Check out the new open-access journal article by Dr. Chunrui Zou and Yuqing Zou:

Zou, Y., & Zou, C. (2023). Exploring factors associated with higher education students' learning outcomes in emergency remote teaching environments during the COVID-19 pandemic: General patterns and individual differences. Education and Information Technologies.?https://doi.org/10.1007/s10639-023-12032-9

（探索在COVID-19新冠大流行期間的緊急遠(yuǎn)程教學(xué)環(huán)境中，與高等教育學(xué)生學(xué)習(xí)成果相關(guān)的因素： 一般模式和個(gè)體差異）

Our purposes were to explore the factors associated with higher education students' learning outcomes in emergency remote teaching environments (ERTEs) during the COVID-19 pandemic at both the population and individual levels.

（我們的研究目的是從群體和個(gè)體兩個(gè)層面探索在COVID-19新冠大流行期間的緊急遠(yuǎn)程教學(xué)環(huán)境中，與高等教育學(xué)生學(xué)習(xí)成果相關(guān)的因素。）

9418 students from 41 countries were selected for analysis from a survey-based dataset collected with the aim of understanding the self-perceived impacts of the first-wave COVID-19 pandemic on higher education students.

（我們從一個(gè)基于調(diào)查問(wèn)卷的數(shù)據(jù)中選取了來(lái)自41個(gè)國(guó)家的9418名學(xué)生進(jìn)行分析。收集此問(wèn)卷的目的是了解高等教育學(xué)生如何感覺(jué)COVID-19新冠第一波大流行對(duì)于他們的影響。）

Fig. 1 Participant number for each country

We conducted structural equation modeling analysis to explore associated factors and latent profile analysis to identify student profiles based on these factors. Utilizing the identified profiles, we developed a random forest-based classifier to identify the membership of students' profiles.

（我們進(jìn)行了結(jié)構(gòu)方程建模分析以探究相關(guān)因素，并進(jìn)行了潛在類型分析以根據(jù)這些因素識(shí)別學(xué)生類型。利用所識(shí)別的學(xué)生類型，我們開(kāi)發(fā)了一種基于隨機(jī)森林的分類器來(lái)識(shí)別學(xué)生類型的成員資格。）

Fig. 2 Framework of the design of this study

The results revealed that multiple environmental and individual factors were significantly associated with learning outcomes, each with varying path coefficient magnitudes.

（結(jié)構(gòu)方程建模分析的結(jié)果表明，多種環(huán)境或個(gè)人因素與學(xué)生學(xué)習(xí)成果有顯著相關(guān)性，且每種因素的路徑系數(shù)大小各不相同。）

Fig. 3 Structural equation modeling analysis results

Based on these factors, eight profiles were identified with different learning outcomes and student characteristics. The classifier achieved a testing accuracy of 0.904.

（基于這些顯著相關(guān)的因素，我們通過(guò)潛在類型分析識(shí)別出八個(gè)具有不同學(xué)習(xí)成果和學(xué)生背景特征的類型。分類器的測(cè)試準(zhǔn)確率達(dá)到0.904。）

Fig. 4 Scores for six factors, learning outcomes, and academic emotions in each class. (a): heatmap; (b): line plot

Fig. 5 SEM model scaled scores for six factors in each class. (a): radar charts; (b): dot charts

By integrating variable-centered and person-centered approaches, this study bridges the gap in understanding general patterns and individual differences regarding key factors associated with higher education students' learning outcomes. The findings have implications for designing individualized interventions and support strategies to enhance student learning outcomes and mitigate educational disparities in ERTEs during crisis situations.

（通過(guò)整合以變量為中心和以人為中心的方法，本研究彌補(bǔ)了對(duì)于與高等教育學(xué)生學(xué)習(xí)成果相關(guān)的因素的一般模式和個(gè)體差異的理解的差距。研究結(jié)果對(duì)于在緊急遠(yuǎn)程教學(xué)環(huán)境中設(shè)計(jì)個(gè)性化的干預(yù)和支持策略，以促進(jìn)學(xué)生學(xué)習(xí)成果和提升教育公平具有重要意義。）