Netlytic Social Network Analysis Tool

Abstract: Netlytic is a cloud-based text and social networks analyzer that can automatically summarize large volumes of text and discover social networks from online conversations on social media sites such as Twitter, Youtube, blogs, online forums and chats. The program is designed to help researchers and interested parties find data and understand an online group's operation, the demographics and habits of the group's users, and understand how this information and other elements work together in a network. Major features of the program include data harvesting, content analysis, and network visualization mapping. 

Description: Netlytic is a social network analyzing tool. Its usage and purpose falls under the realm of network science. Gephi.org writes that, "Network Science is a new and emerging scientific discipline that examines the interconnections among diverse physical, informational, biological, cognitive, and social networks. This field of science seeks to discover common principles, algorithms and tools that govern network behavior. The National Research Council defines Network Science as 'the organized knowledge of networks based on their study using the scientific method.'" In this context Netlytic seeks to explore new realms of knowledge hidden beneath the intricate systems that form social media platforms. 

     One of the primary features of Netlytic is data harvesting. Users with the basic free account are allowed to create up to three data sets simultaneously. Paid accounts have access to many more sets at once. The first step in creating a set is to choose a medium to pull information from including Twitter, Facebook, Instagram, Youtube, cloud storage files, RSS (Rich Site Summary) feeds, forums, chatrooms, and more.

     When extracting data from Twitter, the user must link a Twitter account with the program. Search term keywords including operators, hashtags, and @usernames are used to refine the selection process.  Importing data from Facebook only works with public Facebook pages, not user profile pages. With Instagram Netlytic is able to harvest the post test, and test from relevant comments. For Youtube data from video comments is extracted. Datasets from cloud storage providers can be uploaded to Netlytic. Acceptable file formats include .txt, .csv, and .rss. Manual text file uploads is also possible with CSV and RSS files. Information from RSS feeds can be taken directly pasting the feed's URL into the program.

     Data mining from Twitter, Facebook, Instagram, and Youtube can be set to occur every hour for one, three or six days. Mining collection for RSS feeds can be set for a daily collection for one, three, or six months. The less frequent posting habits on RSS feeds seems to necesatate the long extraction processes available. Once the harvesting process is complete, Netlytic will display the url to the post, username of author, date of posting, post text, and geographic location if possible in a large list. Users can share datasets with other users or send the url of the set to a nonuser. 

     Once a dataset is complete Netlytic can be used for content analysis. Main features include statical compilation of metrics for certain types of posts to report on trends in certain fields such as time of posting, approximate locations of postings, etc. A main element of Netlytic's analysis processing is text analysis, and particularly sentiment analysis of relevant text. Through algorithms run during data mining and analysis, the program is able to scan the words and phrases in the text and categorize them according to certain sentiments. Example categories include "good," "bad," "tasteful," "pleasant," etc.

     The final component of Netlytic's service is network visualization. The program is able to take the information from the data set and compose it into a network graph showing different nodes representing information points and paths that link them. Each node can be selected to view the messages (such as Twitter posts) associated with them. Annotations can also be placed around the map per the user's desire. A share feature is available that allows users to export images of their network.These can be kept as part of the visualization of the dataset (and will reappear upon reopening the visualization) or can be saved as an image on the user’s computer for documentation purposes or shared online

     Netlytic provides two different layout options for viewing, Fruchterman-Reingold and DrL. The website says, "The network’s layout is an important feature because it enables the user to identify patterns in the network such as clusters of individuals, which, once examined can then inform the network analysis (e.g. Who are the primary individuals that make up a given cluster? What groups them together, or alternatively, what could be the reason for other individuals’ exclusion from the cluster?)." The first layout option is a popular force-based algorithim that is good for networks with less than 1,000 nodes. The Drl option is a force-based algorithim useful for visualizing large networks. The long edges in this layout are cut to highlight clusters, allowing for easier recognition. 

 Statement of Relevance to Team Project: This program has many practical implications for the project "McSwift: Marketing Analysis of a Franchise vs. an Artist." The focus of the endeavor is to explore marketing techniques and strategies that the Mcdonalds Corporation and musician Taylor Swift employs. An important form of modern marketing strategy revolves around social marketing. Thus Netlytic is invaluable tool for analyzing the content of social media marketing campaigns that Mcdonalds and Swift employ. 

     Facebook, Twitter, and Instagram are considered the "big three" among current social media platforms. Most social media campaigns run by any company employs the use of those three services, so Netlytic would be useful for harvesting data from each over the course of a campaign. Relevant info one might scrutinize is the frequency of postings regarding a particular product, popular location of postings, time and date of postings, and the content of postings. 

The sentiment and text analysis features of Netlytic would be extremely useful for determining trends in the language use of Mcdonalds posts in comparison to posts by Swift. Insight into keywords used and categorization of the types of words used could provide valuable insight. 

     Netlytic's network visualization feature could be used to great effect to discover connections within individual campaigns. Perhaps hidden trends may emerge when viewing the marketing strategy comprehensively with every node and connecting path in sight. Furthermore the visual mapping component could be utilized to compare and contrast Mcdonalds and Swift. Large scale mapping and data processing from Netlytic's algorithms could reveal many similarities or stark differences between the franchise and the artist. 

Resources for Further Study:

Campbell, William M., Dagli, Charlie K., Weinstein, Clifford J. "Social Network Analysis with Content and Graphs." Lincoln Laboratory Journal. 20(1) 2013: 62-81. Web. 22 Nov. 2014

Gephi Graph Exploration and Manipulation. The Gephi Consortium, 2008. Web. 11 Nov. 2014. 

Machlis Sharon. "22 free tools for data visualization and analysis." Computerworld., 20 Apr. 2011. Web. 22 Nov. 2014

Kreigler, Anine. "Using Social Network Analysis to Profile Organised Crime." Institute for Security Studies., Aug 2014. Web. 22 Nov. 2014

Twitonomy. Diginomy Pty Ltd, 2014. Web. 22 Nov. 2014

yWorks yED Graph Editor. yWorks GmbH, 2007. Web. 11 Nov. 2014.