Applied NLP Methods for Organizational Research

April 1, 8, 22, 29, 2021

Course Overview

This course includes an overview of Natural Language Processing (NLP) using Machine and Deep Learning algorithms. Specific NLP topics include: data preparation, a deep dive into supervised and unsupervised Machine Learning techniques, a deep dive into state-of-the-art Deep Learning techniques, and what the future holds for these approaches within organizational research.

Course Description

This course is a developmental opportunity for SIOP attendees interested in the People Analytics/Data Science area of Industrial/Organizational Psychology. This course will introduce techniques and best practices for Natural Language Processing (NLP) and provide examples of applications within the area of People Analytics. This course will include hands-on practice using the Python programming language. This course is organized across four 3-hour modules and will include learning exercises to be completed between modules.

 Intended Audience

The instructional level of this course is Intermediate/Advanced. It is intended for SIOP members who have a strong quantitative background and programming experience. This course will use the Python programming language, but those that work with R should be able to follow along. I-O psychologists, people analytics practitioners, and quantitatively focused HR practitioners who would like to improve their NLP and data science skills may benefit from this session. 

 Learning Objectives

 This course will provide:

• An overview of the history and potential future of NLP.
• NLP and data science insights and techniques from leading People Analytics Experts.
• Methods and best practices for working with text-based HR data.
• Detailed explanations and walkthroughs of state-of-the-art machines and deep learning techniques to improve your NLP skillset.

Course Instructors

Dr. Nick Koenig is a Principal Data Scientist at Modern Hire where he has built, validated, and productionized machine learning models using both structured and unstructured data. He has spent the last 5 years of his career developing strategies to integrate machine learning into the field of Industrial and Organizational Psychology. He is the primary member of the winning team from the inaugural SIOP machine learning competition and has co-hosted the SIOP machine learning competition for the past two years. Before working as a data scientist at Modern Hire he spent over 5 years working at Walmart where he worked on the Global Selection and Assessment Team designing, validating, and implementing interviews and assessments that touched over 5 million candidates a year. While at Walmart he also worked as a Senior Research Scientist within Walmart Labs where he leveraged both micro and macro data to better predict and understand consumer demand.

Nick received his B.A. from the University of Missouri – Columbia and his Ph.D. in Industrial and Organizational Psychology from the University of Central Florida. In his free time, he enjoys hanging out with friends and family, mountain biking, and sampling beer from different breweries.

Dr. Matthew Arsenault has been an internal consultant on Walmart’s Global Selection and Assessment team for three and a half years. In this role, he combines domain expertise and quantitative methods to build knowledge to inform strategic initiatives related to selection and talent management. He conducts research and builds systems across the employee lifecycle from pre-hire assessments to exit surveys. He has used machine learning techniques to improve the handling of high-volume data and in deriving insights. He helps teams across Walmart develop validation strategies and evaluate the fairness of Machine Learning solutions. He was a member of the teams who won the SIOP Machine Learning Competition in 2018 and 2019 and he has participated in several SIOP sessions discussing the use of Machine Learning in decision making within organizations.

Matthew received his Ph.D. in Industrial and Organizational Psychology from the University of Oklahoma.

Dr. Daniel Schmerling is a Senior Manager of Data Science on the Employee Insights Team at Prudential where he is responsible for leading all artificial intelligence initiatives and analyses in the HR space.  Some of Dr. Schmerling’s work at Prudential includes the development and implementation of a skills based talent marketplace using natural language processing to automatically use employee resumes to identify relevant employee skills and match those skills to appropriate job openings and/or stretch assignment opportunities within the organization.  Before working at Prudential, Dr. Schmerling was a Senior Machine Learning Engineer at Wonderlic where he led the development of the first of its kind automated job analysis system which could validly and automatically identify the KSAs required for a job based solely on a job title and job description.  Before that, Dr. Schmerling also served as a Manager on the Talent Assessment team within People Analytics at Capital One.  In this role he owned the selection systems and processes for a number of LOBs designing, validating, and implementing selection tools and applications.  He started his career with FMP Consulting as a Human Capital Consultant in Alexandria, VA where among many different projects, he served as project manager developing a performance management system for use with the players on the University of Miami Men’s Basketball Team.  Finally, Dr. Schmerling was a member of the winning team from the inaugural SIOP machine learning competition and has presented on machine learning and artificial intelligence at numerous Industrial and Organizational Psychology as well as Artificial Intelligence conferences.

Dr. Schmerling received his B.A. in Psychology from the University of Maryland, College Park and his Ph.D. in Industrial and Organizational Psychology from the University of Central Florida.  In his free time, Daniel enjoys exercising, woodworking, and spending time with his family and friends.

Guest Speakers

Michael A. Campion is the Herman C. Krannert Distinguished Professor of Management at Purdue University (since 1986).  Previous industrial experience (1978-1986) includes 4 years each at IBM and Weyerhaeuser Company.  He is among the 10-20 most published authors in the top journals in I/O for the last three decades, and is the second most cited author of over 9000 authors in textbooks in both I/O Psychology and Human Resource Management.  He is past editor of Personnel Psychology, past president of SIOP, and past winner (in 2010) of the Scientific Contribution Award given by the SIOP.  He manages a small consulting firm (Campion Consulting Services) that has conducted nearly 1400 projects for over 180 private and public sector organizations during the past 35 years on nearly all human resources topics.  His research and consulting include employment testing, interviewing, mitigating employment discrimination, job analysis, work and team design, training, turnover, promotion, motivation, and recently computerized text analysis and artificial intelligence for employment decision making.  He co-authored the first application of machine learning to personnel selection in a top I/O journal (Campion et al., 2016, JAP), authored several articles under review, is researching and developing new procedures currently, and is a consultant to several major government and private sector organizations on this topic. 

Emily D. Campion is an Assistant Professor in Management in the Strome College of Business at Old Dominion University. As a consultant, she has worked with companies and governmental agencies to improve personnel selection systems, evaluate and reduce employment discrimination, conduct job analyses, and assess pay equity. In her research, Emily focuses on personnel selection practices that help address adverse impact, how to use text analytics to enhance employment decision making, and alternative work arrangement experiences (e.g., multiple jobholding, gig economy). Emily is currently serving as an editorial board member for the Journal of Vocational Behavior. Prior to academia, she was a daily reporter in Indiana and an AmeriCorps member in Washington, D.C. She earned her B.A. in Journalism from Indiana University and her Ph.D. in Organization and Human Resources from the University at Buffalo, The State University of New York.