Modeling key differences in underrepresented students' interactions with an online STEM course

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Little is known about the ways that underrepresented students in online STEM courses interact and behave differently from their peers, or whether online courses offer learning opportunities that can better suit these under-served populations. The current study examines the logged behavioral patterns of 470 university students, spanning 3 years, who were enrolled in an online introductory STEM course. Cross-validated data mining methods were applied to their interaction logs to determine if first generation, non-white, female, or non-Traditional (≥ 23 years old) students could be classified by their behaviors. Model classification accuracies were evaluated with the Matthews Correlation Coefficient (MCC). First generation (MCC = .123), non-white (MCC = .153), female (MCC = .183) and non-Traditional students (MCC = .109) were classified at levels significantly above chance (MCC = 0). Follow-up analyses of predictive features showed that first-generation students made more quiz attempts, non-white students interacted more during night hours (8pm-8am), female students submitted quizzes earlier, and non-Traditional students accessed discussion forums less than their peers. We show that understanding behaviors is crucial in this context because behaviors in the first two weeks alone (e.g., discussion forumparticipation, number of logins) predicted eventual grade in the course (MCC = .200). Implications are discussed, including suggestions for future research as well as interventions and course features that can support underrepresented STEM students in online learning spaces.

Original languageEnglish (US)
Title of host publicationProceedings of the Technology, Mind, and Society Conference, TechMindSociety 2018
PublisherAssociation for Computing Machinery
ISBN (Electronic)9781450354202
DOIs
StatePublished - Apr 5 2018
Event2018 Technology, Mind, and Society Conference, TechMindSociety 2018 - Washington, United States
Duration: Apr 5 2018Apr 7 2018

Publication series

NameACM International Conference Proceeding Series

Other

Other2018 Technology, Mind, and Society Conference, TechMindSociety 2018
CountryUnited States
CityWashington
Period4/5/184/7/18

Fingerprint

Students
Data mining

Keywords

  • Educational data mining
  • STEM education
  • Underrepresented

ASJC Scopus subject areas

  • Software
  • Human-Computer Interaction
  • Computer Vision and Pattern Recognition
  • Computer Networks and Communications

Cite this

Bosch, N., Wes Crues, R., Henricks, G. M., Perry, M., Angrave, L. C., Shaik, N., ... Anderson, C. J. (2018). Modeling key differences in underrepresented students' interactions with an online STEM course. In Proceedings of the Technology, Mind, and Society Conference, TechMindSociety 2018 [a6] (ACM International Conference Proceeding Series). Association for Computing Machinery. https://doi.org/10.1145/3183654.3183681

Modeling key differences in underrepresented students' interactions with an online STEM course. / Bosch, Nigel; Wes Crues, R.; Henricks, Genevieve M.; Perry, Michelle; Angrave, Lawrence Christopher; Shaik, Najmuddin; Bhat, Suma Pallathadka; Anderson, Carolyn Jane.

Proceedings of the Technology, Mind, and Society Conference, TechMindSociety 2018. Association for Computing Machinery, 2018. a6 (ACM International Conference Proceeding Series).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Bosch, N, Wes Crues, R, Henricks, GM, Perry, M, Angrave, LC, Shaik, N, Bhat, SP & Anderson, CJ 2018, Modeling key differences in underrepresented students' interactions with an online STEM course. in Proceedings of the Technology, Mind, and Society Conference, TechMindSociety 2018., a6, ACM International Conference Proceeding Series, Association for Computing Machinery, 2018 Technology, Mind, and Society Conference, TechMindSociety 2018, Washington, United States, 4/5/18. https://doi.org/10.1145/3183654.3183681
Bosch N, Wes Crues R, Henricks GM, Perry M, Angrave LC, Shaik N et al. Modeling key differences in underrepresented students' interactions with an online STEM course. In Proceedings of the Technology, Mind, and Society Conference, TechMindSociety 2018. Association for Computing Machinery. 2018. a6. (ACM International Conference Proceeding Series). https://doi.org/10.1145/3183654.3183681
Bosch, Nigel ; Wes Crues, R. ; Henricks, Genevieve M. ; Perry, Michelle ; Angrave, Lawrence Christopher ; Shaik, Najmuddin ; Bhat, Suma Pallathadka ; Anderson, Carolyn Jane. / Modeling key differences in underrepresented students' interactions with an online STEM course. Proceedings of the Technology, Mind, and Society Conference, TechMindSociety 2018. Association for Computing Machinery, 2018. (ACM International Conference Proceeding Series).
@inproceedings{a00d260ff48942d39934c32430d9d8e5,
title = "Modeling key differences in underrepresented students' interactions with an online STEM course",
abstract = "Little is known about the ways that underrepresented students in online STEM courses interact and behave differently from their peers, or whether online courses offer learning opportunities that can better suit these under-served populations. The current study examines the logged behavioral patterns of 470 university students, spanning 3 years, who were enrolled in an online introductory STEM course. Cross-validated data mining methods were applied to their interaction logs to determine if first generation, non-white, female, or non-Traditional (≥ 23 years old) students could be classified by their behaviors. Model classification accuracies were evaluated with the Matthews Correlation Coefficient (MCC). First generation (MCC = .123), non-white (MCC = .153), female (MCC = .183) and non-Traditional students (MCC = .109) were classified at levels significantly above chance (MCC = 0). Follow-up analyses of predictive features showed that first-generation students made more quiz attempts, non-white students interacted more during night hours (8pm-8am), female students submitted quizzes earlier, and non-Traditional students accessed discussion forums less than their peers. We show that understanding behaviors is crucial in this context because behaviors in the first two weeks alone (e.g., discussion forumparticipation, number of logins) predicted eventual grade in the course (MCC = .200). Implications are discussed, including suggestions for future research as well as interventions and course features that can support underrepresented STEM students in online learning spaces.",
keywords = "Educational data mining, STEM education, Underrepresented",
author = "Nigel Bosch and {Wes Crues}, R. and Henricks, {Genevieve M.} and Michelle Perry and Angrave, {Lawrence Christopher} and Najmuddin Shaik and Bhat, {Suma Pallathadka} and Anderson, {Carolyn Jane}",
year = "2018",
month = "4",
day = "5",
doi = "10.1145/3183654.3183681",
language = "English (US)",
series = "ACM International Conference Proceeding Series",
publisher = "Association for Computing Machinery",
booktitle = "Proceedings of the Technology, Mind, and Society Conference, TechMindSociety 2018",

}

TY - GEN

T1 - Modeling key differences in underrepresented students' interactions with an online STEM course

AU - Bosch, Nigel

AU - Wes Crues, R.

AU - Henricks, Genevieve M.

AU - Perry, Michelle

AU - Angrave, Lawrence Christopher

AU - Shaik, Najmuddin

AU - Bhat, Suma Pallathadka

AU - Anderson, Carolyn Jane

PY - 2018/4/5

Y1 - 2018/4/5

N2 - Little is known about the ways that underrepresented students in online STEM courses interact and behave differently from their peers, or whether online courses offer learning opportunities that can better suit these under-served populations. The current study examines the logged behavioral patterns of 470 university students, spanning 3 years, who were enrolled in an online introductory STEM course. Cross-validated data mining methods were applied to their interaction logs to determine if first generation, non-white, female, or non-Traditional (≥ 23 years old) students could be classified by their behaviors. Model classification accuracies were evaluated with the Matthews Correlation Coefficient (MCC). First generation (MCC = .123), non-white (MCC = .153), female (MCC = .183) and non-Traditional students (MCC = .109) were classified at levels significantly above chance (MCC = 0). Follow-up analyses of predictive features showed that first-generation students made more quiz attempts, non-white students interacted more during night hours (8pm-8am), female students submitted quizzes earlier, and non-Traditional students accessed discussion forums less than their peers. We show that understanding behaviors is crucial in this context because behaviors in the first two weeks alone (e.g., discussion forumparticipation, number of logins) predicted eventual grade in the course (MCC = .200). Implications are discussed, including suggestions for future research as well as interventions and course features that can support underrepresented STEM students in online learning spaces.

AB - Little is known about the ways that underrepresented students in online STEM courses interact and behave differently from their peers, or whether online courses offer learning opportunities that can better suit these under-served populations. The current study examines the logged behavioral patterns of 470 university students, spanning 3 years, who were enrolled in an online introductory STEM course. Cross-validated data mining methods were applied to their interaction logs to determine if first generation, non-white, female, or non-Traditional (≥ 23 years old) students could be classified by their behaviors. Model classification accuracies were evaluated with the Matthews Correlation Coefficient (MCC). First generation (MCC = .123), non-white (MCC = .153), female (MCC = .183) and non-Traditional students (MCC = .109) were classified at levels significantly above chance (MCC = 0). Follow-up analyses of predictive features showed that first-generation students made more quiz attempts, non-white students interacted more during night hours (8pm-8am), female students submitted quizzes earlier, and non-Traditional students accessed discussion forums less than their peers. We show that understanding behaviors is crucial in this context because behaviors in the first two weeks alone (e.g., discussion forumparticipation, number of logins) predicted eventual grade in the course (MCC = .200). Implications are discussed, including suggestions for future research as well as interventions and course features that can support underrepresented STEM students in online learning spaces.

KW - Educational data mining

KW - STEM education

KW - Underrepresented

UR - http://www.scopus.com/inward/record.url?scp=85048733481&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85048733481&partnerID=8YFLogxK

U2 - 10.1145/3183654.3183681

DO - 10.1145/3183654.3183681

M3 - Conference contribution

AN - SCOPUS:85048733481

T3 - ACM International Conference Proceeding Series

BT - Proceedings of the Technology, Mind, and Society Conference, TechMindSociety 2018

PB - Association for Computing Machinery

ER -