Predicting student success with and without library instruction using supervised machine learning methods

IF 1.8 Q2 INFORMATION SCIENCE & LIBRARY SCIENCE
Karen Harker, Carol Hargis, Jennifer Rowe
{"title":"Predicting student success with and without library instruction using supervised machine learning methods","authors":"Karen Harker, Carol Hargis, Jennifer Rowe","doi":"10.1108/pmm-12-2023-0047","DOIUrl":null,"url":null,"abstract":"<h3>Purpose</h3>\n<p>The main purpose of this analysis was to demonstrate the value of predictive modeling of student success and identify the key groups of students for which library instruction could provide the most impact.</p><!--/ Abstract__block -->\n<h3>Design/methodology/approach</h3>\n<p>Data regarding the attendance of library instruction associated with a first-year writing course were combined with student demographic and academic data over a four year period representing over 10,000 students. We applied supervised machine learning methods to determine the most accurate model for predicting student outcomes, including course outcome, persistence and graduation. We also assessed the impact of library instruction on these outcomes.</p><!--/ Abstract__block -->\n<h3>Findings</h3>\n<p>The gradient-boosted decision tree model provided the most accurate predictions. The impact of library instruction was modest but still was second only to the previous grade point average (GPA). The value of this metric, however, was greatest for students who were struggling, especially those who were first-generation students, regardless of ethnicity. More notably, the impact of library instruction was substantially greater for specific student demographics, including students with lower cumulative GPAs.</p><!--/ Abstract__block -->\n<h3>Research limitations/implications</h3>\n<p>Features of the models were limited to high-level academic metrics, some of which may not be very useful in predicting outcomes. Measures more closely related to learning styles, the course or course of study could provide for greater accuracy.</p><!--/ Abstract__block -->\n<h3>Practical implications</h3>\n<p>Prediction modeling could allow for a more selective approach to outreach and offers information that the librarian can use to customize instruction sessions and reference interactions.</p><!--/ Abstract__block -->\n<h3>Social implications</h3>\n<p>Targeting students who may be at risk of not succeeding in a course has ethical implications either way. If used to bias the subjective assessments, these predictions could produce self-fulfilling prophecies. Conversely, to ignore indicators of possible difficulties the student may have with the material is a disservice to the education of that student.</p><!--/ Abstract__block -->\n<h3>Originality/value</h3>\n<p>There are few studies that have incorporated library instruction into models of predicting student outcomes. Library resources and services can play a major role in the success of students, particularly those who have had less exposure to the resources and skills needed to use these resources.</p><!--/ Abstract__block -->","PeriodicalId":44583,"journal":{"name":"Performance Measurement and Metrics","volume":null,"pages":null},"PeriodicalIF":1.8000,"publicationDate":"2024-07-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Performance Measurement and Metrics","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1108/pmm-12-2023-0047","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"INFORMATION SCIENCE & LIBRARY SCIENCE","Score":null,"Total":0}
引用次数: 0

Abstract

Purpose

The main purpose of this analysis was to demonstrate the value of predictive modeling of student success and identify the key groups of students for which library instruction could provide the most impact.

Design/methodology/approach

Data regarding the attendance of library instruction associated with a first-year writing course were combined with student demographic and academic data over a four year period representing over 10,000 students. We applied supervised machine learning methods to determine the most accurate model for predicting student outcomes, including course outcome, persistence and graduation. We also assessed the impact of library instruction on these outcomes.

Findings

The gradient-boosted decision tree model provided the most accurate predictions. The impact of library instruction was modest but still was second only to the previous grade point average (GPA). The value of this metric, however, was greatest for students who were struggling, especially those who were first-generation students, regardless of ethnicity. More notably, the impact of library instruction was substantially greater for specific student demographics, including students with lower cumulative GPAs.

Research limitations/implications

Features of the models were limited to high-level academic metrics, some of which may not be very useful in predicting outcomes. Measures more closely related to learning styles, the course or course of study could provide for greater accuracy.

Practical implications

Prediction modeling could allow for a more selective approach to outreach and offers information that the librarian can use to customize instruction sessions and reference interactions.

Social implications

Targeting students who may be at risk of not succeeding in a course has ethical implications either way. If used to bias the subjective assessments, these predictions could produce self-fulfilling prophecies. Conversely, to ignore indicators of possible difficulties the student may have with the material is a disservice to the education of that student.

Originality/value

There are few studies that have incorporated library instruction into models of predicting student outcomes. Library resources and services can play a major role in the success of students, particularly those who have had less exposure to the resources and skills needed to use these resources.

使用监督机器学习方法预测有无图书馆指导的学生成功率
目的这项分析的主要目的是证明学生成功预测建模的价值,并确定图书馆指导能对哪些关键学生群体产生最大影响。设计/方法/途径与一年级写作课程相关的图书馆指导出席率数据与学生人口统计和学业数据相结合,在四年期间代表了 10,000 多名学生。我们应用监督机器学习方法来确定预测学生成绩(包括课程成绩、坚持率和毕业率)的最准确模型。我们还评估了图书馆指导对这些结果的影响。研究结果梯度提升决策树模型提供了最准确的预测。图书馆教学的影响不大,但仍仅次于之前的平均学分绩点(GPA)。然而,对于学业困难的学生,尤其是第一代学生,不论种族如何,这一指标的价值最大。更值得注意的是,图书馆指导对特定学生群体的影响要大得多,其中包括累计平均学分绩点(GPA)较低的学生。社会影响针对可能无法成功完成课程的学生,无论如何都会产生道德影响。如果主观评价出现偏差,这些预测可能会产生自我实现的预言。反之,如果忽视学生在学习材料时可能遇到困难的指标,则是对学生教育的一种伤害。原创性/价值将图书馆指导纳入学生成绩预测模型的研究很少。图书馆资源和服务对学生的成功起着重要作用,尤其是那些较少接触资源和使用这些资源所需技能的学生。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 求助全文
来源期刊
Performance Measurement and Metrics
Performance Measurement and Metrics INFORMATION SCIENCE & LIBRARY SCIENCE-
CiteScore
2.20
自引率
0.00%
发文量
1
期刊介绍: ■Quantitative and qualitative analysis ■Benchmarking ■The measurement and role of information in enhancing organizational effectiveness ■Quality techniques and quality improvement ■Training and education ■Methods for performance measurement and metrics ■Standard assessment tools ■Using emerging technologies ■Setting standards or service quality
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信