social network analysis

37
SOCIAL NETWORK ANALYSIS SAFI JANG RABBIYA IJAZ SHAZA KHAN RANA KASHAN OSAMA MASOOD

Upload: mabli

Post on 26-Jan-2016

51 views

Category:

Documents


0 download

DESCRIPTION

SOCIAL NETWORK ANALYSIS. SAFI JANG RABBIYA IJAZ SHAZA KHAN RANA KASHAN OSAMA MASOOD. WHAT IS SNA ?. A social network analysis examines the structure of social relationships in a group to uncover the informal connections between people. - PowerPoint PPT Presentation

TRANSCRIPT

Page 1: SOCIAL NETWORK ANALYSIS

SOCIAL NETWORK ANALYSIS

SAFI JANGRABBIYA IJAZSHAZA KHANRANA KASHANOSAMA MASOOD

Page 2: SOCIAL NETWORK ANALYSIS

WHAT IS SNA ?

A social network analysis examines the structure of social relationships in a group to uncover the informal connections between people.

It is the mapping and measuring of relationships and flows between people, groups, organizations, computers, URLs, and other connected information/knowledge entities

2

Page 3: SOCIAL NETWORK ANALYSIS

But SNA is not just a methodology

It is a unique perspective on how society functions

3

3

Page 4: SOCIAL NETWORK ANALYSIS

BASIC CONCEPTS

4

4

Page 5: SOCIAL NETWORK ANALYSIS

REPRESENTING NETWORKS

NODES are the individual actors within the networks

EDGES are the relationships between the actors

5

5

Page 6: SOCIAL NETWORK ANALYSIS

6

6

Page 7: SOCIAL NETWORK ANALYSIS

IDENTIFYING STRONG/WEAK TIES IN THE NEWTWORK

ADD WEIGHTS TO EDGES . WEIGHTS COULD BE : FREQUENCY OF INTERACTION NUMBER OF ITEMS EXCHANGED DISTANCE , ETC

7

7

Page 8: SOCIAL NETWORK ANALYSIS

HOW TO IDENTIFY KEY/CENTRAL NODES

To understand networks and their participants, we evaluate the location of actors in the network. Measuring the network location is finding the centrality of a node.

8

8

Page 9: SOCIAL NETWORK ANALYSIS

DEGREE CENTRALITY

It is the number of direct connections a node has. In the network above, Diane has the most direct connections in the network, making her the 'connector' or 'hub' in this network. For a graph G: = (V,E) with n vertices, the degree centrality Cd(v) for vertex v is:

9

9

Page 10: SOCIAL NETWORK ANALYSIS

BETWEENNESS CENTRALITY

While Diane has many direct ties, Heather has few direct connections Yet, she has one of the best locations in the network -- she is between two important constituencies.

where σst is the number of shortest paths from s to t, and σst(v) is the number of shortest paths from s to t that pass through a vertex v

the golden rule of networks is: Location, Location, Location ! 10

10

Page 11: SOCIAL NETWORK ANALYSIS

CLOSENESS CENTRALITY

•Fernando and Garth have fewer connections than Diane, yet the pattern of their direct and indirect ties allow them to access all the nodes in the network more quickly than anyone else.

•They are in an excellent position to monitor the information flow in the network !11

11

Page 12: SOCIAL NETWORK ANALYSIS

BOUNDARY SPANNERS

Nodes that connect their group to other sub-groups in a network

Boundary Spanners are those in a social network who can span across various social networks.

They can be essential to the flow of novel information.

Boundary spanners can be used by the news

media in setting its agenda by getting information and ideas to a variety of social networks, rather than just one.

12

12

Page 13: SOCIAL NETWORK ANALYSIS

CHARACTERISING NETWORK STRUSTURES

ReciprocityThe ratio of the number of relations which are reciprocated (i.e. there is an edge in both directions) over the total number of relations in the network

Indicator of the degree of mutuality

13

13

Page 14: SOCIAL NETWORK ANALYSIS

DensityA network’s density is the ratio of the number of edges in the network over the total number of possible edges between all pairs of nodes

It is a common measure of how well connected a

network is

14

14

Page 15: SOCIAL NETWORK ANALYSIS

APPLICATIONS OF SNA IN THE REAL WORLD

In OrganizationsIn Crime InvestigationIn Health CareIn Social Networking WebsitesIn Preventing TerrorismIn Fraud Detection

15

15

Page 16: SOCIAL NETWORK ANALYSIS

SNA In Organizations

Through research it has been found out that most of the work done in an organization is through informal communication channels

Mapping and analyzing these informal channels helps managers understand how communication actually takes place in an organization

16

16

Page 17: SOCIAL NETWORK ANALYSIS

SNA also helps in identifying hidden links and helps in improving the communication flow.

17

17

Page 18: SOCIAL NETWORK ANALYSIS

SNA In Social Networking Websites SNA used for better

recommendations

18

18

Page 19: SOCIAL NETWORK ANALYSIS

SNA In Health Care

Information, disease pathogens, ideas, money, and many other things can flow across networks

Hidden patterns of genetic disease transferred from one generation to another

Diseases transfer from physical contact

19

19

Page 20: SOCIAL NETWORK ANALYSIS

SNA In Preventing Terrorism By mapping the social network of the

subjects. Example

9/11 Mumbai Attacks

20

20

Page 21: SOCIAL NETWORK ANALYSIS

21

Page 22: SOCIAL NETWORK ANALYSIS

SNA In Crime Investigation Very much similar to terrorism

Privacy preserving SNA When 2 or more agencies are involved When laws keep you from sharing data Computation o important metrics while

keeping the entire network unknown

22

22

Page 23: SOCIAL NETWORK ANALYSIS

23

23

Page 24: SOCIAL NETWORK ANALYSIS

SNA In Fraud Detection

Build Data Repository SNA provides top-down and bottom-

up analysis for uncovering previously hidden linkages

It detects risky networks

24

24

Page 25: SOCIAL NETWORK ANALYSIS

SMALL WORLD EXPERIMENT

The theory states that everybody on this planet is separated by only six other people.

The "Six Degrees" Facebook application calculates the number of steps between any two members

25

25

Page 26: SOCIAL NETWORK ANALYSIS

SNA TOOLS

26

26

Page 27: SOCIAL NETWORK ANALYSIS

Pajek A program package designed for

Windows, Pajek is most commonly used to analyze large and complex networks.

Pajek also provides tools for analysis and visualization of: collaboration networks organic molecule in chemistry Internet networks data-mining (2-mode networks), etc.

27

27

Page 28: SOCIAL NETWORK ANALYSIS

Analysis in Pajek

Analyses in Pajek are performed using six data structures:

Network – main object (vertices and lines - arcs, edges);

Partition – nominal property of vertices (gender);

Vector – numerical property of vertices; Permutation – reordering of vertices; Cluster – subset of vertices (e.g. a cluster from

partition); Hierarchy – hierarchically ordered clusters and

vertices.

28

28

Page 29: SOCIAL NETWORK ANALYSIS

Using Pajek

Some properties of nice pictures of networks:

Not too many crossings of lines A graph that can be drawn without

crossing of lines is called a planar graph Not too many small angles among lines

that have one vertex in common Not too long or too short lines (all lines

approximately of the same length) Vertices should not be too close to lines

29

29

Page 30: SOCIAL NETWORK ANALYSIS

Using Pajek

Two approaches to deal with large networks: Local view: obtained by extracting subnetwork

induced by selected cluster of vertices. Example: Students in the class: relations among

boys (girls) only. Global view: obtained by shrinking vertices in

the same cluster to new (compound) vertex. In this way relations among clusters of vertices are shown. Example: Students in the class: compound

relation between boys and girls (number of arcs between the two groups).

30

30

Page 31: SOCIAL NETWORK ANALYSIS

Using Pajek

31

31

Page 32: SOCIAL NETWORK ANALYSIS

Goals of Pajek

The main goals in the design of Pajek are: To support abstraction by (recursive)

decomposition of a large network into several smaller networks that can be treated further using more sophisticated methods;

To provide the user with some powerful visualization tools;

To implement a selection of efficient (subquadratic) algorithms for analysis of large networks.

32

32

Page 33: SOCIAL NETWORK ANALYSIS

Twitter & SNA Tweetwheel: Allows you to view and analyze

relationships within a network. Below is a screenshot taken of the analysis of a Twitter Network.

33

33

Page 34: SOCIAL NETWORK ANALYSIS

Facebook & SNA: TouchGraph

34

34

Page 35: SOCIAL NETWORK ANALYSIS

Facebook & SNA: TouchGraph

35

35

Page 36: SOCIAL NETWORK ANALYSIS

REFERENCES

https://docs.google.com/viewer?a=v&pid=gmail&attid=0.1&thid=12cee7d02cc18b01&mt=application/pdf&url=https://mail.google.com/mail/?ui%3D2%26ik%3D06a2014ff8%26view%3Datt%26th%3D12cee7d02cc18b01%26attid%3D0.1%26disp%3Dattd%26realattid%3Df_ghol3ixg0%26zw&sig=AHIEtbT45SzIJqlr4ChSIpn8MLLaHo2fgw&pli=1

http://www.orgnet.com/sna.html36

36

Page 37: SOCIAL NETWORK ANALYSIS

http://www.davidkelly.ie/2008/09/19/twitter-social-network-analysis-apps/

vlado.fmf.uni-lj.si/pub/networks/pajek/doc/pajekman.pdf

http://www.davidkelly.ie/2008/09/19/twitter-social-network-analysis-apps/

37

37