Influence et cont...
Follow
Find tag "centrality"
4.6K views | +4 today
Influence et contagion
L'influence et la contagion dans la cyberculture
Curated by luiy
Your new post is loading...
Your new post is loading...
Scooped by luiy
Scoop.it!

Who is central to a social network? It depends on your centrality #measure | #sna #influence #basics

Who is central to a social network? It depends on your centrality #measure | #sna #influence #basics | Influence et contagion | Scoop.it
luiy's insight:

One important feature of networks is the relative centrality of individuals in them.  Centrality is a structural characteristic of individuals in the network, meaning a centrality score tells you something about how that individual fits within the network overall.  Individuals with high centrality scores are often more likely to be leaders, key conduits of information, and be more likely to be early adopters of anything that spreads in a network. 

 

- Individuals who are highly connected to others within their own cluster will have a high closeness centrality.

more...
No comment yet.
Scooped by luiy
Scoop.it!

How to Find the Best Connected Individual in Your Social Network | #SNA #influence

How to Find the Best Connected Individual in Your Social Network | #SNA #influence | Influence et contagion | Scoop.it
Field experiments in rural India have revealed a cheap and simple way to find the best connected individuals in any social network–just ask the people.
luiy's insight:

Banerjee and co made their discovery by studying the network of links between individuals in 75 rural villages in southwest India. They measured these networks by asking people who they visited, who visited them, who they were related to, who they borrowed money from, who they lent money to, and so on.

 

They then asked people in 35 villages the following question: “If we want to spread information about a new loan product to everyone in your village, to whom do you suggest we speak?”

 

The results provide a fascinating insight into the knowledge humans build up about their social networks. When people answered this question (and substantial numbers didn’t), they unerringly identified central individuals within their village.

 

 

 

more...
No comment yet.
Scooped by luiy
Scoop.it!

graph-tool: Efficent network analysis with #python | #SNA #tools

graph-tool: Efficent network analysis with #python | #SNA #tools | Influence et contagion | Scoop.it
graph-tool: Efficent network analysis with python
luiy's insight:

An extensive array of features is included, such as support for arbitrary vertex, edge or graph properties, efficient "on the fly" filtering of vertices and edges, powerful graph I/O using the GraphML, GML and dot file formats, graph pickling, graph statistics (degree/property histogram, vertex correlations, average shortest distance, etc.), centrality measures, standard topological algorithms (isomorphism, minimum spanning tree, connected components, dominator tree, maximum flow, etc.), generation of random graphs with arbitrary degrees and correlations, detection of modules and communities via statistical inference ,,,,,, 

more...
No comment yet.
Rescooped by luiy from SNA - Social Network Analysis ... and more.
Scoop.it!

“Follow the Leader”: A #Centrality Guided #Clustering and Its Application to #SNA

“Follow the Leader”: A #Centrality Guided #Clustering and Its Application to #SNA | Influence et contagion | Scoop.it

"Within graph theory and network analysis, centrality of a vertex measures the relative importance of a vertex within a graph. The centrality plays key role in network analysis and has been widely studied using different methods. Inspired by the idea of vertex centrality, a novel centrality guided clustering (CGC) is proposed in this paper. Different from traditional clustering methods which usually choose the initial center of a cluster randomly, the CGC clustering algorithm starts from a “LEADER”—a vertex with the highest centrality score—and a new “member” is added into the same cluster as the “LEADER” when some criterion is satisfied. The CGC algorithm also supports overlapping membership. Experiments on three benchmark social network data sets are presented and the results indicate that the proposed CGC algorithm works well in social network clustering."


Via João Greno Brogueira
luiy's insight:

In this work, a novel hierarchical clustering algorithm is proposed for social network clustering. Traditional clustering methods, such as -means, usually choose clustering centers randomly, and the hierarchical clustering algorithms usually start from two elements with shortest distance. Different from these methods, this work chooses the vertex with highest centrality score as the starting point. If one does some analysis on social network datasets, one may notice that in each community, there is usually some member (or leader) who plays a key role in that community. In fact, centrality is an important concept [13] within social network analysis. High centrality scores identify members with the greatest structural importance in a network and these members are expected to play key roles in the network. Based on this observation, this work proposes to start clustering from the member with highest centrality score. That is, a group is formed starting from its “leader,” and a new “member” is added into an existing group based on its total relation with the group. The main procedure is as follows. Choose the vertex with the highest centrality score which is not included in any existing group yet and call this vertex a “LEADER.” A new group is created with this “LEADER.” Repeatedly add one vertex to an existing group if the following criterion is satisfied: the density of the newly extended group is above a given threshold.

more...
No comment yet.