Loading presentation...

Present Remotely

Send the link below via email or IM

Copy

Present to your audience

Start remote presentation

  • Invited audience members will follow you as you navigate and present
  • People invited to a presentation do not need a Prezi account
  • This link expires 10 minutes after you close the presentation
  • A maximum of 30 users can follow your presentation
  • Learn more about this feature in our knowledge base article

Do you really want to delete this prezi?

Neither you, nor the coeditors you shared it with will be able to recover it again.

DeleteCancel

Make your likes visible on Facebook?

Connect your Facebook account to Prezi and let your likes appear on your timeline.
You can change this under Settings & Account at any time.

No, thanks

Analyzing information diffusion and influence on social media

My Master project presentation 2012
by

meriem merry

on 13 June 2013

Comments (0)

Please log in to add your comment.

Report abuse

Transcript of Analyzing information diffusion and influence on social media

Data Representation
Where to need SNA?
History
Experiments
Part 4:
Information diffusion
Part 3:
About SNA
Part 1:
About Networks
Part 2:
Outline
What is SNA?
History
Applications
Data Representation & Visualization
Networks Types
Centrality Metrics
Before Social Media
Information
Opinions
Relationships
Business
Media
The application of the broader field of network science to the study of human relationships and connecting by offering systematic methods to evaluate SM efforts based on scientific evidences.
Social science
Computer science
Organizations, Projects & Teams
Politics, Power & Terrorism
Influence, Diffusion & Contagion
Computer Science & Academia
Leonhard Euler
1736
Auguste Comte
1800
Georg Simmel
1900
Jacob Moreno
1930
Graham Durant-Law
Valdis
Krebs
Marc Smith
L.Barabasi
Types
Network Visualization
Egocentric
Full
Multiplex
Multimodal
Centrality metrics
Degree
Betweenness
Density
Information diffusion
Social Influence
The process of spreading information through members of the network
A phenomenon in which the actions of a user cause his/her friends to behave in similar way
Importance
How d es propagation
take place
Will You follow the Crowd?!
Information cascade or herding
(By Banerjee.,92)
How to understand the diffusion process
Models
Linear Threshold Model
Independent Cascade Model
Epidemic Model
Linear Influence Model
...etc
Definitions
Why study the Flow of information?
Modeling diffusion
Node statute: Active or Inactive
Initial Active Set "Ao"
Algorithm
Models
Tools and Datasets
Results
Conclusions & Perspectives
Results
Conclusion
Why NodeXL
Flexible Import and export
Direct connections to social media
Zoom and scale
Flexible layouts
Easily adjusted appearance
Dynamic Filtering
Powerful vertex grouping
Graph metrics calculations
Task automation
2534 nodes: "Users"
2650 edges: "contact" relationship
Type of network: Egocentric and Explicit
836 nodes: "Videos"
3885 edges: "Commenting" relationship
Type of network: non-egocentric and Implicit
Linear Threshold Model
Independent Cascade Model
Implementation
Tv
Weighted Cascade
How to choose initial adopters "Ao"
High Overall Degree
High Out-degree
High Betweenness
Randomly
Tools and Datasets
LTM
ICM
WCM
LTM
ICM
WCM
The structure of the network affects the diffusion process
(Size, diameter, density, bridges, components)
Choosing the models depends on the type of the network and its relationships
Choosing initial active set can be tricky
Explicit relationships spread the information widely
SNA tools depend on the type of analysis
Time
Combine knowledge
Users' profiles
New modeling algorithm
Maximization
"The important thing in science is not so much to obtain new facts as to discover new ways of thinking about them"
Sir William Bragg, Winner of 1915 Nobel Prize in Physics (1862-1942)
Analyzing Information diffusion and influence in social media networks
Who is linked to Whom??
How can individual's action affect others??
Information Propagation Analysis In Social Media
By: Meriem Laifa
2011-2012
Recently
= Number of existing links / All possible links
How well connected is a network?
= total number of links of a node
How many people can this individual reach directly?
= Fraction of shortest paths
How likely is this person to be the most directed route between two people in the network?
Run 1000 times
Ao = {5,10,15,20}
Influence = sum of active nodes / 1000
Full transcript