Asee peer logo

An Initial Study Applying Data Analysis and Machine Learning Techniques to Analyze Dissertations and Theses in the Engineering Education Field

Download Paper |

Conference

2017 ASEE Annual Conference & Exposition

Location

Columbus, Ohio

Publication Date

June 24, 2017

Start Date

June 24, 2017

End Date

June 28, 2018

Conference Session

International Research Experiences

Tagged Division

International

Tagged Topic

Diversity

Page Count

16

Permanent URL

https://peer.asee.org/28250

Download Count

20

Request a correction

Paper Authors

biography

Luis Felipe Zapata Rivera Florida Atlantic University

visit author page

Felipe Zapata Is a Phd student of Computer Engineering at Florida Atlantic University, in the past worked as a researcher assistant in the group of educational computer in the Eafit University in Medellin, Colombia. His work areas include: Remote Laboratories for Education, Development of online assessment systems and Machine Learning. He conducted their studies in systems engineering and masters degree at Eafit University. During his masters he developed systems using automatic assessment (computer based assessments) using questions generated by algorithms and integrated with LMS systems.

visit author page

biography

Maria M. Larrondo-Petrie Florida Atlantic University

visit author page

Dr. Maria Larrondo Petrie has a Ph.D. in Computer Engineering and is a Professor and Associate Dean of International Affairs in the College of Engineering and Computer Science of Florida Atlantic University. She is the Executive Director of LACCEI (Latin American and Caribbean Consortium of Engineering Institutions) and serves as an officer of the International Division of ASEE (American Society of Engineering Institutions), a member of the Board of Governors of the IEEE Education Society and a member of the IEEE Committee for Global Accreditation Activities. She is Editor-in-Chief of the Latin American and Caribbean Journal of Engineering Education, forms part of the International Advisory Board to the Journal of Engineering Education published by ASEE, and is on the Editorial Board of the IEEE Education Society's Iberian-American publication, called RITA because of its acronym in Spanish. She is Chair of Engineering Education Initiatives in EftA (OAS Engineering for the Americas) and organizes the annual Summit of Engineering for the Americas . She is part of the Education Committee of UPADI (in English: Pan American Federation of Engineering Associations), serves of the Board of ASIBEI (Iberian-American Engineering Education Association), and in the past served as First Vice President of IFEES (International Federation of Engineering Societies). In 2017 she received the Duncan Fraser Global Engineering Education award from IFEES and the Global Engineering Deans Council and was inducted into the PanAmerican Academy of Engineering.

visit author page

Download Paper |

Abstract

The current education system is not producing enough engineers to meet market demand for several reasons, including misalignment of curriculum with companies’ demands, high students’ dropout levels in the Engineering programs, students’ motivational problems, and lack of adequate technological tools that improve the teaching and learning processes. This poses a great challenge for engineering education. Some of the current questions are: how to improve the quality of teaching engineering? What are the differences between engineering education and the education in other fields? What tools can be developed to improve the teaching and learning process?.

Given these concerns, there is a growing number of Master’s thesis and PhD dissertations focusing on learning technologies, learning analytics, models and theories related to Engineering Education. These theses come from programs offered by colleges of education, or by departments of engineering education within colleges of engineering, or by programs in traditional engineering departments in colleges of engineering. This results in a wide spectrum of topics and perspectives that vary from education of engineering to engineering education.

This paper focus on the evolution of engineering education research around the world by processing and analyzing dissertation documents and theses related to Engineering Education, utilizing a variety of data analysis techniques. The first approach includes the classification and ranking of the dissertation and theses by analyzing metadata fields such as: title, abstract, institution, topics, keywords, and date of publication. The second approach consisted of an unstructured search, using unsupervised learning clustering algorithms (Machine Learning) and information retrieval techniques for text analysis. With this approach the computer based on the abstract content, can group, classify and rank the documents and topics automatically without the need of additional metadata.

Zapata Rivera, L. F., & Larrondo-Petrie, M. M. (2017, June), An Initial Study Applying Data Analysis and Machine Learning Techniques to Analyze Dissertations and Theses in the Engineering Education Field Paper presented at 2017 ASEE Annual Conference & Exposition, Columbus, Ohio. https://peer.asee.org/28250

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: © 2017 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