Linking language to math success in an on-line course

Scott Crossley, Tiffany Barnes, Collin Lynch, Danielle S. McNamara

Research output: Contribution to conferencePaper

4 Citations (Scopus)

Abstract

This study takes a novel approach toward understanding success in a math course by examining the linguistic features and affect of students’ language production within a blended (with both on-line and traditional face to face instruction) undergraduate course (n=158) on discrete mathematics. Three linear effects models were compared: (a) a baseline linear model including non-linguistic fixed effects, (b) a model including only linguistic factors, (c) a model including both linguistic and non-linguistic effects. The best model (c) explained 16% of the variance of final course scores, revealing significant effects for one non-linguistic feature (days on the system) and two linguistic features (Number of dependents per prepositional object nominal and Sentence linking connectives). One non-linguistic factor (Is a peer tutor) and two linguistic variables (Words related to self and Words related to tool use) demonstrated marginal significance. The findings indicate that language proficiency is strongly linked to math performance such that more complex syntactic structures and fewer explicit cohesion devices equate to higher course performance. The linguistic model also indicated that less self-centered students and students using words related to tool use were more successful. In addition, the results indicate that students that are more active in on-line discussion forums are more likely to be successful.

Original languageEnglish (US)
Pages180-185
Number of pages6
StatePublished - Jan 1 2017
Externally publishedYes
Event10th International Conference on Educational Data Mining, EDM 2017 - Wuhan, China
Duration: Jun 25 2017Jun 28 2017

Conference

Conference10th International Conference on Educational Data Mining, EDM 2017
CountryChina
CityWuhan
Period6/25/176/28/17

Fingerprint

Linguistics
Students
Syntactics

Keywords

  • Math
  • NLP
  • On-line learning
  • Student success

ASJC Scopus subject areas

  • Computer Science Applications
  • Information Systems

Cite this

Crossley, S., Barnes, T., Lynch, C., & McNamara, D. S. (2017). Linking language to math success in an on-line course. 180-185. Paper presented at 10th International Conference on Educational Data Mining, EDM 2017, Wuhan, China.

Linking language to math success in an on-line course. / Crossley, Scott; Barnes, Tiffany; Lynch, Collin; McNamara, Danielle S.

2017. 180-185 Paper presented at 10th International Conference on Educational Data Mining, EDM 2017, Wuhan, China.

Research output: Contribution to conferencePaper

Crossley, S, Barnes, T, Lynch, C & McNamara, DS 2017, 'Linking language to math success in an on-line course' Paper presented at 10th International Conference on Educational Data Mining, EDM 2017, Wuhan, China, 6/25/17 - 6/28/17, pp. 180-185.
Crossley S, Barnes T, Lynch C, McNamara DS. Linking language to math success in an on-line course. 2017. Paper presented at 10th International Conference on Educational Data Mining, EDM 2017, Wuhan, China.
Crossley, Scott ; Barnes, Tiffany ; Lynch, Collin ; McNamara, Danielle S. / Linking language to math success in an on-line course. Paper presented at 10th International Conference on Educational Data Mining, EDM 2017, Wuhan, China.6 p.
@conference{5404867cc8c840b0a0c4ba69aaf1a56b,
title = "Linking language to math success in an on-line course",
abstract = "This study takes a novel approach toward understanding success in a math course by examining the linguistic features and affect of students’ language production within a blended (with both on-line and traditional face to face instruction) undergraduate course (n=158) on discrete mathematics. Three linear effects models were compared: (a) a baseline linear model including non-linguistic fixed effects, (b) a model including only linguistic factors, (c) a model including both linguistic and non-linguistic effects. The best model (c) explained 16{\%} of the variance of final course scores, revealing significant effects for one non-linguistic feature (days on the system) and two linguistic features (Number of dependents per prepositional object nominal and Sentence linking connectives). One non-linguistic factor (Is a peer tutor) and two linguistic variables (Words related to self and Words related to tool use) demonstrated marginal significance. The findings indicate that language proficiency is strongly linked to math performance such that more complex syntactic structures and fewer explicit cohesion devices equate to higher course performance. The linguistic model also indicated that less self-centered students and students using words related to tool use were more successful. In addition, the results indicate that students that are more active in on-line discussion forums are more likely to be successful.",
keywords = "Math, NLP, On-line learning, Student success",
author = "Scott Crossley and Tiffany Barnes and Collin Lynch and McNamara, {Danielle S.}",
year = "2017",
month = "1",
day = "1",
language = "English (US)",
pages = "180--185",
note = "10th International Conference on Educational Data Mining, EDM 2017 ; Conference date: 25-06-2017 Through 28-06-2017",

}

TY - CONF

T1 - Linking language to math success in an on-line course

AU - Crossley, Scott

AU - Barnes, Tiffany

AU - Lynch, Collin

AU - McNamara, Danielle S.

PY - 2017/1/1

Y1 - 2017/1/1

N2 - This study takes a novel approach toward understanding success in a math course by examining the linguistic features and affect of students’ language production within a blended (with both on-line and traditional face to face instruction) undergraduate course (n=158) on discrete mathematics. Three linear effects models were compared: (a) a baseline linear model including non-linguistic fixed effects, (b) a model including only linguistic factors, (c) a model including both linguistic and non-linguistic effects. The best model (c) explained 16% of the variance of final course scores, revealing significant effects for one non-linguistic feature (days on the system) and two linguistic features (Number of dependents per prepositional object nominal and Sentence linking connectives). One non-linguistic factor (Is a peer tutor) and two linguistic variables (Words related to self and Words related to tool use) demonstrated marginal significance. The findings indicate that language proficiency is strongly linked to math performance such that more complex syntactic structures and fewer explicit cohesion devices equate to higher course performance. The linguistic model also indicated that less self-centered students and students using words related to tool use were more successful. In addition, the results indicate that students that are more active in on-line discussion forums are more likely to be successful.

AB - This study takes a novel approach toward understanding success in a math course by examining the linguistic features and affect of students’ language production within a blended (with both on-line and traditional face to face instruction) undergraduate course (n=158) on discrete mathematics. Three linear effects models were compared: (a) a baseline linear model including non-linguistic fixed effects, (b) a model including only linguistic factors, (c) a model including both linguistic and non-linguistic effects. The best model (c) explained 16% of the variance of final course scores, revealing significant effects for one non-linguistic feature (days on the system) and two linguistic features (Number of dependents per prepositional object nominal and Sentence linking connectives). One non-linguistic factor (Is a peer tutor) and two linguistic variables (Words related to self and Words related to tool use) demonstrated marginal significance. The findings indicate that language proficiency is strongly linked to math performance such that more complex syntactic structures and fewer explicit cohesion devices equate to higher course performance. The linguistic model also indicated that less self-centered students and students using words related to tool use were more successful. In addition, the results indicate that students that are more active in on-line discussion forums are more likely to be successful.

KW - Math

KW - NLP

KW - On-line learning

KW - Student success

UR - http://www.scopus.com/inward/record.url?scp=85049380194&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85049380194&partnerID=8YFLogxK

M3 - Paper

AN - SCOPUS:85049380194

SP - 180

EP - 185

ER -