• No results found

Crawling and Detecting Community Structure in Online Social Networks using Local Information

N/A
N/A
Protected

Academic year: 2021

Share "Crawling and Detecting Community Structure in Online Social Networks using Local Information"

Copied!
11
0
0

Loading.... (view fulltext now)

Full text

(1)

Crawling and Detecting Community

Structure in Online Social Networks

using Local Information

Norbert Blenn, Christian Doerr, Bas Van Kester and Piet Van Mieghem

TU Delft - Network Architectures and Services (NAS)

(2)

Outline

“In order to find communities in a graph one needs the full graph.”

“Crawling large Datasets like Online Social Networks takes very long.”

Facebook: 901 million (active April 2012), Twitter: Over 140 million (active March 2012) Ideal Crawling with one PC: 1s per request: Facebook 29years, Twitter: 4,5years

1.

Crawling

BFS/DFS/RFS

Mutual Friend Crawling (MFC)

• the Reference Score

• Performance

2.

Community Detection

The Reference Score

Compared to well known methods

3.

Conclusion

(3)

Crawling Online Social Networks

via Breadth/Depth first Search

standard Breadth First Search

1 2 3 4 5 6 7 8 9 10 11 1 2 3 4 5 6 7 8 9 11 10

What most people do (Random First Search RFS) standard Depth First Search

1 2 3 4 i i2 n i1

But unfortunately Social Networks are not tree like using a BFS/DFS/RFS leads to a sampling

bias by using any of these methods and the fact one has to “wait” until the full graph is crawled to detect communities.

(4)

Crawling Online Social Networks

via Mutual Friend Crawling

Our proposed method “Mutual Friend Crawling” (MFC) overcomes this situation by crawling a Graph from any given seed point, Community wise.

MFC is based on BFS/DFS plus one assumption:

• the degree of neighboring nodes is known

• and keeps a “Reference Score” SR

• This in the search trajectory the next node to be next node to visit is the one having the highest SR

(5)

Crawling Online Social Networks

via Mutual Friend Crawling

Example:

Starting with node 2: its neighbors are 0,1,3,4 with degrees

the Reference Scores are: 0:0.2, 1:0.2, 3:0.25, 4:0.2 Lets take 4

(6)

Crawling Online Social Networks

via Mutual Friend Crawling - Performance

BFS (blue) DFS(green) MFC(red)

(7)

How is the reference Score behaving while MFC is traversing the graph.

• As there MFC stays in communities the reference score is always increasing denoting that the community is tightly connected. As soon as there is a drop in SR a new

community is been found.

• This “drop” is largest if an expressed community structure can be found. Otherwise it will be small

Community Detection in OSNs

(8)

Community Detection in

Online Social Networks

via Mutual Friend Crawling

Problem of misclassification

• If starting with a hub (11), the nodes 10 and 21 are classified as being in the same community as node 11 (the first community).

Solution:

• after “finishing” a community

check if the nodes in this community should really be in this community

(9)

Conclusion

& Future Work

We proposed an algorithm to crawl online social networks community wise

• in order to minimize sampling bias in communities.

• to be able to analyze data while still crawling the network The algorithm detects communities,

• (even for directed and weighted graphs) Future work:

• overlapping communities

• formalism to understand the drop in the reference score in order to catch how structured a graph is. (compared to modularity)

(10)

Thank you for your attention

Questions

Delft University of Technology Faculty of Electr. Engineering Dept. of Telecommunication Mekelweg 4 2628 CD Delft The Netherlands Room: EWI 19.240

(11)

Crawling Online Social Networks

In order to measure the performance we were looking for “ground truth” datasets

As it is very hard to find some real world datasets where the community partition is known we came up with a “Cluster Graph Generator”

via Mutual Friend Crawling - Performance

1. node generation and slot assignment 2. assigning nodes to clusters

3. creating the links

References

Related documents

6.1.1 The objective of the incentive is to support projects with green technology upgrades and business development activities that will lead to cleaner

The upper part shows the prediction (red line, higher value for higher probability of death) and the trends of intracranial pressure (ICP, blue line), mean arterial pressure

In this thesis, machine learning techniques will be applied to peptidomics data from patients with septic shock, to attempt to identify patterns within it and learn and rank

Among these firms, the likelihood of diversification is between 15.7 and 23.2 percentage points higher than for those firms banking with state-owned banks (SBI and nationalized

AAT: Aachener Aphasie Test; ACE-R: Addenbrooke ’ s Cognitive Examination; AD: Alzheimer ’ s disease; ADAS-CoG: Alzheimer ’ s Disease Assessment Scale-Cognition; ADL: Basic activities

Stephen Sundlof: Yes, and I think as we discussed earlier we are trying to run that down right now to find out, you know, if there are any other products that this company

Huntington Landmark Senior Adult Community Association 20880 Oakridge Lane, Huntington Beach, CA 92646 Architectural Control Committee (ACC) Specifications.. Specification 1

 Internal auditors: The Institute of Internal Auditors (IIA) (2011) defines the task of internal auditing as an independent, objective assurance and consulting