Volume 5, Issue 3, March 2015
ISSN: 2277 128X
International Journal of Advanced Research in
Computer Science and Software Engineering
Research Paper
Available online at: www.ijarcsse.com
Special Issue: E-Technologies in Anthropology
Conference Held at Bon Secours College for Women, India
Data Mining Techniques in the Field of Applied Anthropology
With Respect To Social Network Analysis
S. Alamelukiruthika
MCA.,M.Phil, Asst.Prof.in Departmant of Computer Application,
Bon Secours College for Women, Thanjavur,
Tamil Nadu, India
Anthropology has been called “the most humane of the sciences and the most scientific of the humanities”. The Wide
range of approaches that span in this field are Science (hypothesis, observation, and testing) and Humanities (more
subjective, based on feeling)The word anthropology itself tells the basic story--from the Greek anthropos ("human")
and logia ("study“) .Anthropology is The study of humanity, including our prehistoric origins and contemporary
human diversity The goals of Anthropology are to study diversity and preserve diversity,study commonalities in all
humanity,look at our own culture more objectively, like an outsider and to apply this knowledge in an attempt to
alleviate human challenges. In this paper we would discuss few data mining techniques used for social network
analysis which forms a part of Liguistic or social anthropology.
Social anthropology deals with the study of communication, mainly (but not exclusively) among
humans.Sociolinguistics is a subfield which deals with the study of communication in social life (analysis of
discourse) and the variations of communication in different cultural contexts
The emergence of worldwide web has led to social Interaction,Knowledge Exchange,Knowledge Discovery Data mining
techniques can be used for building descriptive and predictive models of social interactions with a very fine granularity
and with practically no reporting bias In a social network analysis datamining can be used for Community
Extraction,Link Prediction, Cascading Behavior,Identifying Prominent Actors and Experts in Social Networks,Search in
Social Networks,Trust in Social Networks,Characterization of Social Networks and Anonymity in Social Networks
I.
COMMUNITY EXTRACTION
Inherent to social networks are communities, which are groups of individuals connected to each other in some way .
Communities play a vital role in understanding the creation, representation, and transfer of knowledge among people,
and are an essential building block of all social networks. Discovering communities of users in a social network is
Possible to use popular link analysis techniques like HITS algorithm and Graph Clustering techniques. Community
Detection in Large Networks uses algorithm based on label propagation
© 2015, IJARCSSE All Rights Reserved
Page | 6
Alamelukiruthika, International Journal of Advanced Research in Computer Science and Software Engg. 5 (3),
March- 2015, pp. 6-8
II.
LINK PREDICTION
Given a snapshot of a social network, can we infer which new interactions among its members are likely to occur in the
near future? We formalize this question as the link prediction problem, and develop approaches to link prediction based
on measures for analyzing the “proximity” of nodes in a network. We can also find the following ,
– Given a social network at time ti predict the social link between actors at time ti+1
– Given a social network with an incomplete set of social links between a complete
set of actors, predict the unobserved social links
– Given information about actors, predict the social link between them (this is quite
similar to social network extraction Classical approach for link prediction is to fit the social network on a model and
then use it for link prediction.Latent Space model , Dynamic Latent Space model and p* model can be used.
III.
CASCADING BEHAVIOUR
Theoretical models suggest that social networks influence the evolution of cooperation, but to date there have been few
experimental studies. Observational data suggest that a wide variety of behaviors may spread in human social networks,
but subjects in such studies can choose to befriend people with similar behaviors, posing difficulty for causal inference.
Bandwagon Dynamics and Granovetter's threshold model can describe cascading behaviours
Link mining
Link mining involves data Mining techniques that take into account the links
between objects and entities while building predictive or descriptive models.
Link based object ranking, Group Detection, Entity Resolution, Link
Prediction are some of the techniques used Its applications are Hyperlink Mining, Relational Learning, Inductive Logic
Programming,and Graph Mining
Kleinberg’s Hubs and Authorities techniques can be used for link mining.
Identifying Prominent Actors in a Social Network
A common approach is to compute scores/rankings over the set (or a subset) of actors in the social network which
indicate degree of importance/expertise/influence
– E.g. Pagerank, HITS, centrality measures.The Centrality measures that exist in the social science domain for
measuring importance of actors in a social network are Degree Centrality
,Closeness Centrality, Betweenness Centrality
© 2015, IJARCSSE All Rights Reserved
Page | 7
Alamelukiruthika, International Journal of Advanced Research in Computer Science and Software Engg. 5 (3),
March- 2015, pp. 6-8
IV.
IDENTIFYING EXPERTS IN A SOCIAL NETWORK
Link analysis can be used for for expert identification the other mehods are Steyvers et al „s Bayesian model to assign
topic distributions to users which can be used for ranking them with reference to the topics and Harada et al ,use a search
engine to retrieve top k pages for a particular topic query and then extract the users present in them
Search in Social Networks
The search in social networks can include querying for information in a social network,query routing in a network.A
user can send out queries to neighbours and if the neighbor knows the answer then he/she replies else forward it to their
neighbors. Thus a query propagates through a networkand to develop schemes for efficient routing through a network.
According to Watts-Dodds-Newman's Model individuals in a social network are marked by distinguishing
characteristics,groups of individuals can be grouped under groups of groups,group membership is the primary basis for
social interaction, Individuals hierarchically cluster the social world in multiple ways based on different
attributes,Perceived similarity between individuals determine 'social distance' between them.
© 2015, IJARCSSE All Rights Reserved
Page | 8