Assessing Student Conceptual Understanding : Supplementing Deductive Coding with Natural Language Processing Techniques Public Deposited

http://ir.library.oregonstate.edu/concern/graduate_thesis_or_dissertations/n296x2980

Descriptions

Attribute NameValues
Creator
Abstract or Summary
  • Assessing student conceptual understanding is a valuable method for gauging specific student learning outcomes but can be difficult and time consuming to measure. This research investigates the potential of automating some intermediary steps of a qualitative analysis of student conceptual understanding with tools from the field of Natural Language Processing (NLP), Computational Linguistics, and Cognitive Psychology. This investigation centers on interviews conducted with newly graduated engineers over the first three years of their professional lives. Lexical features of those interview transcripts were measured using a variety of open-source NLP software. A theoretical framework was developed to link those lexical indicators to features of cognitive load and conceptual understanding. Results of the application of NLP to create indicators of student conceptual understanding were compared to the results of a traditional qualitative assessment. It was found that certain lexical indicators, primarily the Uber Index, could be useful descriptors of conceptual understanding when certain conditions are met but that the limitations of the approach must further addressed in future research. Factors that limit this application include variances in text length and the magnitude of change in conceptual understanding in an individual.
Resource Type
Date Available
Date Copyright
Date Issued
Degree Level
Degree Name
Degree Field
Degree Grantor
Commencement Year
Advisor
Committee Member
Academic Affiliation
Non-Academic Affiliation
Keyword
Subject
Rights Statement
Peer Reviewed
Language
Replaces
Additional Information
  • description.provenance : Made available in DSpace on 2016-03-24T15:53:32Z (GMT). No. of bitstreams: 2 license_rdf: 1370 bytes, checksum: cd1af5ab51bcc7a5280cf305303530e9 (MD5) ArbogastChristianA2016.pdf: 1041263 bytes, checksum: 38917d34a9c985fa7be2afbca5fa76c2 (MD5) Previous issue date: 2016-03-16
  • description.provenance : Submitted by Christian Arbogast (arbogasc@oregonstate.edu) on 2016-03-16T22:54:37Z No. of bitstreams: 2 license_rdf: 1370 bytes, checksum: cd1af5ab51bcc7a5280cf305303530e9 (MD5) ArbogastChristianA2016.pdf: 1041263 bytes, checksum: 38917d34a9c985fa7be2afbca5fa76c2 (MD5)
  • description.provenance : Approved for entry into archive by Laura Wilson(laura.wilson@oregonstate.edu) on 2016-03-24T15:53:32Z (GMT) No. of bitstreams: 2 license_rdf: 1370 bytes, checksum: cd1af5ab51bcc7a5280cf305303530e9 (MD5) ArbogastChristianA2016.pdf: 1041263 bytes, checksum: 38917d34a9c985fa7be2afbca5fa76c2 (MD5)
  • description.provenance : Approved for entry into archive by Julie Kurtz(julie.kurtz@oregonstate.edu) on 2016-03-21T21:52:28Z (GMT) No. of bitstreams: 2 license_rdf: 1370 bytes, checksum: cd1af5ab51bcc7a5280cf305303530e9 (MD5) ArbogastChristianA2016.pdf: 1041263 bytes, checksum: 38917d34a9c985fa7be2afbca5fa76c2 (MD5)

Relationships

In Administrative Set:
Last modified: 08/23/2017

Downloadable Content

Download PDF
Citations:

EndNote | Zotero | Mendeley

Items