+ Big Data, Network Analysis Week 13
+ How is date being used Predict Presidential Election - Nate Silver – election-predictions-a-win-big-data-york-times/238182/ election-predictions-a-win-big-data-york-times/238182/ Predict Pregnancy - Target – target-figured-out-a-teen-girl-was-pregnant-before-her- father-did/ target-figured-out-a-teen-girl-was-pregnant-before-her- father-did/
+ Why Networks? Why is the role of networks in CS, Info Science, Social Science, Physics, Economics, and Biology expanding? More Data Rise of the Web and Social Media Shared vocabulary between (very different fields)
+ Reasoning about Networks How do we reason about networks? Empirical: Look at large networks and see what we find Mathematical Models: probabilistic, graph theory Algorithms for analyzing graphs What do we hope to achieve from the networks? Patterns and statistical properties of network data Design principles and models Understand why networks are organized the way they are (predict behaviors or networked systems)
+ Why networks? Network data is increasingly available: Large on-line computing applications where data can naturally be represented as a network Online communities: Facebook Communications: Instant Messenger News and Social Media: Blogging Also in systems biology, health, medicine, …
+ Networks: Rich Data a – Internet b – Citation network c – World Wide Web d – sexual network e – dating network
+ Networks Information networks: World Wide Web: hyperlinks Citation Blog Social networks: Organizational Communication Collaboration Sexual Collaboration Technological networks: Power grid Airline, road, river Telephone Internet Autonomous systems
+ What is Social Network Analysis? Network analysis is the study of social relations among a set of actors. It is a field of study, not just a method. “Social network analysis involves theorizing, model building and empirical research focused on uncovering the patterning of links among actors. It is concerned also with uncovering the antecedents and consequences of recurrent patterns.” (Linton Freeman)
+ The Network Perspective People (nodes) Ties (edges)
+ Ties in a social network Directed or undirected Simplex or multiplex Valued or unvalued 7
+ What is a Social Network? A set of dyadic ties, all of the same type, among a set of actors Actors can be persons, organizations, groups A tie is an instance of a specific social relationship 11
+ Network Relations Among Individuals Kinship Role-based (friend of) Cognitive/Perceptual (knows, aware of) Affiliations Affective (likes, trusts) Communication Among Organizations Buy from / Sell to Owns shares of Joint ventures 12
+ Key Perspectives in Social Network Analysis Focus on relationships between actors rather than just the attributes of actors. Interdependent view rather than atomistic (individualist) view of social processes and effects. Social structure affects substantive outcomes (which is a philosophical departure from other traditions) 13
+ Interdisciplinary Field of Study Computer Science Designing and understanding complex network structures Mathematics, Physics Methods, complex systems analysis Social Science (Sociology, Social Psychology, Economics) Theories and measurement of social networks, using networks to understand human behavior 14
+ Multiple Levels of Analysis Individual Level How does individual position in a network affect various outcomes for the individual? Systems Level How does the network structure as a whole affect outcomes for various tasks? 15
+ Network Data Collection Common Types: Survey Interviews Affiliation/membership records Behavioral (e.g., observation of communication patterns) Experiments 16 Data obtained through manyeyes and graphed:
+ Types of Network Data One mode Two mode Whole network Egocentric 17 AB C AB School A
+ Non-directed versus Directed Graphs 18 AB C AB C
Analyzing Social Networks ABCD A-111 B1-10 C11-1 D A DB C Simple Adjacency Matrix
+ Some Key Principles in Social Networks Degree The degree to which actors are connected directly to each other by cohesive bonds Density The proportion of direct ties in a network relative to the total number possible Centrality a group of metrics that aim to quantify the "importance" or "influence" (in a variety of senses) of a particular node (or group) within a network 20
+ Degree in Social Networks 21
+ Density in Social Networks 22 Low Density High Density / Integrated “Radial” (Valente)
+ Centrality in Social Networks Degree Centrality Closeness Centrality Betweeness Centrality 23
+ Why all of this sudden interest? The strength of the “Strength of Weak Ties” argument. Granovetter (1973) Argues that ‘weaker’ peripheral ties build heterogeneous networks, which in turn provide access to new and useful information. Heterogeneity through weak-ties widely accepted as a “good thing” for communication Access to jobs Access to other opportunities Helps distribute ideas, innovations 24
+ Ted Talk The hidden influence of social networks
+ Social Networks &list=PL05CC28C66163B00D&feature=results_main &list=PL05CC28C66163B00D&feature=results_main
+ Slides adapted from: Jure Leskovec, Stanford CS224W: Social and Information Network Analysis ure Leskovec, Stanford CS224W: Social and Information Network Analysis