Relation mining using cross correlation of multi domain social networks
Social network analysis has emerged as an important research area in intelligence analysis to facilitate decision maker in more informed decisions. With the passage of time social networks services are increasingly being used in legal and criminal investigations including understanding and tracking...
| Main Authors: | , , |
|---|---|
| Format: | Conference or Workshop Item |
| Language: | English English English English |
| Published: |
2015
|
| Subjects: | |
| Online Access: | http://irep.iium.edu.my/48791/ http://irep.iium.edu.my/48791/ http://irep.iium.edu.my/48791/4/Relation_Mining_using_Cross_Correlation_of_Multi_Domain_Social_Networks-front_cover.pdf http://irep.iium.edu.my/48791/5/verso_page_asadullah.pdf http://irep.iium.edu.my/48791/6/toc_asadullah.pdf http://irep.iium.edu.my/48791/1/fozia-paper2015.pdf |
| Summary: | Social network analysis has emerged as an important research area in intelligence analysis to facilitate decision maker in more informed decisions. With the passage of time social networks services are increasingly being used in legal and criminal investigations including understanding and tracking of dark networks, i.e. illegal covert networks. Criminal organizations are well-suited to be studied using social network analysis as they consist of networks of individuals that span countries and continent using false identities over different networks to remain anonymous. There is great need to recognize the criminals carrying different fake identities to correctly track their immoral activities. This research article is focusing on devising a method which can be used to identify group of people i.e. criminals, terrorist or friends on different Social networks by analyzing patterns and performing correlations across different social network systems. Data integration using cross correlation is used to merge entities to form single focused networks. This single focused network also estimate the intensity of relationship between individuals in general networks based on the number of networks they are connected. To the best of our knowledge no such studies is done in the social network analysis, therefore this method is unique and offers innovations in making effective use of presence of people in different networks. |
|---|