

How does content spread in blogs? What kinds of
content are shared?
3
Our goal

• Characterize how the structure of the blogosphere
  influences the patterns of content spreading
• 1. Understand the structure of the blogosphere
• Is the structure ideal for content dissemination?
• 2. Understand the spreading patterns of content
• What types of content spread?
• How quickly does content spread?

4
Part1. Measurementmethodology
Part2. Analysis of network properties
Part3. Analysis of spreading patterns
5
Spinn3r dataset

• Extracted post URL, site, host, language,
  timestamps, etc.
• Step1 Focus on top 15 blog domains
• Step2 Scrape content to find embedded HTML
  links
• Code available at http//www.mpi-sws.org/jnavarr
  o/tools/
• Limitations
• Comments and blogrolls missing
• Some blogs only post summaries
• Only used dataset with numbered tiers

6
Step1 Top 15 blog sites

Total
7
Step2 Extracting HTML links
Links tomedia content
Links toother blogs
8
Part1. Measurementmethodology
Part2. Analysis of network properties
Part3. Analysis of spreading patterns
9
Network of blogs
Directed network of 85,013 nodes and 129,079 edges
A
B
10
Network structure

• Average node degree 1.5
• Power-law degree distribution
• 6 of links are reciprocal
• 35 of links cross blog domains
• 7 of links cross language boundaries

73 of blogs in the largest connected
component
11
Network structure 2

• Density Ratio of observed links, out of all
  possible links

Network structure is more sparse than social
networks
12
Insights for information propagation

• Sparse structure power-law degree distribution
• Clear preference for bloggers to particular
  topics or sources
• Trend setters (high in-degree) and recommenders
  (high out-degree)
• Potential factors that can limit spreading
• Blog domains had no visible effect on linking
• Language barriers inhibit the flow of information

13
Part1. Measurementmethodology
Part2. Analysis of network properties
Part3. Analysis of spreading patterns
14
Spreading of media content

• What types of content are shared?
• How quickly does information spread?

media
15
Types of content shared
16
Popularity of YouTube videos

• Video popularity follows a power-law
  distribution
• Very large diffusion processes exist
• Preferential attachment may drive linking

17
Popular video categories

• We downloaded metadata of top 10,000 videos

Musicmost popular
Still spread!
Keen onpolitics
18
Time lag in the spread of videos
Flash floods
Ripples
19
Example spreading pattern
Blogs linking the same video are connected
Diffusion through the blogosphere

• McCains political campaignlinked by 79 blogs

20
Insights from spreading patterns

• Videos in different genres spread with very
  different patterns
• Flash floods found quickly and spread rapidly
• Ripples took longer to spread, re-discovered
  years after upload
• Diffusion through links in the blogosphere
• 24 of videos had any spreading in the blog graph
• Other spreading factors featuring and search

21
Part1. Measurementmethodology
Part2. Analysis of network properties
Part3. Analysis of spreading patterns
22
Conclusion

• Identified spreading patterns and factors that
  limit spreading
• Blogs serve as a medium to filter and spread
  media content
• Potential implication Recommendation systems
  can take into account and exploit different
  spreading patterns
• Future work spreading patterns of other types of
  content