CASOS 2017 Summer Institute
June 4 - 9, 2017
Carnegie Mellon University, Pittsburgh, PA USA
Gates/Hillman Center, 5000 Forbes Ave., Pittsburgh, PA 15213
Room 6115, 6th floor
The purpose of the CASOS Summer Institute is to provide and intense and hands-on introduction to network analytics and visualization from a combined social-network, network-science, link-analysis and dynamic network analysis perspective. Particular attention will be paid to the application of the associated techniques and theories to complex socio-technical systems with dynamic and/or geo-spatial features. Attendees will learn to:
- extract networks from texts, JSON files (e.g., news and tweets), or spreadsheets;
- analyze and visualize networks using one-mode, two-mode, and n-mode metrics;
- identify groups and clusters;
- examine networks spatially;
- examine overtime networks and explore dynamic aspects of these networks;
- and simulate change in networks and the diffusion/dispersion of information and beliefs through networks.
Participants learn about current trends, practices, and tools available for social networks analysis, link analysis, simulation, and multi-agent modeling. Basic social network and dynamic network representations, statistics, analysis and visualization techniques are covered. Techniques for designing, analyzing, and validating computational models with and without network components are presented. There is also an emphasis on appropriate and inappropriate ways to critique computational models and network analyses. The strengths and weaknesses of computational and network approaches to examining complex socio-technical issues are discussed. Multiple computational platforms are explored and hands-on experience are provided. An examination of social network methods, complexity theory and procedures for integrating network-based metrics and statistics into computational models completes the program.
The software tools students will learn and work with include: ORA, AutoMap, and Construct, which are network analysis, information extraction, and simulations tools, respectively, that are developed at CASOS and widely used globally in business, government, and education.
Text analysis, network analysis and multi-agent modeling as it applies to the extraction, analysis, and modeling of networks will be covered. Participants will be able to complete the institute without programming skills or in-depth understanding of particular social theories. Computer programming, statistical analysis and basic social or organizational theory are not included under the topics covered.
Students are encouraged to bring their own data and to learn to use the CASOS tools to code, analyze, reason about and visualize there data. Hands-on instruction and assistance will be provided on how to import data to ORA from CSV files, SQL databases, email servers, UCINET formats, PenLink, I2/Analyst Notebook and other raw data formats. Students will work through a tool chain where they extract networks from texts, analyze those networks, and the using simulation techniques evolve those networks.
The hands-on curriculum builds on both social network and computational analysis techniques, and illustrates how to use these techniques to study social, organizational and policy issues.
- Social Network Analysis
- Dynamic Network Analysis (multi-mode, multi-network), meta-networks and high-dimensional networks
- Geo-networks, putting networks on maps, geo-network measures
- Grouping and community detection techniques
- Social media network analytics
- Semantic networks and extracting networks from texts
- Agent-based dynamic network simulation
- Simulation model validation and docking
- Hands-on introduction to CASOS tools: ORA, AutoMap, and Construct
- Kathleen M. Carley, PhD, Carnegie Mellon University, Director of CASOS
- Other Faculty TBA
Participation is open to graduate students, faculty, and personnel from industry, education and government.
- Industry: $1,675.00
- Government/Military (with ID): $1,475.00
- Faculty/Postdocs: $1,225.00
- Students: $925.00
Questions?: Contact us by email: casos [at] cmu [dot] edu, phone: 412-268-3163
Registration is provided on the Carnegie Mellon Campus & Event Services website, Register Here
**The first day of the training will begin on Sunday June 4th and continue through Friday June 9th. Participants can come Saturday June 3rd for assistance in preparing their machines for the week. On Saturday June 10th, the CASOS Staff and Instructors are available for additional one-on-one instruction. You can sign up for one-on-one instruction during the week of Summer Institute.
- You are strongly encouraged to bring your own laptop. However, you must have it up-to-date in terms of security features and it must be registered with the Carnegie Mellon wireless internet. Please see the "What to Bring" link below.
- Warning: Please make sure that your laptop is running Windows 7, Windows 8, or Windows 10. The software may not run properly under Windows VISTA. If bringing a MAC OS laptop please load Windows or a functional emulator since not all the software will run on a Mac OS. Here is a suggested list of emulators:
For more information on computers and software, please visit the What to Bring page.
- Data will be provided to all participants for the hands-on sessions.
- Option: You may bring your own data! The CASOS group invites you to bring your own data and to use that during the workshop. If you do not have your own data, don't worry, we will provide some. Here are examples of types of data that you might want to bring:
- Texts in .txt format that you want to run through AutoMap.
- Some type of relational data in DL, dynetml, csv, excel, or other standard network format. Data can also be in mysql or access if you know how to write queries to extract it.
Examples are: email messages, webpage content, paper abstracts, news articles, comment fields from fixed formatted files.
Restrictions: Put one message, page, abstract, article per file.
Put all files for same group or time period in a folder. Exclude pictures.
Examples are: who talks to whom, trade level between countries, semantic networks, event networks.
Restrictions: Look at CASOS tools web page for easy formats to read. If you have node by attribute data, such as for each person degree, age, position you can use that data to create relational data.
Make sure your machine is large enough for your data. You can have multiple networks. Each network can be in its own file, but need not be. If you are bringing your own machine, which we highly recommend, just bring your data on your machine.