Session
Computer Science and Communication Engineering
Description
A collection of data is gathered from surveys held in a Spring Course of the Economic Faculty in the University “Ismail Qemali” of Vlora, Albania. The data set for each student contains the names of the other students through which he/she have a “social relationship”. This relationship includes frequent communications, discussions on exercise solutions, and sitting usually close to each other in the class. We have constructed. At the end of the course, a final network based on this type of relationship. We are particularly interested on the clustering coefficient of this network and assessing it’s “significance”, in the sense of being somehow unusual or unexpected. Simulated random graph models, using R platform, are used to test the “significance” of the observed clustering coefficient.
Keywords:
Social networks, Clustering coefficient, Random graph models
Proceedings Editor
Edmond Hajrizi
ISBN
978-9951-550-14-7
First Page
64
Last Page
67
Location
Durres, Albania
Start Date
7-11-2015 9:00 AM
End Date
7-11-2015 5:00 PM
DOI
10.33107/ubt-ic.2015.90
Recommended Citation
Gjermëni, Orgeta, "Assessing Clustering in a Social University Network Course" (2015). UBT International Conference. 90.
https://knowledgecenter.ubt-uni.net/conference/2015/all-events/90
Assessing Clustering in a Social University Network Course
Durres, Albania
A collection of data is gathered from surveys held in a Spring Course of the Economic Faculty in the University “Ismail Qemali” of Vlora, Albania. The data set for each student contains the names of the other students through which he/she have a “social relationship”. This relationship includes frequent communications, discussions on exercise solutions, and sitting usually close to each other in the class. We have constructed. At the end of the course, a final network based on this type of relationship. We are particularly interested on the clustering coefficient of this network and assessing it’s “significance”, in the sense of being somehow unusual or unexpected. Simulated random graph models, using R platform, are used to test the “significance” of the observed clustering coefficient.