Using machine learning to understand students' gaze patterns on graphing tasks. Invited Paper - Refereed

Alex Lyford; Lonneke Boels

doi:10.52041/iase.icots11.T8D2

Using machine learning to understand students' gaze patterns on graphing tasks. Invited Paper - Refereed

Alex Lyford^*
, Lonneke Boels

^*Corresponding author for this work

Middlebury College

Research output: Contribution to conference › Paper › Academic

Abstract

Graphs are ubiquitous. Many graphs, including histograms, bar charts, and stacked dotplots, have proven tricky to interpret. Students’ gaze data can indicate students’ interpretation strategies on these graphs. We therefore explore the question: In what way can machine learning quantify differences in students’ gaze data when interpreting two near-identical histograms with graph tasks in between? Our work provides evidence that using machine learning in conjunction with gaze data can provide insight into how students analyze and interpret graphs. This approach also sheds light on the ways in which students may better understand a graph after first being presented with other graph types, including dotplots. We conclude with a model that can accurately differentiate between the first and second time a student solved near-identical histogram tasks.

Original language	English
Pages	1-6
DOIs	https://doi.org/10.52041/iase.icots11.T8D2
Publication status	Published - Dec 2022
Event	11th International conference on teaching statistics: Bridging the Gap: Empowering & Educating Today’s Learners in Statistics - Ros Tower Hotel, Rosario, Argentina Duration: 11 Sept 2022 → 16 Dec 2022 https://icots.info/11/

Conference

Conference	11th International conference on teaching statistics
Abbreviated title	ICOTS11
Country/Territory	Argentina
City	Rosario
Period	11/09/22 → 16/12/22
Internet address	https://icots.info/11/

Keywords

histogram
Statistics education research
machine learning algorithm
random forests
secondary school students
graph tasks
eye-tracking

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

Access to Document

10.52041/iase.icots11.T8D2

4 Conference contribution
2 Article
1 Poster

Conceptual difficulties when interpreting histograms: A review
Boels, L., Bakker, A., Van Dooren, W. & Drijvers, P., Sept 2019, In: Educational Research Review. 28, p. 100291 26 p.
Research output: Contribution to journal › Article › Academic › peer-review

Open Access
File
Eye tracking secondary school students’ strategies when interpreting statistical graphs
Boels, L. B. M. M., Bakker, A. & Drijvers, P. H. M., Jul 2019, Proceedings of the 43rd Conference of the International Group for the Psychology of Mathematics Education: Improving access to the power of mathematics. Graven, M., Venkat, H., Essien, A. A. & Vale, P. (eds.). Pretoria, South-Africa: PME, Vol. 2. p. 113-120 8 p.
Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Academic › peer-review

Open Access
File
Het FIzier gericht op… wat elke wiskundedocent zou moeten weten over histogrammen
Translated title of the contribution: What every teacher should know about histogramsBoels, L. B. M. M., Feb 2019, In: Euclides. 94, 4, p. 10-13 4 p.
Research output: Contribution to journal › Article › Professional
Unravelling teachers’ strategies when interpreting histograms: an eyetracking study
Boels, L. B. M. M., Bakker, A. & Drijvers, P. H. M., 2019, Proceedings of the Eleventh Congress of the European Society for Research in Mathematics Education (CERME11, February 6 – 10, 2019). Jankvist, U. T., Van den Heuvel-Panhuizen, M. & Veldhuis, M. (eds.). Utrecht, the Netherlands: Freudenthal Group & Freudenthal Institute, Utrecht University and ERME, p. 888-895 8 p.
Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Academic › peer-review

Open Access
File
Revealing Conceptual Difficulties when Interpreting Histograms: An Eye-Tracking Study
Boels, L. B. M. M., Ebbes, R., Bakker, A., van Dooren, W. & Drijvers, P. H. M., 8 Jul 2018, Looking back, looking forward. Proceedings of the Tenth International Conference on Teaching Statistics (ICOTS10, Kyoto, july 2018). Sorto, M. A., White, A. & Guyot, L. (eds.). Voorburg, The Netherlands: International Statistics Institute, p. 1-4 4 p.
Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Academic › peer-review

Open Access
File

Cite this

@conference{51e30d839ff14b3d9b1968f2dba3cc46,

title = "Using machine learning to understand students' gaze patterns on graphing tasks. Invited Paper - Refereed",

abstract = "Graphs are ubiquitous. Many graphs, including histograms, bar charts, and stacked dotplots, have proven tricky to interpret. Students{\textquoteright} gaze data can indicate students{\textquoteright} interpretation strategies on these graphs. We therefore explore the question: In what way can machine learning quantify differences in students{\textquoteright} gaze data when interpreting two near-identical histograms with graph tasks in between? Our work provides evidence that using machine learning in conjunction with gaze data can provide insight into how students analyze and interpret graphs. This approach also sheds light on the ways in which students may better understand a graph after first being presented with other graph types, including dotplots. We conclude with a model that can accurately differentiate between the first and second time a student solved near-identical histogram tasks.",

keywords = "histogram, Statistics education research, machine learning algorithm, random forests, secondary school students, graph tasks, eye-tracking",

author = "Alex Lyford and Lonneke Boels",

year = "2022",

month = dec,

doi = "10.52041/iase.icots11.T8D2",

language = "English",

pages = "1--6",

note = "11th International conference on teaching statistics : Bridging the Gap: Empowering \& Educating Today{\textquoteright}s Learners in Statistics, ICOTS11 ; Conference date: 11-09-2022 Through 16-12-2022",

url = "https://icots.info/11/",

}

TY - CONF

T1 - Using machine learning to understand students' gaze patterns on graphing tasks. Invited Paper - Refereed

AU - Lyford, Alex

AU - Boels, Lonneke

PY - 2022/12

Y1 - 2022/12

N2 - Graphs are ubiquitous. Many graphs, including histograms, bar charts, and stacked dotplots, have proven tricky to interpret. Students’ gaze data can indicate students’ interpretation strategies on these graphs. We therefore explore the question: In what way can machine learning quantify differences in students’ gaze data when interpreting two near-identical histograms with graph tasks in between? Our work provides evidence that using machine learning in conjunction with gaze data can provide insight into how students analyze and interpret graphs. This approach also sheds light on the ways in which students may better understand a graph after first being presented with other graph types, including dotplots. We conclude with a model that can accurately differentiate between the first and second time a student solved near-identical histogram tasks.

AB - Graphs are ubiquitous. Many graphs, including histograms, bar charts, and stacked dotplots, have proven tricky to interpret. Students’ gaze data can indicate students’ interpretation strategies on these graphs. We therefore explore the question: In what way can machine learning quantify differences in students’ gaze data when interpreting two near-identical histograms with graph tasks in between? Our work provides evidence that using machine learning in conjunction with gaze data can provide insight into how students analyze and interpret graphs. This approach also sheds light on the ways in which students may better understand a graph after first being presented with other graph types, including dotplots. We conclude with a model that can accurately differentiate between the first and second time a student solved near-identical histogram tasks.

KW - histogram

KW - Statistics education research

KW - machine learning algorithm

KW - random forests

KW - secondary school students

KW - graph tasks

KW - eye-tracking

U2 - 10.52041/iase.icots11.T8D2

DO - 10.52041/iase.icots11.T8D2

M3 - Paper

SP - 1

EP - 6

T2 - 11th International conference on teaching statistics

Y2 - 11 September 2022 through 16 December 2022

ER -

Using machine learning to understand students' gaze patterns on graphing tasks. Invited Paper - Refereed

Abstract

Conference

Keywords

UN SDGs

Access to Document

Fingerprint

Research output

Conceptual difficulties when interpreting histograms: A review

Eye tracking secondary school students’ strategies when interpreting statistical graphs

Het FIzier gericht op… wat elke wiskundedocent zou moeten weten over histogrammen

Unravelling teachers’ strategies when interpreting histograms: an eyetracking study

Revealing Conceptual Difficulties when Interpreting Histograms: An Eye-Tracking Study

Cite this