Pointers to Conceptual Understanding

Samuel Cunningham-Nelson, Andrea Goncher, Michelle Mukherjee, Wageeh Boles

Research output: Book chapter/Published conference paperConference paper

Abstract

CONTEXT Concept inventories are tests used to elicit student misunderstandings and misconceptions. Traditionally, they exist as a set of multiple-choice questions (MCQs), including the correct option, as well as some distractors (Libarkin, 2008). This multiple-choice format allows for faster marking and feedback; however, it does not identify conceptual misunderstandings, or if a student has guessed the correct answer. By adding a space for students to add a textual justification (Goncher, Jayalath, & Boles, 2016), their answers can be checked to ensure that the concepts are correctly understood.
PURPOSE Automated textual analysis will allow insights to be uncovered, and to help speed up the process of grading to give feedback to students and informing educators. As part of that process, we endeavour to address the following questions: 1. What pointers can be identified that indicate a student’s conceptual understanding? 2. What conclusions can we make from these identified pointers to conceptual understanding?
APPROACH Over the past four years, two concept inventories have been deployed, both with multiple choice questions, as well as a free text field for students to give reasoning and explanation. We will combine several machine learning techniques to analyse the textual response data, including: • Word2vec – which allows words to be modelled as vectors, for easier computation (Mikolov, Chen, Corrado, & Dean, 2013) • LDA (Latent Dirichlet Allocation) – Allows classification and grouping of topics and areas (Blei, et al., 2003) • SVMs (Support vector machines) – which allow classification to be performed and similar areas grouped
RESULTS Four pointers were identified to help to automatically determine if conceptual understanding is present. The first three pointers can be determined with certainty, the fourth “validity of the response” is one that is traditionally determined by a human marker. Comparing with an expert marked dataset, the algorithm to determine this pointer achieved a 75% accuracy.
CONCLUSIONS Using the four identified pointers we are able to detect if a student has correctly identified the concept which they were being tested for in a particular question. The four pointers, allow some leniency if one of these is not achieved, and can also allow us to draw conclusions as to where issues lie in a student’s understanding. This presents several opportunities for benefits such as individualised feedback for students and entire class feedback for educators.
Original languageEnglish
Title of host publicationProceedings of the 28th Annual Conference of the Australasian Association for Engineering Education
EditorsNazmul Huda, David Inglis, Nicholas Tse, Graham Town
Place of PublicationSydney
PublisherAustralasian Association for Engineering Education
Pages687-695
Number of pages9
ISBN (Electronic)9780646980263
Publication statusPublished - 10 Dec 2017
Event28th Annual Conference of the Australasian Association for Engineering Education: AAEE 2017 - Novotel Manly Pacific, Manly Beach, Australia
Duration: 10 Dec 201713 Mar 2018
http://www.aaee.net.au/index.php/aaee-conference/aaee2017/234-aaee-2017 (Conference website)
https://search.informit.com.au/browsePublication;res=IELENG;isbn=9780646980263 (Conference proceedings)

Conference

Conference28th Annual Conference of the Australasian Association for Engineering Education
Abbreviated titleIntegrated Engineering
CountryAustralia
CityManly Beach
Period10/12/1713/03/18
OtherThe theme of the 28th Annual Conference of the Australasian Association for Engineering Education (AAEE 2017) was "Integrated Engineering". It refers to the combination of theory and practice that is characteristic of engineering training, and encompasses more than the well-balanced set of technical skills and professional attributes expected in modern engineering graduates. The theme also refers to the need to train engineers who are willing and able to share responsibility for guiding the world in which they live through the major challenges facing society in the 21st century.
Internet address

Fingerprint Dive into the research topics of 'Pointers to Conceptual Understanding'. Together they form a unique fingerprint.

  • Cite this

    Cunningham-Nelson, S., Goncher, A., Mukherjee, M., & Boles, W. (2017). Pointers to Conceptual Understanding. In N. Huda, D. Inglis, N. Tse, & G. Town (Eds.), Proceedings of the 28th Annual Conference of the Australasian Association for Engineering Education (pp. 687-695). Australasian Association for Engineering Education. https://search.informit.com.au/documentSummary;dn=391862776566667;res=IELENG