Instructor Information

John Piorkowski

Work Phone: 443-778-6372

John Piorkowski serves as the Chief Engineer and Applied Information Sciences Branch Lead within the Asymmetric Operations Sector at the Johns Hopkins University/Applied Physics Laboratory. He also serves as the chair for the information systems engineering  and co-chair for the data science programs in the Whiting School of Engineering at Johns Hopkins University. 

During his 30 year career, John has led number efforts in the areas of communications, networking, software systems, and data analytics. More recently he has been focused on applications of data analytics and social media analytics.

John received a B.S. in Electrical Engineering from The Pennsylvania State University, an M.S. in Electrical Engineering from The Johns Hopkins University, a Post-Masters Certificate in Electrical Engineering from The Johns Hopkins University with a concentration in Telecommunications, and a PhD  in Information Systems from The University of Maryland Baltimore County.

His hobbies include cycling, running, and swimming.

Ian McCulloh

Cell Phone: 240-506-3417

Ian McCulloh is an adjunct associate professor in the Bloomberg School of Public Health and the Whiting School of Engineering at Johns Hopkins University.  He is the Federal Chief Data Scientist and managing director at Accenture, a Fortune 100 company where he oversees hundreds of data scientists and artificial intelligence practitioners supporting the U.S. Federal government.  He oversees Accenture's Discovery Lab focused on artificial intelligence and data science research.  His most recent papers have been focused on the neuroscience of persuasion, social media analysis, and training data impacts on AI performance.  He is the author of “Social Network Analysis with Applications” (Wiley: 2013), “Networks Over Time” (Oxford: forthcoming), “ISIS in Iraq: Understanding the Social and Psychological Foundations of Terror” (Oxford: forthcoming) and has published over 80 peer-reviewed papers, primarily in the area of social network analysis.  He also works with various medical practitioners in the Baltimore area to improve the effectiveness of public health campaigns.  He retired as a Lieutenant Colonel from the US Army after 20 years of service in special operations and improvised explosive device forensics.  He founded the West Point Network Science Center and created the Army’s Advanced Network Analysis and Targeting (ANAT) program. In his most recent military assignments as a strategist, he led interdisciplinary teams of Ph.D. scientists at Special Operations Command Central (SOCCENT) and Central Command (CENTCOM) to conduct social science research in 15 countries across the Middle East and Central Asia to included denied areas, which he used to inform data-driven strategy for countering extremism and irregular warfare, as well as empirically assess the effectiveness of military operations.  He holds a Ph.D. and M.S. from Carnegie Mellon University’s School of Computer Science, an M.S. in Industrial Engineering, and M.S. in Applied Statistics from the Florida State University, and a B.S. in Industrial Engineering from the University of Washington.  He is married with four children and a granddaughter.

Course Information

Course Description

Today an immense social media landscape is being fueled by new applications, growth of devices (e.g., Smartphones and devices), and human appetite for online engagement. With a myriad of applications and users, significant interest exists in the obvious question, “How does one better understand human behavior in these communities to improve the design and monitoring of these communities?” To address this question a multidisciplinary approach that combines social network analysis (SNA), natural language processing, and data analytics is required. This course combines all these topics to address contemporary topics such as marketing, population influence, etc. There will be several small projects. Prerequisite(s): Knowledge of Python or R; matrix algebra.

Prerequisites

Foundation PrerequisitesEN.685.621 OR EN.605.621;Foundation Prerequisites for Cybersecurity Majors:EN.605.621 AND EN.695.601 AND EN.695.641

Course Goal

To understand an end-to-end approach to analyze social media, online media campaigns, and measure the behavior of personas interacting with social media technology.  Apply this understanding to capture social media data using open source tools and provide mature analysis to inform and advise executives on social media policy.

Course Objectives

  • By the end of the course, students should be able to:
    Ingest and visualize social media data, render network visualizations, and understand accuracy, bias, validity, and repeatability in social media representation.
  • Conduct basic social network analysis to include centrality, subgroup analysis, social theory, and statistical analysis of networks.
  • Characterize social media clusters and discourse using natural language processing, sentiment analysis and topic classification.
  • Conduct over-time network analysis including statistical change detection, exponential random graph modeling, and stochastic actor oriented modeling.

When This Course is Typically Offered

Syllabus

  • Introduction to Social Media Analytics
  • Graph Theory and Centrality Measures
  • Data and Application Program Interface (API)
  • Centralization and Social Theory
  • Natural Language Processing
  • Fake News, Influence, and Subgroup Analysis
  • Machine Learning
  • Relational Algebra
  • Network Statistical Models
  • Network Diffusion and Interventions
  • Sentiment Analysis
  • Topic Modeling
  • Visual Content Analytics
  • Final Presentations

Student Assessment Criteria

Homework 25%
Mid-Term Project 25%
Final Project/Paper 40%
Discussion Participation 10%

Each week, students will apply lesson concepts on a real-world data set of their choosing.  Each assignment will build on the previous week assignment.  Students will submit a mid-term presentation in week 8  and a final project at the end of the course.  The intent is for students to leave the course with an empowered, integrated understanding of social media analysis and a finalized project to begin a portfolio of their capability.

Students will also be expected to participate in an open discussion forum to further explore topics and challenges in social media analytics. The field of social media analytics continues to evolve and there are many technical challenges in this field.

Computer and Technical Requirements

Basic proficiency in R, Python, or other scripting language.  The language for the course will be R, however, students will be provided with an easy to follow tutorial. In addtion, some Python scripts with also be used in the course.

Participation Expectations

Homework is expected to be turned in on the website as indicated in the assignment tool; it will be considered late if it is received after that time. Special circumstances (e.g., temporary lack of internet access) can be cheerfully accommodated if the student informs us in advance. Homework that is unjustifiably late will have the grade reduced for lateness.

Students are expected to participate/submit the following to receive a grade for the course:

  • Discussion Participation
  • Homework
  • Mid-Term Project
  • Final Project

We generally do not directly grade spelling and grammar. However, egregious violations of the rules of the English language will be noted without comment. Consistently poor performance in either spelling or grammar is taken as an indication of poor written communication ability that may detract from your grade.

Textbooks

Textbook information for this course is available online through the MBS Direct Virtual Bookstore.

Course Notes

There are notes for this course.

Final Words from the Instructor

This course will empower students to conduct social media analysis that rivals the capability of industry leaders and provide insight for superior decision-making.

(Last Modified: 06/20/2018 12:28:32 AM)