• Save
NodeXL @PBS
Upcoming SlideShare
Loading in...5
×

Like this? Share it with your network

Share
  • Full Name Full Name Comment goes here.
    Are you sure you want to
    Your message goes here
    Be the first to comment
No Downloads

Views

Total Views
2,512
On Slideshare
2,381
From Embeds
131
Number of Embeds
10

Actions

Shares
Downloads
2
Comments
0
Likes
12

Embeds 131

https://twitter.com 39
http://ars-uns.blogspot.com.ar 34
http://ars-uns.blogspot.com 23
http://ars-uns.blogspot.com.es 20
http://ars-uns.blogspot.mx 8
http://ars-uns.blogspot.fr 2
http://www.linkedin.com 2
http://cloud.feedly.com 1
http://tweetedtimes.com 1
https://tasks.crowdflower.com 1

Report content

Flagged as inappropriate Flag as inappropriate
Flag as inappropriate

Select your reason for flagging this presentation as inappropriate.

Cancel
    No notes for slide
  • A few pioneering companies and researchers are beginning to develop metrics and tools that enable individuals to analyze community interaction in more meaningful ways. Nearly all such systems are based on participation statistics such as how often people post and how long they stick around.While these are important metrics that can be aggregated in meaningful ways and tracked over time, they miss perhaps the most important dimension of social media:namely social connections. They fail to capture or analyze “relational data” such as “who is friends with who” or “who has influenced who”Fortunately, there is a robust set of concepts and mathematical language for dealing with relational data. It is called Social Network Analysis.WHAT IS A NETWORK?“A network or graph is dened as a collection of n nodes connected by m edges. A network canbe directed, meaning the edges point in one direction, or undirected, meaning the edges go in both directions. The edges can join more than two vertices together. Such graphs are called hypergraphs. The edges can be weighted, contain self loops, and have different properties within the edges or nodes.”Our Explanation: To better understand the network perspective, consider the social network of Twitter users shown in the following figure. It is an example of a Sociogram, also called a network graph, which is a common way of visualizing networks. Like all networks, it consists of two primary building blocks: vertices (also called nodes or agents) and edges (also called ties or connections). The vertices are represented by images of the Twitter users, and the edges are represented by the lines that point from one vertex to another. The size of each Twitter user’s profile image is determined by the user’s total number of tweets as reported by the Twitter Application Programmer Interface (API), which gives sophisticated users access to powerful services. This is one example of how attribute data (e.g., data that describe a person) can be overlaid onto a network. A line, or edge, exists between two people when one “follows” the other or if one user “mentions” or “replies” to the other. All of these connections in aggregate reveal the emergent structure of two distinct groups with few connecting links. This accurately represents the way the workshop brought together previously separate clusters of people from different disciplines. It also helps identify individuals who fill important positions in the network, such as those who many people follow and thosewho are connected to both clusters.
  • A few pioneering companies and researchers are beginning to develop metrics and tools that enable individuals to analyze community interaction in more meaningful ways. Nearly all such systems are based on participation statistics such as how often people post and how long they stick around.While these are important metrics that can be aggregated in meaningful ways and tracked over time, they miss perhaps the most important dimension of social media: namely social connections. They fail to capture or analyze “relational data” such as “who is friends with who” or “who has influenced who”Fortunately, there is a robust set of concepts and mathematical language for dealing with relational data. It is called Social Network Analysis.
  • NodeXL is a plugin (technically a template) for Microsoft Excel 2007 and above, which allows you to analyze and visualize relational data.It includes features that make it easy for analysts to grab data from social media tools like email, Twitter, YouTube, and Flickr;and then make sense of that data by calculating metrics and visualizing networks. It is constantly being updated to improve scalability, usability, and functionality, and serves as a platform on which to try novel approaches to SNA.Attribute data or network metric calculations describing individuals and connections in the network can be mapped onto different visual attributes such as size, color, and opacity.Subgraph images like those seen on the left characterize person-specific networks and Excel’s formulas can be used to calculate additional metrics.For example, this network shows the most active contributors to a website design Q&A community, with greener nodes filling the social role of “question answerer” and redder nodes representing discussion starters.A social network  is commonly defined as a social structure made of actors such as individuals, organizations, groups, etc. In terms of network theory, they are called "vertices" or "nodes." The vertices can be isolated in a network or connected to other vertexes through "edges" or connections between actors based on interdependencies such as friendship, professional affiliation, conflicting priorities, etc.There are several commercial tools available to analyse the role and relationship of stakeholders as part of a social network and how actors may be positioned to influence the outcome of a project. NodeXL, a free Excel application and alternative to commercial software, is particularly useful if you need to map stakeholders of your program.NodeXL is used to visualize and analyse networks and is being developed for a larger audience than those of the more complicated and sometimes obscure scientific social network packages. It has been developed by Microsoft Research and a group of universities. While many other social network programs are difficult to learn and provide poor visualization, NodeXL generates amazing graphs and works directly out of the box if you have Excel installed on your computer.You can easily customize the graph’s appearance; zoom, scale and pan the graph; dynamically filter vertices and edges; alter the graph’s layout; find clusters of related vertices; and calculate a set of graph metrics
  • Since technical assistance programs often introduce new laws, systems, regulations, etc. in developing countries, these programs inevitably have to manage stakeholders affected by the program. It is often useful to identify power brokers, stakeholders who are central to the network of influencers and the connections among those affected by the program. 
  • Social network analysis sees the world as consisting of entities (called vertices or nodes) and connections between those entitles (called edges or ties).A) EDGES“An edge can thus be defined as a set of two vertices or an ordered pair, in the case of a directed graph. An edge (a set of two elements) is drawn as a line connecting two vertices, called end points or (less often) end vertices. An edge with end vertices x and y is denoted by xy (without any symbol in between). The edge set of G is usually denoted by E(G), or E when there is no danger of confusion.The size of a graph is the number of its edges, i.e. |E(G)|.”Our explanation: Edges, also known as links, ties, connections, and relationships, are the building blocks of networks. An edge connects two vertices together. Edges can represent many different types of relationships like proximity, collaborations, kinship, friendship, trade partnerships, citations, investments, hyperlinking, transactions, and shared attributes. A tie can be said to exist if it has some official status, is recognized by the participants, or isobserved by exchange or interaction between them. A tie is any form of relationship or connection between two entities. Undirected or directed edges are the two major types of connections. Directed edges (also known as asymmetric edges) have a clear origin and destination: money is lent from one person to another, a Twitter user follows another user, an email is sent to a recipient, or a web page links to another web page. They are represented on a graph as a line with an arrow pointing from the source vertex to the recipient vertex. Directed edges may be reciprocated or not. If I sent you a message you may send one back in return, or not. An undirected edge (also known as a symmetric edge) simply exists between two people or things: a couple is married, two Facebook users are friends, or two people are members of the same organization. No origin or destination is clear in these mutual relationships. They cannot exist unless they are reciprocated. Undirected edges are represented on a graph as a line connecting two vertices with no arrowsB)VERTICES “In graph theory, a vertex (plural vertices) or node is the fundamental unit out of which graphs are formed: an undirected graph consists of a set of vertices and a set of edges (unordered pairs of vertices), while a directed graph consists of a set of vertices and a set of arcs (ordered pairs of vertices). From the point of view of graph theory, vertices are treated as featureless and indivisible objects, although they may have additional structure depending on the application from which the graph arises; for instance, a semantic network is a graph in which the vertices represent concepts or classes of objects.”Our Explanation: Vertices, also called nodes, agents, entities, or items, can represent many things. Often they represent people or social structures such as workgroups, teams, organizations, institutions, states, or even countries. At other times they represent content such as web pages, keyword tags, or videos. They can even represent physicalor virtual locations or events. They often correspond with the primary building blocks of social media platform, friends in social networking sites, and posts or authors in blogs.Although not necessary for network analysis, having attribute data that describe each of the vertices can add insights to the analysis and visualizations. For example, the figure shown above used descriptive attribute data about the total number of posts to convey a sense of who is most active on Twitter. Other attribute data from Twitter, such asthe number of followers, people they follow, and their join date, can also be mapped to visual attributes. More generally, attribute data may describe demographic characteristics of a person (age, gender, race), data that describe the person’s use of a system (number of logins, messages posted, edits made) or other characteristics such as income or location. In network visualization tools like NodeXL, attribute data can be mapped to visual properties such as the size, color, or opacity of the vertices.It lends itself to visual representations such as the one you see, in the form of a network “graph”.A set of metrics can be calculated to characterize the network as a whole or individual entities within the network.For example, in this simple “kite friendship network”, Diane has the highest “Degree Centrality”, which is a fancy way of saying she has the most friends.However, Heather has the highest “betweenness centrality” suggesting her important spot as a bridge spanner between Jane and Ike and the rest of the group.The point here is that social network analysis provides a compelling method to understanding social media data.Unfortunately, it has until recently only been used by those with PhDs or those in specialized fields such as intelligence analysts.
  • Overall graph metricsThe following overall metrics get inserted into the Overall Metrics worksheet: Graph Type Directed or undirected. Vertices The number of vertices in the graph. Unique Edges The number of edges that do not have duplicates. Edges With Duplicates The number of edges that have duplicates. Total Edges The number of edges in the graph. This is the sum of Unique Edges and Edges With Duplicates. And Many others.Vertex degree (undirected graphs only)In an undirected graph, a vertex's degree is the number of edges incident to the vertex. In a directed graph, degree is undefined and is not calculated. A self-loop in an undirected graph is counted twice when a vertex's degree is calculated.Vertex in-degree (directed graphs only)In a directed graph, a vertex's in-degree is the number of incoming edges incident to the vertex. In an undirected graph, in-degree is undefined and is not calculated. A self-loop in a directed graph is counted once as an incoming edge (in-degree) and once as an outgoing edge (out-degree).Vertex out-degree (directed graphs only)In a directed graph, a vertex's out-degree is the number of outgoing edges incident to the vertex. In an undirected graph, out-degree is undefined and is not calculated. A self-loop in a directed graph is counted once as an outgoing edge (out-degree) and once as an incoming edge (in-degree). Vertex betweenness and closeness centralitiesA vertex that occurs on many shortest paths between other vertices has a larger betweenness centrality than vertices that do not. Betweenness centrality is defined in this article: http://en.wikipedia.org/wiki/Centrality#Betweenness_centrality Betweenness is a centrality measure of a vertex within a graph (there is also edge betweenness, which is not discussed here). Betweenness centrality quantifies the number of times a node acts as a bridge along the shortest path between two other nodes.NodeXL uses the algorithm described in the paper "A Faster Algorithm for Betweenness Centrality," by UlrikBrandes. The paper can be found here: http://www.inf.uni-konstanz.de/algo/publications/b-fabc-01.pdf The closeness centrality of a vertex is the inverse of the sum of the shortest distances between the vertex and all other vertices reachable from it.
  • Edge Color: Edge WeightVertex Shape: Betweeness Centrality; if greater than 1000 then set to solid Triangle otherwise set to DiskVertex Size mapped to In-Degree of graph matrics
  • The data was made available via the Name Gen Web Facebook app, which enabled me to download all of my Facebook friend data as an XML file and see who was connected to who. I’ve highlighted Srirambecause, as my friend, he appears at the center of the graph, connected almost to everyone I’m connected to.Group By cluster used for Grouping.Algorithm Used for layout : Harel-Koren Fast Multiscale…Status of Relationship:Green Color: MarriedLight Green : DivorcedBlue Color: Engaged And Male BlankLight Blue Color : Single and Female BlankYellow Color: In a RelationshipRed Color: It's ComplicatedOrange : SeparatedLight Orange : In an Open RelationshipVertex Size:Based on Birthday Small : More Age(Before 1950) and Blank
  • This graph reflects “Mentions” and “Replies-to” relationships in tweets with the “NaMo4PM” hash tag on 27-07-2013, “followed/followers/tweets” data has also been harvested.NodeXL also provides means to Filtering by relationship date, number of followers, number of tweets, tweet date, and joined twitter date… among others. I experimented with a simple filter mentioned below to reduce the number of results in my graph.Vertex Shape based on followers:->No. of followers greater than 16 lakh than show the Image otherwise set as a desk. Edge Color based on tweet dateGroup By cluster used for Grouping.Algorithm Used for layout : Fruchterman-ReingoldThis is a very important point: as the size of the social network grows, NodeXL becomes less useful for producing nifty images of the network; however, NodeXL remains very useful as an interactive tool for exploring the data you harvest.

Transcript

  • 1. Analysing Social Media Networks: With NodeXL PRESENTED BY: SUDHANSHU RANJAN ARBIND KUMAR PUNIT KISHORE
  • 2. What Is A Network? • A network or graph is a collection of n nodes connected by m edges. A network can be directed, meaning the edges point in one direction, or undirected, meaning the edges go in both directions. The edges can join more than two vertices together. Such graphs are called hyper graphs. The edges can be weighted, contain self loops, and have different properties within the edges or nodes.” Social Network Analysis • A systematic method for understanding relationships between entities(called vertices or nodes) and connections between those entities (called edges or ties). • A robust set of concepts and mathematical language for dealing with relational data. It is called Social Network Analysis. • Relational data” such as “who is friends with who” or “who has influenced who”. • Social media tools such as email, discussion forums, blogs, micro-blogs, and wikis are used by billions of people worldwide.
  • 3. Social Media Landscape
  • 4. Online Community Analysis
  • 5. What Is NodeXL? NodeXL is a free, open-source template for Microsoft® Excel® 2007, 2010 and 2013 that makes it easy to explore network graphs. With NodeXL, you can enter a network edge list in a worksheet, click a button and see your graph, all in the familiar environment of the Excel window. It makes Social Network Analysis easy for anyone familiar with basic spreadsheet functions. It was designed especially to facilitate learning the concepts and methods of social network analysis with visualization as a key component NodeXL has been optimized for analysing online social media –it includes built-in connections to query the APIs of Twitter, Flickr, Facebook and YouTube, allowing you to draw networks of users and their activity. APIs: Application Programming Interfaces
  • 6. Who Requires NodeXL ? Students who are learning social network analysis. Professionals who are interested in applying network analysis to business problems and particularly for those who lack experience with programming languages. What's New: The latest release enhances NodeXL's Twitter Search Network feature by expanding the network to include all people who were “replied to” or “mentioned” by the people who tweeted the search term, but who didn't tweet the search term themselves.
  • 7. Common Social Network Sites For Analyzer Data Set Import Options: Facebook Twitter YouTube Email Flickr And Many More…..
  • 8. Primitives of NodeXL Two primary building blocks: • vertices (also called nodes or agents or people) • Edges (also called ties or connections or relationship) Groups – cluster of vertices Graph type (directed or undirected) Graph layouts and graph Refresh
  • 9. Parameter: Measuring And Visualizing Networks Calculating Graph Metrics • Overall Graph Metrics • Degree(Undirected Graph) , IN & OUT Degree(Directed Graph) • Betweeness And Closeness Centralities • And Many Others.. Generate Sub Graph Image of Each Vertices Autofill Columns: • Setting Filters • Visualization Options of Edges, Vertices And Group Like Color, Shape, Label, Visibility Threshold, etc..
  • 10. Personal Email Collection Vertices: 760 Edges: 1013
  • 11. Social Network Graphing Using Facebook Data My Facebook Friends, Sriram Highlighted
  • 12. Twitter Feed : “NaMo4PM”
  • 13. “Samsung” vs “Apple” Mobile Tweet Rate
  • 14. NodeXL Features Cont… http://research.microsoft.com/en-us/projects/nodexl/
  • 15. NodeXL Features • Flexible Import and Export Import and export graphs in GraphML, Pajek, UCINet, and matrix formats. • Direct Connections to Social Networks Import social networks directly from Twitter, YouTube, Flickr and email, or use one of several available plug-ins to get networks from Facebook, Exchange and WWW hyperlinks. • Zoom and Scale Zoom into areas of interest, and scale the graph's vertices to reduce clutter. • Flexible Layout Use one of several "force-directed" algorithms to lay out the graph, or drag vertices around with the mouse. Have NodeXL move all of the graph's smaller connected components to the bottom of the graph to focus on what's important. • Easily Adjusted Appearance Set the colour, shape, size, label, and opacity of individual vertices by filling in worksheet cells, or let NodeXL do it for you based on vertex attributes such as degree, betweenness centrality or PageRank. Cont…
  • 16. NodeXL Features • Dynamic Filtering Instantly hide vertices and edges using a set of sliders— hide all vertices with degree less than five, for example. • Powerful Vertex Grouping Group the graph's vertices by common attributes, or have NodeXL analyze their connectedness and automatically group them into clusters. Make groups distinguishable using shapes and color, collapse them with a few clicks, or put each group in its own box within the graph. "Bundle" intergroup edges to make them more manageable. • Graph Metric Calculations Easily calculate degree, betweenness centrality, closeness centrality, eigenvector centrality, PageRank, clustering coefficient, graph density and more. • Task Automation Perform a set of repeated tasks with a single click.
  • 17. Visualize Your Facebook Network • Through Social Network Importer:  Close NodeXL Download the zip file from http://socialnetimporter.codeplex.com/ Unzip the file: you will find two items:  FacebookAPI.DLL SocialNetImporter.DLL  Copy these files to the NodeXL Plug-ins Directory (C:Program FilesSocial Media Research FoundationNodeXL Excel TemplatePlugIns) Restart NodeXL: you should see the Facebook Import option in the NodeXL>Data>Import menu. • Through GraphML Import Option:  Download your social network data with the app - https://apps.facebook.com/namegenweb/  Choose to download in the GraphML format  Save it to your local machine and make sure that the extension of the file is “.graphml”  Now import your Graphml file in NodeXL and play with it (Identify your friend clusters, calculate the graph metrics, add filters…)
  • 18. Closing Thought ! • Once Network data is available then social network analyzer can formulate its organizational, marketing and branding strategies. • To tackle increasingly complex datasets and challenging problems. We’ll be contributing to the lively and growing field of social network analysis. • We have to use the various features of NodeXL to analyse the social media network. However, knowing how to apply them effectively will resolve real- world problems .
  • 19. NodeXL Software  Software Tutorial and Sample Datasets : https://docs.google.com/open?id=0B2B1G-mVVD8-VXh3QWFEVm1UOVMyeHM1MkV2ZUdMQQ  Software Download link: http://nodexl.codeplex.com/releases/view/109697
  • 20. THANK YOU