Predicting teachers' research reading: A machine learning approach

被引:0
|
作者
Yousefpoori-Naeim, Mehrdad [1 ]
He, Surina [1 ]
Cui, Ying [1 ]
Cutumisu, Maria [2 ]
机构
[1] Univ Alberta, Measurement Evaluat & Data Sci, Edmonton, AB, Canada
[2] McGill Univ, Fac Educ, Dept Educ & Counselling Psychol, Montreal, PQ, Canada
基金
加拿大自然科学与工程研究理事会;
关键词
Teacher autonomy; Teachers' professional reading; Teacher development; Logistic regression; Support vector machine (SVM); Machine learning models; PROFESSIONAL-DEVELOPMENT; HABITS; KNOWLEDGE; ATTITUDES; EDUCATION; LITERACY; IMPACT;
D O I
10.1007/s11159-023-10061-7
中图分类号
G40 [教育学];
学科分类号
040101 ; 120403 ;
摘要
In addition to pre- and in-service teacher education programmes, teachers' autonomous reading of content related to their work contributes significantly to their professional development. This study investigated the factors that influenced the professional reading of 10,469 language teachers in the 2018 dataset of the Programme for International Student Assessment (PISA). Two machine learning models - logistic regression and Support Vector Machines (SVM) - were used to classify light and heavy readers. Nineteen variables related to teachers, including various aspects of their life, education and instructional practices, were used as predictors for classification. The results indicate that the two models had very similar accuracy scores around 65%. Moreover, the length of the reading texts that teachers assign to their students, instruction of reading comprehension strategies, and teachers' own general reading habits were found to be the most important predictors of professional reading time. Pr & eacute;dire les lectures professionelles des enseignants : approche par l'apprentissage machine - En plus des programmes de formation initiale et continue des enseignants, le choix autonome qu'ils font des lectures li & eacute;es & agrave; leur activit & eacute; professionnelle favorise consid & eacute;rablement leur & eacute;volution professionnelle. La pr & eacute;sente & eacute;tude examine les facteurs ayant influ & eacute; sur les lectures professionnelles de 10 469 professeurs de langues, & agrave; la lumi & egrave;re des donn & eacute;es recueillies en 2018 dans le cadre du Programme international pour le suivi des acquis des & eacute;l & egrave;ves (PISA). Deux mod & egrave;les d'apprentissage - celui de la r & eacute;gression logistique et celui des machines & agrave; vecteurs de support ou s & eacute;parateurs & agrave; vaste marge (en anglais support-vector machine, SVM) - furent utilis & eacute;s pour & eacute;tablir des cat & eacute;gories des lecteurs occasionels et des lecteurs avidus. Dix-neuf variables li & eacute;es aux enseignants, entre autres diff & eacute;rents aspects de leur vie, leur formation et leurs pratiques p & eacute;dagogiques furent utilis & eacute;es comme indicateurs pr & eacute;visionnels pour cette classification. Les r & eacute;sultats indiquent une tr & egrave;s grande similitude des scores de pr & eacute;cision avoisinant les 65 % pour les deux mod & egrave;les. En outre, la longueur des textes que les enseignants donnent & agrave; lire & agrave; leurs & eacute;l & egrave;ves, l'enseignement des strat & eacute;gies de compr & eacute;hension de la lecture et les habitudes globales de lecture des enseignants se sont r & eacute;v & eacute;l & eacute;s & ecirc;tre les principaux indicateurs pr & eacute;visionnels de leur temps de lecture professionnelle.
引用
收藏
页码:477 / 496
页数:20
相关论文
共 50 条
  • [1] Research Experiences for Teachers in Machine Learning
    Jaskie, Kristen
    Larson, Jean
    Johnson, Milton
    Turner, Kathy
    O'Donnell, Megan
    Christen, Jennifer Blain
    Rao, Sunil
    Spanias, Andreas
    [J]. 2021 IEEE FRONTIERS IN EDUCATION CONFERENCE (FIE 2021), 2021,
  • [2] Predicting How Well Adolescents Get Along with Peers and Teachers: A Machine Learning Approach
    Ali, Farhan
    Ang, Rebecca P.
    [J]. JOURNAL OF YOUTH AND ADOLESCENCE, 2022, 51 (07) : 1241 - 1256
  • [3] Predicting How Well Adolescents Get Along with Peers and Teachers: A Machine Learning Approach
    Farhan Ali
    Rebecca P. Ang
    [J]. Journal of Youth and Adolescence, 2022, 51 : 1241 - 1256
  • [4] Predicting Terrorism with Machine Learning: Lessons from "Predicting Terrorism: A Machine Learning Approach"
    Basuchoudhary, Atin
    Bang, James T.
    [J]. PEACE ECONOMICS PEACE SCIENCE AND PUBLIC POLICY, 2018, 24 (04)
  • [5] Predicting Dyslexia and Reading Speed in Adolescents from Eye Movements in Reading and Non-Reading Tasks: A Machine Learning Approach
    El Hmimdi, Alae Eddine
    Ward, Lindsey M.
    Palpanas, Themis
    Kapoula, Zoi
    [J]. BRAIN SCIENCES, 2021, 11 (10)
  • [6] A machine learning approach to reading level assessment
    Petersen, Sarah E.
    Ostendorf, Mari
    [J]. COMPUTER SPEECH AND LANGUAGE, 2009, 23 (01): : 89 - 106
  • [7] Predicting chattering alarms: A machine Learning approach
    Tamascelli, Nicola
    Paltrinieri, Nicola
    Cozzani, Valerio
    [J]. COMPUTERS & CHEMICAL ENGINEERING, 2020, 143
  • [8] Machine Learning Approach for Predicting Bumps on Road
    Ghadge, Manjusha
    Pandey, Dheeraj
    Kalbande, Dhananjay
    [J]. PROCEEDINGS OF THE 2015 INTERNATIONAL CONFERENCE ON APPLIED AND THEORETICAL COMPUTING AND COMMUNICATION TECHNOLOGY (ICATCCT), 2015, : 481 - 485
  • [9] A Machine Learning Approach for Predicting Nicotine Dependence
    Kharabsheh, Mohammad
    Meqdadi, Omar
    Alabed, Mohammad
    Veeranki, Sreenivas
    Abbadi, Ahmad
    Alzyoud, Sukaina
    [J]. INTERNATIONAL JOURNAL OF ADVANCED COMPUTER SCIENCE AND APPLICATIONS, 2019, 10 (03) : 179 - 184
  • [10] A Machine Learning Approach to Predicting MPN Patients
    Greenfield, Graeme
    Blayney, Jaine
    McMullin, Mary Frances
    Mills, Ken
    [J]. BRITISH JOURNAL OF HAEMATOLOGY, 2021, 193 : 61 - 61