Using Topic Modeling to Assess Middle School Science Discourse based on Next Generation Science Standards

DOI

10.2991/icat2e-17.2016.11How to use a DOI?

Keywords

K-12 education assessment, discourse analysis, Next Generation Science Standards, natural language processing, topic modeling.

Abstract

In this paper we apply natural language understanding and topic modeling methods to create an instructional tool for assessing science discourse in interactive multimedia presentations that are created, shared and discussed by students. The resulting assessment prototype will enable teachers to follow student discourse in real time, to understand gaps in student learning, and to improve teaching practices. Middle School Life Sciences and Physical Sciences standards from the Next Generation Science Standards (NGSS) serve as a basis for assessing domain relevance. Domain knowledge and standards are modeled, and student discussions are analyzed and graphed.

Copyright

© 2017, the Authors. Published by Atlantis Press.

Open Access

This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).

Download article (PDF)

TY  - CONF
AU  - Erin Shaw
AU  - Richard Phillips
AU  - Anne Kao
AU  - Robert Torres
PY  - 2017/03
DA  - 2017/03
TI  - Using Topic Modeling to Assess Middle School Science Discourse based on Next Generation Science Standards
BT  - Proceedings of The 2017 International Conference on Advanced Technologies Enhancing Education (ICAT2E 2017)
PB  - Atlantis Press
SP  - 42
EP  - 45
SN  - 2352-5398
UR  - https://doi.org/10.2991/icat2e-17.2016.11
DO  - 10.2991/icat2e-17.2016.11
ID  - Shaw2017/03
ER  -