Search

Your search keyword '"Li, Yuheng"' showing total 351 results
Start Over Author "Li, Yuheng" Search Limiters Academic (Peer-Reviewed) Journals
351 results on '"Li, Yuheng"'

9. Practical and Ethical Challenges of Large Language Models in Education: A Systematic Scoping Review

Author

Yan, Lixiang, Sha, Lele, Zhao, Linxuan, Li, Yuheng, Martinez-Maldonado, Roberto, Chen, Guanliang, Li, Xinyu, Jin, Yueqiao, and Gašević, Dragan

Subjects
Computer Science - Computation and Language, Computer Science - Artificial Intelligence, Computer Science - Computers and Society
Abstract

Educational technology innovations leveraging large language models (LLMs) have shown the potential to automate the laborious process of generating and analysing textual content. While various innovations have been developed to automate a range of educational tasks (e.g., question generation, feedback provision, and essay grading), there are concerns regarding the practicality and ethicality of these innovations. Such concerns may hinder future research and the adoption of LLMs-based innovations in authentic educational contexts. To address this, we conducted a systematic scoping review of 118 peer-reviewed papers published since 2017 to pinpoint the current state of research on using LLMs to automate and support educational tasks. The findings revealed 53 use cases for LLMs in automating education tasks, categorised into nine main categories: profiling/labelling, detection, grading, teaching support, prediction, knowledge representation, feedback, content generation, and recommendation. Additionally, we also identified several practical and ethical challenges, including low technological readiness, lack of replicability and transparency, and insufficient privacy and beneficence considerations. The findings were summarised into three recommendations for future studies, including updating existing innovations with state-of-the-art models (e.g., GPT-3/4), embracing the initiative of open-sourcing models/systems, and adopting a human-centred approach throughout the developmental process. As the intersection of AI and education is continuously evolving, the findings of this study can serve as an essential reference point for researchers, allowing them to leverage the strengths, learn from the limitations, and uncover potential research opportunities enabled by ChatGPT and other generative AI models.

Published
2023
Full Text
View/download PDF

10. Automatic Classification of Learning Objectives Based on Bloom's Taxonomy

Author

Li, Yuheng, Rakovic, Mladen, Poh, Boon Xin, Gaševic, Dragan, and Chen, Guanliang

Abstract

Learning objectives, especially those well defined by applying Bloom's taxonomy for Cognitive Objectives, have been widely recognized as important in various teaching and learning practices. However, many educators have difficulties developing learning objectives appropriate to the levels in Bloom's taxonomy, as they need to consider the progression of learners' skills with learning content as well as dependencies between different learning objectives. To remedy this challenge, we aimed to apply state-of-the-art computational techniques to automate the classification of learning objectives based on Bloom's taxonomy. Specifically, we collected 21,380 learning objectives from 5,558 different courses at an Australian university and manually labeled them according to the six cognitive levels of Bloom's taxonomy. Based on the labeled dataset, we applied five conventional machine learning approaches (i.e., naive Bayes, logistic regression, support vector machine, random forest, and XGBoost) and one deep learning approach based on pre-trained language model BERT to construct classifiers to automatically determine a learning objective's cognitive levels. In particular, we adopted and compared two methods in constructing the classifiers, i.e., constructing multiple binary classifiers (one for each cognitive level in Bloom's taxonomy) and constructing only one multi-class multi-label classifier to simultaneously identify all the corresponding cognitive levels. Through extensive evaluations, we demonstrated that: (i) BERT-based classifiers outperformed the others in all cognitive levels (Cohen's K up to 0.93 and F1 score up to 0.95); (ii) three machine learning models -- support vector machine, random forest, and XGBoost -- delivered performance comparable to the BERT-based classifiers; and (iii) most of the binary BERT-based classifiers (5 out of 6) slightly outperformed the multi-class multi-label BERT-based classifier, suggesting that separating the characterization of different cognitive levels seemed to be a better choice than building only one model to identify all cognitive levels at one time. [For the full proceedings, see ED623995.]

Published
2022

11. Bone marrow-derived mesenchymal stem cells relieve the adverse effects of simulated microgravity on mouse cerebral cortex

Author

GONG Jintao, LI Jianwei, LI Yuheng, LI Qian, ZHAO Chunhua

Subjects
mesenchymal stem cells, microgravity, hindlimb unloading, apoptosis, cellular senescence, Medicine
Abstract

Objective To explore the protective effects and the underlying mechanisms of bone marrow mesenchymal stem cells (BMSCs) on the brain in microgravity environment. Methods The physiological effects of microgravity were simulated with the hindlimb unloading (HU) mouse model. The animals were divided into 3 groups: the control group (wild-type mice), the hindlimb unloading (HU) group, and the BMSCs treatment group, with six in each. RT-qPCR was adopted to determine the expression levels of pro-inflammatory cytokines (Il-6, Il-1β and Tnf-α) in the cerebral cortex; immunohistochemistry was performed to evaluate the proportions of microglia (IBA-positive) and astrocytes (GFAP-positive); Western blot was used to measure the expression levels of apoptosis-and senescence-related molecules (BAX, BCL-2, p21, and p53). Results Compared with wild-type mice, the expression levels of Il-6, Il-1β and Tnf-α in the cerebral cortex of HU mice were significantly increased (P＜0.05), the expression level of BAX, p21 and p53 was also significantly increased(P＜0.05). However, the expression level of BCL-2 protein were significantly decreased (P＜0.05). The proportion of microglia (IBA1 positive) and astrocytes (GFAP positive) was increased (P＜0.05); After BMSCs treatment, the expression level of Il-1β in the cerebral cortex of HU mice was significantly decreased (P＜0.05), the expression levels of BAX, p21 and p53 were significantly decreased (P＜0.05), and the expression level of BCL-2 protein was significantly increased (P＜0.05). The proportion of microglia (IBA1 positive) and astrocytes (GFAP positive) decreased (P＜0.05). Conclusions BMSCs potentially relieve the detrimental effects of simulated microgravity on mouse brain by inhibiting inflammation, apoptosis and cellular senescence.

Published
2024
Full Text
View/download PDF

12. Fe nanoparticle-functionalized ordered mesoporous carbon with tailored mesostructures and their applications in magnetic removal of Ag(i)

Author

Zhang Wenjuan, Li Yuheng, Ran Mengyu, Wang Youliang, Ding Yezhi, Zhang Bobo, Feng Qiancheng, Chu Qianqian, Shen Yongqian, and Sheng Wang

Subjects
fe, ordered mesoporous carbon, ag(i), adsorption, Technology, Chemical technology, TP1-1185
Abstract

Fe nanoparticle-functionalized ordered mesoporous carbon (Fe0/OMC) was synthesized using triblock copolymers as templates and through solvent evaporation self-assembly, followed by a carbothermal reduction. Fe0/OMC had three microstructures of two-dimensional hexagonal (space group, p6mm, Fe0/OMC-1), body centered cubic (Im3̄m, Fe0/OMC-2), and face centered cubic (Fm3̄m, Fe0/OMC-3) which were controlled by simply adjusting the template. All Fe0/OMC displayed paramagnetic characteristics, with a maximum saturation magnetization of 50.1 emu·g−1. This high magnetization is advantageous for the swift extraction of the adsorbent from the solution following the adsorption process. Fe0/OMC was used as an adsorbent for the removal of silver ions (Ag(i)) from aqueous solutions, and the adsorption capacity of Fe0/OMC-1 was enhanced by the functionalization of Fe0. Adsorption property of Fe0/OMC-1 was significantly higher than that of Fe0/OMC-2 and Fe0/OMC-3, indicating that the long and straight ordered pore channels were more favorable for adsorption, and the adsorption capacity of Ag(i) on Fe0/OMC-1 was 233 mg·g−1. The adsorption process exhibited conformity with both the pseudo-second-order kinetic model and the Freundlich model, suggesting that the dominant mechanism of adsorption involved multilayer adsorption on heterogeneous surfaces.

Published
2024
Full Text
View/download PDF

14. Which Hammer Should I Use? A Systematic Evaluation of Approaches for Classifying Educational Forum Posts

Author

Sha, Lele, Rakovic, Mladen, Li, Yuheng, Whitelock-Wainwright, Alexander, Carroll, David, Gaševic, Dragan, and Chen, Guanliang

Abstract

Classifying educational forum posts is a longstanding task in the research of Learning Analytics and Educational Data Mining. Though this task has been tackled by applying both traditional Machine Learning (ML) approaches (e.g., Logistics Regression and Random Forest) and up-to-date Deep Learning (DL) approaches, there lacks a systematic examination of these two types of approaches to portray their performance difference. To better guide researchers and practitioners to select a model that suits their needs the best, this study aimed to systematically compare the effectiveness of these two types of approaches for this specific task. Specifically, we selected a total of six representative models and explored their capabilities by equipping them with either extensive input features that were widely used in previous studies (traditional ML models) or the state-of-the-art pre-trained language model BERT (DL models). Through extensive experiments on two real-world datasets (one is open-sourced), we demonstrated that: (i) DL models uniformly achieved better classification results than traditional ML models and the performance difference ranges from 1.85% to 5.32% with respect to different evaluation metrics; (ii) when applying traditional ML models, different features should be explored and engineered to tackle different classification tasks; (iii) when applying DL models, it tends to be a promising approach to adapt BERT to the specific classification task by fine-tuning its model parameters. [For the full proceedings, see ED615472.]

Published
2021

Catalog

Books, media, physical & digital resources
See catalog results