Incorporating Features Learned by an Enhanced Deep Knowledge Tracing Model for STEM/Non-STEM Job Prediction

Yeung, Chun Kit; Yeung, Dit Yan

doi:10.1007/s40593-019-00175-1

Cited by 26 publications

(10 citation statements)

References 16 publications

(19 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Although ML models have shown great potential in predicting students' cognitive and affective outcomes, most of the existing studies focused on students' academic achievement and career choice, with little attention to their subjective well‐being (Dong & Hu, 2019; Mandalapu & Gong, 2019; Puah, 2021; Yeung & Yeung, 2019). Although several studies paid attention to subjective well‐being, few of them investigated the effects of student‐related variables, such as the teacher support and learning goals (Kaiser et al., 2021; Morrone et al., 2019; You, 2021).…”

Section: Literature Reviewmentioning

confidence: 99%

Using machine learning to predict UK and Japanese secondary students' life satisfaction in PISA 2018

Pan,

Cutumisu

2023

Brit J of Edu Psychol

View full text Add to dashboard Cite

BackgroundLife satisfaction is a key component of students' subjective well‐being due to its impact on academic achievement and lifelong health. Although previous studies have investigated life satisfaction through different lenses, few of them employed machine learning (ML) approaches.ObjectiveUsing ML algorithms, the current study predicts secondary students' life satisfaction from individual‐level variables.MethodTwo supervised ML models, random forest (RF) and k‐nearest neighbours (KNN), were developed based on the UK data and the Japan data in PISA 2018.ResultsFindings show that (1) both models yielded better performance on the UK data than on the Japanese data; (2) the RF model outperformed the KNN model in predicting students' life satisfaction; (3) meaning in life, student competition, teacher support, exposure to bullying and ICT resources at home and at school played important roles in predicting students' life satisfaction.ConclusionsTheoretically, this study highlights the multi‐dimensional nature of life satisfaction and identifies several key predictors. Methodologically, this study is the first to use ML to explore the predictors of life satisfaction. Practically, it serves as a reference for improving secondary students' life satisfaction.

show abstract

Section: Literature Reviewmentioning

confidence: 99%

Using machine learning to predict UK and Japanese secondary students' life satisfaction in PISA 2018

Pan,

Cutumisu

2023

Brit J of Edu Psychol

View full text Add to dashboard Cite

show abstract

“…Gan et al came up with a modeling method integrating such features as learners' ability, the difficulty of cognitive items, learning, and forgetting [31]. Yeung et al combined the prediction results of the DKT+ model with the student features extracted from datasets to predict whether students would be occupied in STEM professions [32]. Wu et al introduced a KT-based test paper generation method [33].…”

Section: State Of the Artmentioning

confidence: 99%

Higher Education-Oriented Recommendation Algorithm for Personalized Learning Resource

Zhang

Xiao

2022

Int. J. Emerg. Technol. Learn.

View full text Add to dashboard Cite

As smart education is continuously deepened in higher education, personalized learning resource recommendation has developed into a significant research field of smart learning. Although the prediction accuracy has been improved by knowledge tracing models established on the basis of students’ historical learning data, how to design and apply personalized learning recommendation by combining classroom teaching of higher education is a great difficulty.To recommend personalized learning resources meeting the teaching requirements in higher education, the Q-LRDP-D (Learning Resource Difficulty Prediction and Dijkstra based on Q matrix) algorithm was proposed in this study. First, learning resources were modeled in accordance with Q matrix theory. Then, students’ learning difficulty was predicted through the long short-term memory (LSTM) algorithm of a learning resource difficulty prediction module, followed by cyclic prediction through combining the to-be-learned knowledge points as required by teaching units to form a directed path diagram of learning resources. Next, the least learning resources conforming to students’ learning levels were recommended using the shortest path algorithm to complete learning tasks. Lastly, the accuracy and effectiveness of the established model were verified through undergraduate teaching experiments. Results demonstrate that the modeling of learning resources in higher education on the basis of Q matrix theory is applicable to the LSTM algorithm. In comparison with the benchmark algorithm, its precision is obviously improved. With the recommendation algorithm, the average return on learning resources in the experimental class is 6.31, which is considerably higher than that in the control group. This study provides a certain reference for improving students’ learning efficiency through recommendation algorithms in higher education and teaching.

show abstract

“…The dataset used is ASSISTments 2009−2010 and area under a ROC curve (AUC) as evaluation metric. This evaluation metric's advantages include supporting a summary of performance measurement and robust metrics across all possible thresholds [16]. The higher AUC score indicates that the model applied has a good performance.…”

Section: Fig3 Distribution Of Proposed Models Using a Probabilistic Approachmentioning

confidence: 99%

A Literature Review of Knowledge Tracing for Student Modeling : Research Trends, Models, Datasets, and Challenges

Hilda¹,

Hidayah

Kusumawardani

2021

JITeCS

View full text Add to dashboard Cite

Modeling students' knowledge is a fundamental part of online learning platforms. Knowledge tracing is an application of student modeling which renowned for its ability to trace students' knowledge. Knowledge tracing ability can be used in online learning platforms for predicting learning performance and providing adaptive learning. Due to the wide uses of knowledge tracing in student modeling, this study aims to understand the state-of-the-art and future research of knowledge tracing. This study focused on reviewing 24 studies published between 2017 to the third quarter of 2021 in four digital databases. The selected studies have been filtered using inclusion and exclusion criteria. Several previous studies have shown that there are two approaches used in knowledge tracing, including probabilistic and deep learning. Bayesian Knowledge Tracing model is the most widely used in the probabilistic approach, while the Deep Knowledge Tracing model is the most popular model in the deep learning approach. Meanwhile, ASSISTments 2009–2010 is the most frequently tested dataset for probabilistic and deep learning approaches. In the future, additional studies are required to explore several models which have been developed previously. Therefore this study provides direction for future research of each existing approach.

show abstract

Incorporating Features Learned by an Enhanced Deep Knowledge Tracing Model for STEM/Non-STEM Job Prediction

Cited by 26 publications

References 16 publications

Using machine learning to predict UK and Japanese secondary students' life satisfaction in PISA 2018

Using machine learning to predict UK and Japanese secondary students' life satisfaction in PISA 2018

Higher Education-Oriented Recommendation Algorithm for Personalized Learning Resource

A Literature Review of Knowledge Tracing for Student Modeling : Research Trends, Models, Datasets, and Challenges

Contact Info

Product

Resources

About