Asee peer logo

Capturing Narratives of Graduate Engineering Attrition through Online Forum Mining

Download Paper |


2018 ASEE Annual Conference & Exposition


Salt Lake City, Utah

Publication Date

June 23, 2018

Start Date

June 23, 2018

End Date

July 27, 2018

Conference Session

Assessment and Research Tools

Tagged Division

Educational Research and Methods

Page Count




Permanent URL

Download Count


Request a correction

Paper Authors

author page

Carey Whitehair


Catherine G.P. Berdanier Pennsylvania State University, University Park Orcid 16x16

visit author page

Catherine G.P. Berdanier is an Assistant Professor in the Department of Mechanical and Nuclear Engineering at Pennsylvania State University. She earned her B.S. in Chemistry from The University of South Dakota, her M.S. in Aeronautical and Astronautical Engineering and Ph.D. in Engineering Education from Purdue University. Her research interests include graduate-level engineering education, including inter- and multidisciplinary graduate education, online engineering cognition and learning, and engineering communication.

visit author page

Download Paper |


This research paper presents methods by which researchers can harvest data from social media forums as a way to gain insight on sensitive issues or populations. In the present research, we are interested in studying doctoral attrition, which is a complex and multifaceted phenomenon that poses practical significance to funding agencies, advisors, and students themselves. Sampling non-completers is difficult, and researchers generally find it difficult to collect nationwide narratives of attrition. This paper presents a novel method for studying attrition using the publicly-available online forum to collect first-hand accounts and authentic narratives of attrition. These often- anonymous online discussions offer a unique view into the authentic thoughts of engineering graduate students considering leaving their engineering program throughout the decision-making process. This paper proposes a method to efficiently collect and parse open-source information into coherent narratives across “posts” or “threads” of conversation using data mining tools. The underlying methodology developed is based on achieving a holistic view of the discourse patterns and authentic narratives surrounding attrition, which in turn allows researchers to capture meaningful, authentic, and credible emergent themes unbiased by social response. We present a short summary of results to show the dominant narratives of attrition achieved through this method; however, the main focus of this paper is to present the method itself, which has the potential to be extended and modified to aid in other large data mining efforts to answer other research questions related to sensitive topics.

Whitehair, C., & Berdanier, C. G. (2018, June), Capturing Narratives of Graduate Engineering Attrition through Online Forum Mining Paper presented at 2018 ASEE Annual Conference & Exposition , Salt Lake City, Utah. 10.18260/1-2--30176

ASEE holds the copyright on this document. It may be read by the public free of charge. Authors may archive their work on personal websites or in institutional repositories with the following citation: © 2018 American Society for Engineering Education. Other scholars may excerpt or quote from these materials with the same citation. When excerpting or quoting from Conference Proceedings, authors should, in addition to noting the ASEE copyright, list all the original authors and their institutions and name the host city of the conference. - Last updated April 1, 2015