摘要：
Interictal epileptiform discharges (IED) as large intermittent electrophysiological events are associated with various severe brain disorders. Automated IED detection has long been a challenging task, and mainstream methods largely focus on singling out IEDs from backgrounds from the perspective of waveform, leaving normal sharp transients/artifacts with similar waveforms almost unattended. An open issue still remains to accurately detect IED events that directly reflect the abnormalities in brain electrophysiological activities, minimizing the interference from irrelevant sharp transients with similar waveforms only. This study then proposes a dual-view learning framework (namely V2IED) to detect IED events from multi-channel EEG via aggregating features from the two phases: (1) Morphological Feature Learning: directly treating the EEG as a sequence with multiple channels, a 1D-CNN (Convolutional Neural Network) is applied to explicitly learning the deep morphological features; and (2) Spatial Feature Learning: viewing the EEG as a 3D tensor embedding channel topology, a CNN captures the spatial features at each sampling point followed by an LSTM (Long Short-Term Memories) to learn the evolution of these features. Experimental results from a public EEG dataset against the state-of-the-art counterparts indicate that: (1) compared with the existing optimal models, V2IED achieves a larger area under the receiver operating characteristic (ROC) curve in detecting IEDs from normal sharp transients with a 5.25% improvement in accuracy; (2) the introduction of spatial features improves performance by 2.4% in accuracy; and (3) V2IED also performs excellently in distinguishing IEDs from background signals especially benign variants.
期刊：
IEEE Transactions on Dielectrics and Electrical Insulation,2024年31(4):2198-2207
作者机构：
[Hai Liu] National Engineering Research Center for E-Learning, Central China Normal University, Wuhan, China;[Yi Deng] School of Electronic and Electrical Engineering and the State Key Laboratory of New Textile Materials and Advanced Processing Technologies, Wuhan Textile University, Wuhan, China;[Kuihu Zhu; Jiazheng Liu] School of Electronic and Electrical Engineering, Wuhan Textile University, Wuhan, China
摘要：
Partial discharge pattern recognition (PDPR) is the fundamental cornerstone for fault diagnosis. It has emerged as a pivotal focal point in the field of power systems. However, PDPR faces several challenges, such as low signal quality and complex discharge patterns. We propose a multiscale residual aggregation transformer network (MRATNet) to address these challenges effectively. MRATNet learns long-dependent semantic relationships and discriminative features in partial discharge (PD) signals. Moreover, it integrates convolutional and transformer architectures as the feature extraction backbone. Thus, multiscale residual convolution (MSRC) blocks are incorporated to aggregate diverse information, and the transformer is leveraged to capture long-dependent semantic relationships. Meanwhile, the cross-attention mechanism is introduced to capture the spatial and channel feature distributions. The composite embedded feature selection (CEFS) module is proposed to extract discriminative features. Comprehensive experiments demonstrate the effectiveness of MRATNet, yielding exceptional performance on DEPD dataset (91.47%) and PDMDB dataset (86.05%). Finally, extended experiments have been conducted using the Technical University of Berlin’s German emotional language library, suggesting the potential for generalizing our method to other recognition tasks.
作者机构：
[Qiao, Yufei; Zhu, Min; Sun, Wen] Department of Otorhinolaryngology, Peking Union Medical College Hospital, Beijing, People's Republic of China;[Sun, Yang] School of Educational Science, Shenyang Normal University, Shenyang, People's Republic of China;[Cai, Chang; Long, Yuanshun] National Engineering Research Center for E-Learning, Central China Normal University, Wuhan, People's Republic of China;[Guo, Hua] Department of Biomedical Engineering, School of Medicine, Tsinghua University, Beijing, People's Republic of China;[Shen, Hang] Department of Neurology, Peking Union Medical College Hospital, Beijing, People's Republic of China. Electronic address: shenhang12@sina.com
通讯机构：
[Shen, Hang; Shang, Yingying] D;Department of Neurology, Peking Union Medical College Hospital, Beijing, People's Republic of China. Electronic address:;Department of Otorhinolaryngology, Peking Union Medical College Hospital, Beijing, People's Republic of China. Electronic address:
摘要：
Evidence from epidemiological studies suggests that hearing loss is associated with an accelerated decline in cognitive function, but the underlying pathophysiological mechanism remains poorly understood. Studies using auditory tasks have suggested that degraded auditory input increases the cognitive load for auditory perceptual processing and thereby reduces the resources available for other cognitive tasks. Attention-related networks are among the systems overrecruited to support degraded auditory perception, but it is unclear how they function when no excessive recruitment of cognitive resources for auditory processing is needed. Here, we implemented an EEG study using a nonauditory visual attentional selection task in 30 individuals with age-related hearing loss (ARHLs, 60-73 years) and compared them with aged (N = 30, 60-70 years) and young (N = 35, 22-29 years) normal-hearing controls. Compared with their normal-hearing peers, ARHLs demonstrated a significant amplitude reduction for the posterior contralateral N2 component, which is a well-validated index of the allocation of selective visual attention, despite the comparable behavioral performance. Furthermore, the amplitudes were observed to correlate significantly with hearing acuities (pure tone audiometry thresholds) and higher-order hearing abilities (speech-in-noise thresholds) in aged individuals. The target-elicited alpha lateralization, another mechanism of visuospatial attention, demonstrated in control groups was not observed in ARHLs. Although behavioral performance is comparable, the significant decrease in N2pc amplitude in ARHLs provides neurophysiologic evidence that may suggest a visual attentional deficit in ARHLs even without extra-recruitment of cognitive resources by auditory processing. It supports the hypothesis that constant degraded auditory input in ARHLs has an adverse impact on the function of cognitive control systems, which is a possible mechanism mediating the relationship between hearing loss and cognitive decline.
作者：
Li, Jiayuan;Bai, Jie;Zhu, Sha;Yang, Harrison Hao
期刊：
Electronics,2024年13(2):385- ISSN：2079-9292
通讯作者：
Zhu, S;Yang, HH
作者机构：
[Zhu, Sha; Zhu, S; Bai, Jie; Li, Jiayuan] Cent China Normal Univ, Natl Engn Res Ctr E Learning, Wuhan 430079, Peoples R China.;[Yang, HH; Yang, Harrison Hao] SUNY Coll Oswego, Sch Educ, Oswego, NY 13126 USA.
通讯机构：
[Yang, HH ] S;[Zhu, S ] C;Cent China Normal Univ, Natl Engn Res Ctr E Learning, Wuhan 430079, Peoples R China.;SUNY Coll Oswego, Sch Educ, Oswego, NY 13126 USA.
关键词：
digital literacy;digital game-based assessment;ECGD;AHP;assessment model
摘要：
<jats:p>This study measured secondary students’ digital literacy using a digital game-based assessment system that was designed and developed based on the Evidence-Centered Game Design (ECGD) approach. A total of 188 secondary students constituted the valid cases in this study. Fine-grained behavioral data generated from students’ gameplay processes were collected and recorded with the assessment system. The Delphi method was used to extract feature variables related to digital literacy from the process data, and the Analytic Hierarchy Process (AHP) method was used to construct the measurement model. The assessment results of the ECGD-based assessment had a high correlation with standardized test scores, which have been shown to be reliable and valid in prior large-scale assessment studies.</jats:p>
作者机构：
[Yang, Zongkai; Liu, Sannyuya; Duan, Huimin; Liu, Zhi; Liu, Shiqi] Cent China Normal Univ, Fac Artificial Intelligence Educ, Natl Engn Res Ctr Educ Big Data, Wuhan, Peoples R China.;[Yang, Zongkai; Liu, Sannyuya; Liu, Zhi] Cent China Normal Univ, Fac Artificial Intelligence Educ, Natl Engn Res Ctr E Learning, Wuhan, Peoples R China.;[Mu, Rui] Shenzhen Senior High Sch, Yantian Sch, Shenzhen, Peoples R China.
通讯机构：
[Liu, SQ ] C;Cent China Normal Univ, Fac Artificial Intelligence Educ, Natl Engn Res Ctr Educ Big Data, Wuhan, Peoples R China.
关键词：
Conversational agents;Online learning;Scaffolding;Zone of Proximal Development;Quasi- experiment
摘要：
Conversational agents (CAs) primarily adopt knowledge scaffolding (KS) or emotional scaffolding (ES) to intervene in learners' knowledge gain and emotional experience in online learning. However, the ill-defined design for KS and ES, as well as insufficient understanding of their interactive effects on learning outcomes, have hindered the advancement of CAs in theory and practice. This study proposed systematic KS and ES design principles based on Zone of Proximal Development and growth mindset theories. We investigated their individual and combined impacts on knowledge gain and emotional experience. A quasi -experiment was conducted with 128 undergraduate students divided into four groups, corresponding to four distinct CAs: a nonscaffolding control group (CG), ES, KS, and Knowledge and Emotional Scaffolding (K&ES) CA. The results showed that K&ES-based CA had a significant impact on knowledge gain and emotional experience, with both being slightly improved compared to CG. Besides, KS -based CA had a positive effect on knowledge gain and emotional experience, while ES -based CA only slightly improved emotional experience compared to CG. The results validated the effectiveness of the proposed ES and KS design principles. The fine-grained analysis revealed a significant correlation between the achievement positive emotion and knowledge transfer, highlighting the importance of integrating KS and ES. In conclusion, this study offers valuable theoretical, methodological, and empirical insights for utilizing CAs to optimize online learning experiences.
作者机构：
[Liu, Sannyuya; Yuan, Xin; Yue, Jieyu; Li, Zhen; Li, Qing; Liu, SNYY; Hu, Tianhui; Chen, Sijing; Sun, Jianwen] Cent China Normal Univ, Natl Engn Res Ctr Educ Big Data, Wuhan 430079, Peoples R China.;[Liu, Sannyuya; Liu, SNYY] Cent China Normal Univ, Natl Engn Res Ctr E Elearning, Wuhan 430079, Peoples R China.
通讯机构：
[Liu, SNYY ; Chen, SJ] C;Cent China Normal Univ, Natl Engn Res Ctr Educ Big Data, Wuhan 430079, Peoples R China.;Cent China Normal Univ, Natl Engn Res Ctr E Elearning, Wuhan 430079, Peoples R China.
摘要：
The purpose of this study was to investigate the frontier, science, and public engagement of educational science research. This paper conducted a systematic literature review of 101 educational science research articles published in Nature and Science in 1982-2021 based on the Web of Science database and analyzed the current status of research in terms of basic publication characteristics, research themes, and research processes. Five research topics were recognized, namely, education policy evaluation and reform, learning mechanisms and learning interventions, science education, educational technology, and education equity. Content of each topic had a distinctive emphasis. Findings revealed that most studies were dominated by empirical research, involving causal relationships between various educational phenomena, diverse range of research subjects, rigorous scientific randomized experiments, and quantitative analysis. We encourage more research on educational science in the future from four feasible directions, namely, developing active learning approaches to promoting effective learning, extending the research subjects and objectives of science education, conducting long-term, large-scale and practice-oriented research, and introducing new research methods into educational research.
期刊：
IEEE JOURNAL OF BIOMEDICAL AND HEALTH INFORMATICS,2024年PP:1-12 ISSN：2168-2194
作者机构：
[Xueli Pan; Frank van Harmelen] Department of Computer Science, Vrije Universiteit Amsterdam, Amsterdam, The Netherlands;Hubei Provincial Key Laboratory of Artificial Intelligence and Smart Learning, Central China Normal University, Wuhan, China;National Engineering Research Center for E-Learning, Central China Normal University, Wuhan, China;National Language Resources Monitor Research Center for Network Media, Central China Normal University, Wuhan, China;School of Computer Science, Central China Normal University, Wuhan, China
摘要：
It is commonly known that food nutrition is closely related to human health. The complex interactions between food nutrients and diseases, influenced by gut microbial metabolism, present challenges in systematizing and practically applying knowledge. To address this, we propose a method for extracting triples from a vast amount of literature, which is used to construct a comprehensive knowledge graph on nutrition and human health. Concurrently, we develop a query-based question answering system over our knowledge graph, proficiently addressing three types of questions. The results show that our proposed model outperforms other state-of-art methods, achieving a precision of 0.92, a recall of 0.81, and an F1 score of 0.86in the nutrition and disease relation extraction task. Meanwhile, our question answering system achieves an accuracy of 0.68 and an F1 score of 0.61 on our benchmark dataset, showcasing competitiveness in practical scenarios. Furthermore, we design five independent experiments to assess the quality of the data structure in the knowledge graph, ensuring results characterized by high accuracy and interpretability. In conclusion, the construction of our knowledge graph shows significant promise in facilitating diet recommendations, enhancing patient care applications, and informing decision-making in clinical research.
摘要：
Dialogue state tracking (DST) is a core component of task-oriented dialogue systems. Recent works focus mainly on end-to-end DST models that omit the spoken language understanding (SLU) module to directly obtain the dialogue state based on a user’s dialogue. However, the slot information detected by slot filling in SLU is closely tied to the slot–value pair that needs to be updated in DST. Efficient use of the key slot semantic knowledge obtained by slot filling contributes to improving the performance of DST. Based on this idea, we introduce slot filling as a subtask and build an end-to-end joint model to explicitly integrate the slot information detected by slot filling, which further guides DST. In this article, a novel stack-propagation framework with slot filling for multidomain DST is proposed. The stack-propagation framework is introduced to jointly model slot filling and DST. The framework directly feeds the key slot semantic knowledge detected by slot filling into the DST module. In addition, a slot-masked attention mechanism is designed to enable DST to focus on the key slot information obtained by slot filling. When the slot value is updated, a slot–value softcopy mechanism is designed to enhance the influence of the words marked by key slots. Experiments show that our approach outperforms previous methods and performs outstandingly on two benchmark datasets. IEEE
作者机构：
[Xu, Ruyi; Chen, Jingying] Cent China Normal Univ, Natl Engn Res Ctr Educ Big Data, 152 Luoyu Rd, Wuhan 430079, Hubei, Peoples R China.;[Chen, Jingying; Han, Jiaxu] Cent China Normal Univ, Natl Engn Res Ctr Elearning, 152 Luoyu Rd, Wuhan 430079, Hubei, Peoples R China.;[Chen, Jingying] Ningbo Yuxing Educ Technol Co Ltd, Ningbo 315200, Zhejiang, Peoples R China.
通讯机构：
[Jingying Chen] N;National Engineering Research Center of Educational Big Data, Central China Normal University, Wuhan, China<&wdkj&>National Engineering Research Center for E-learning, Central China Normal University, Wuhan, China<&wdkj&>Ningbo Yuxing Educational Technology Co., Ltd, Ningbo, China
期刊：
Education and Information Technologies,2024年:1-33 ISSN：1360-2357
通讯作者：
He, XL;Jiang, CL
作者机构：
[He, Xiuling; Fang, Jing; Li, Yangyang; Li, Yue; He, XL; Zhou, Ruijie] Cent China Normal Univ, Natl Engn Res Ctr Educ Big Data, Wuhan 430079, Peoples R China.;[He, Xiuling; Fang, Jing; Li, Yangyang; Li, Yue; He, XL; Zhou, Ruijie] Cent China Normal Univ, Natl Engn Res Ctr Elearning, Wuhan 430079, Peoples R China.;[Jiang, CL; Jiang, Chunlian] Univ Macau, Fac Educ, Macau, Peoples R China.
通讯机构：
[Jiang, CL ] U;[He, XL ] C;Cent China Normal Univ, Natl Engn Res Ctr Educ Big Data, Wuhan 430079, Peoples R China.;Cent China Normal Univ, Natl Engn Res Ctr Elearning, Wuhan 430079, Peoples R China.;Univ Macau, Fac Educ, Macau, Peoples R China.
摘要：
Computational thinking (CT), as one of the key skills in the twenty-first century, has been integrated into educational programming as an important learning goal. This study aims to explore CT processes involved in pair programming with the support of visual flow design. Thirty freshmen participated, working in pairs to solve two programming problems. Their discourses were recorded, transcribed, and coded based on a CT framework encompassing cognitive, practical, and social perspectives. Both quantitative and qualitative methods were applied to analyze the data. In particular, Epistemic Network Analysis (ENA) was applied to explore the patterns of their CT processes. The findings revealed that social perspectives emerged the most frequently in all pairs’ discourses. The high-level groups (HLGs) focused more on practical and social perspectives whereas the low-level groups (LLGs) emphasized more on cognitive perspectives. The ENA networks revealed that social perspectives mostly centered around cognitive perspectives for all pairs with CT process patterns in HLGs crossing the three perspectives more frequently. In addition, HLGs exhibited a more complicated and developmental trend in solving the two problems, while LLGs displayed a relatively similar CT pattern. The current study provides insights into the design and implementation of collaborative learning activities in educational programming.
作者机构：
[Zhang, Miao] Cent China Normal Univ, Natl Engn Res Ctr E Learning, Wuhan 430079, Peoples R China.;[Zhang, Miao; He, Tingting; Dong, Ming; Dong, M] Cent China Normal Univ, Hubei Prov Key Lab Artificial Intelligence & Smart, Wuhan 430079, Peoples R China.;[Zhang, Miao; He, Tingting; Dong, Ming; Dong, M] Cent China Normal Univ, Natl Language Resources Monitoring & Res Ctr Netwo, Wuhan 430079, Peoples R China.;[He, Tingting; Dong, Ming; Dong, M] Cent China Normal Univ, Sch Comp, Wuhan 430079, Peoples R China.
通讯机构：
[He, TT; Dong, M ] C;Cent China Normal Univ, Hubei Prov Key Lab Artificial Intelligence & Smart, Wuhan 430079, Peoples R China.;Cent China Normal Univ, Natl Language Resources Monitoring & Res Ctr Netwo, Wuhan 430079, Peoples R China.;Cent China Normal Univ, Sch Comp, Wuhan 430079, Peoples R China.
摘要：
Commonsense question answering (CQA) requires understanding and reasoning over QA context and related commonsense knowledge, such as a structured Knowledge Graph (KG). Existing studies combine language models and graph neural networks to model inference. However, traditional knowledge graph are mostly concept-based, ignoring direct path evidence necessary for accurate reasoning. In this paper, we propose MRGNN (Meta-path Reasoning Graph Neural Network), a novel model that comprehensively captures sequential semantic information from concepts and paths. In MRGNN, meta-paths are introduced as direct inference evidence and an original graph neural network is adopted to aggregate features from both concepts and paths simultaneously. We conduct sufficient experiments on the CommonsenceQA and OpenBookQA datasets, showing the effectiveness of MRGNN. Also, we conduct further ablation experiments and explain the reasoning behavior through the case study.
作者机构：
[Gao, Ya; Kong, Xi; Liu, Zhi; Zhao, Liang] Cent China Normal Univ, Natl Engn Res Ctr Educ Big Data, Wuhan, Hubei, Peoples R China.;[Liu, Zhi; Zhao, Liang] Cent China Normal Univ, Natl Engn Res Ctr E Learning, Wuhan, Hubei, Peoples R China.;[Yang, Yuqin] Cent China Normal Univ, Fac Artificial Intelligence Educ, Sch Educ Informat Technol, Wuhan, Hubei, Peoples R China.;[Gao, Y] 152 Luoyu Rd, Wuhan 430079, Hubei, Peoples R China.
通讯机构：
[Gao, Y ] 1;152 Luoyu Rd, Wuhan 430079, Hubei, Peoples R China.
关键词：
Cognitive engagement;Collaborative programming;Epistemic network analysis;Learning outcomes;Students' perceptions of collaboration
摘要：
Collaborative programming is being increasingly used to overcome the difficulties of the individual programming process. In this study, we investigated the effect of collaborative perception on cognitive engagement and learning outcomes in collaborative programming. We used a quasi-experimental research to determine the differences in cognitive engagement and learning outcomes of three groups with different levels of collaborative perception. The findings highlight several important conclusions. First, there were significant differences in cognitive engagement and learning outcomes across collaborative perception groups. Students with high levels of collaborative perception demonstrate more comprehensive and diverse cognitive engagement, resulting in higher learning outcomes compared to those with lower perception. Second, students in the low collaborative perception group had more Clarification-Elaboration cognitive connections, and students in the high collaborative perception group had stronger Clarification-Positioning and Clarification-Verification cognitive connections. Third, collaborative perception positively moderated the relationship between cognitive engagement and learning outcomes. In particular, three cognitive engagement, Clarification, Elaboration, and Positioning, had a greater impact on performance when moderated by collaborative perceptions. These findings have practical implications for educators and course designers, emphasizing the importance of considering students' collaborative perception when forming groups and promoting effective collaborative programming.
摘要：
To monitor and assess social dynamics and risks at large gatherings, we propose "SocialVis," a comprehensive monitoring system based on multi-object tracking and graph analysis techniques. Our SocialVis includes a camera detection system that operates in two modes: a real-time mode, which enables participants to track and identify close contacts instantly, and an offline mode that allows for more comprehensive post-event analysis. The dual functionality not only aids in preventing mass gatherings or overcrowding by enabling the issuance of alerts and recommendations to organizers, but also allows for the generation of proximity-based graphs that map participant interactions, thereby enhancing the understanding of social dynamics and identifying potential high-risk areas. It also provides tools for analyzing pedestrian flow statistics and visualizing paths, offering valuable insights into crowd density and interaction patterns. To enhance system performance, we designed the SocialDetect algorithm in conjunction with the BYTE tracking algorithm. This combination is specifically engineered to improve detection accuracy and minimize ID switches among tracked objects, leveraging the strengths of both algorithms. Experiments on both public and real-world datasets validate that our SocialVis outperforms existing methods, showing 1.2%$$ 1.2\% $$ improvement in detection accuracy and 45.4%$$ 45.4\% $$ reduction in ID switches in dense pedestrian scenarios. Our SocialVis is a framework for visualizing social dynamics, providing real-time monitoring of individual behavior and social distancing in crowds. Its SocialDetect algorithm, using LSKA attention and Wise-IOUv3 loss, improves accuracy in dense settings with occlusion and scale changes. To simulate interactions among individuals, we employ a graph theory-based approach that utilizes multi-object tracking, combined with SPGA, PFV, and PPV techniques, to provide comprehensive insights into crowd behavior. image
期刊：
BRITISH JOURNAL OF EDUCATIONAL TECHNOLOGY,2024年 ISSN：0007-1013
通讯作者：
Zhu, S
作者机构：
[Yang, Harrison Hao] SUNY Coll Oswego, Sch Educ, Oswego, NY USA.;[Zhu, Sha; Zhu, S; Yin, Zhongyue] Cent China Normal Univ, Natl Engn Res Ctr E Learning, 152 Luoyu Rd, Wuhan, Hubei, Peoples R China.
通讯机构：
[Zhu, S ] C;Cent China Normal Univ, Natl Engn Res Ctr E Learning, 152 Luoyu Rd, Wuhan, Hubei, Peoples R China.
摘要：
Abstract The HyFlex course has been widely adopted in higher education settings. However, there is a paucity of empirical studies examining students' acceptance of large‐scale HyFlex courses, as well as factors influencing their acceptance. To fill this research gap, the present study investigated students' acceptance of a large‐scale HyFlex course and the variations in their acceptance according to different participation modes (ie, on‐site, synchronously online and mixed attendance), based on a total of 160 valid samples from a large‐scale HyFlex course at a normal university in central China during the fall semester of 2022. The results indicated that students' overall HyFlex course acceptance was generally high, and the students who alternately engaged in on‐site and synchronously online learning had the highest level of acceptance. Furthermore, this study employed structural equation modelling to validate a model integrating the unified theory of acceptance and use of technology with connected classroom climate (CCC). The findings showed that performance expectancy (PE), effort expectancy, facilitating conditions and CCC directly influenced students' acceptance, with performance expectancy having the strongest direct effect. However, social influence only had an indirect effect on students' acceptance, while CCC had both direct and indirect effects. This study carries substantial theoretical and practical implications, enhancing our understanding of students' acceptance of the HyFlex learning approach.Practitioner notesWhat is already known about this topic The adoption of the HyFlex course, especially in the context of large‐scale courses, is prevalent in higher education settings. Existing studies have predominately focused on assessing the impact of HyFlex course on student engagement and learning outcomes, the development and implementation of HyFlex course structures, and educators' perspectives and experiences with HyFlex courses. Although some research has delved into students' satisfaction with HyFlex courses, particularly in small class settings, our understanding of students' acceptance of large‐scale HyFlex course remains limited. There has been a noticeable gap in investigations exploring distinctions among students who opt for varying HyFlex course delivery modes, such as on‐site, synchronously online and mixed attendance formats. What this paper adds This study reveals that students generally displayed a high level of acceptance towards the large‐scale HyFlex course. Notably, students who participated in alternating on‐site and synchronously online learning exhibited a significantly higher level of acceptance towards the HyFlex course compared to their counterparts. A novel approach was employed in this study by integrating the UTAUT model with the concept of connected classroom climate (CCC) to comprehensively explore the key influencing factors and their interrelationships regarding students' acceptance of a large‐scale HyFlex course. The study found that performance expectancy (PE), effort expectancy (EE), facilitating conditions (FC) and CCC were all significant factors that positively influenced students' acceptance of the HyFlex course. Particularly, PE emerged as the factor with the strongest direct impact on HyFlex course acceptance (ACP). Interestingly, social influence (SI) did not exhibit a significant direct effect on students' ACP. However, it had a significant and positive indirect effect on students' ACP through the mediation of PE. Furthermore, CCC was shown to have both direct and indirect effects on students' acceptance of the HyFlex course, with the indirect effect of CCC on ACP accounted for nearly half of the total effect. Implications for practice and/or policy Instructors should prioritize emphasizing the advantages and benefits of HyFlex courses to enhance students' motivation and willingness to participate actively in these courses. This may involve showcasing how HyFlex course offer flexibility, convenience and varied learning opportunities. When implementing HyFlex courses, instructors should work to mitigate students' perceived EE. This could be achieved through streamlining course navigation, ensuring user‐friendly technology tools and providing clear guidelines for participation. Simultaneously, efforts should be made to enhance perceived learning support to facilitate students' engagement and acceptance of HyFlex courses. Instructors in HyFlex course settings should place a strong emphasis on creating a supportive and collaborative learning environment. This involves fostering interactions among students, encouraging peer‐to‐peer support and providing resources and guidance to help students navigate the challenges and opportunities presented by HyFlex course formats. Building a sense of community and connectedness among students can significantly impact their acceptance and success in such courses.
作者机构：
[Tan, Yuanjun; Chen, Zengzhao; Liu, Quanling; Wang, Shengming; Liu, Hai] Cent China Normal Univ, Fac Artificial Intelligence Educ, Wuhan 430079, Peoples R China.;[Liu, Tingting] Hubei Univ, Sch Educ, Wuhan 430072, Peoples R China.;[Chen, Zengzhao; Liu, Hai] Cent China Normal Univ, Natl Engn Res Ctr E Learning, Wuhan 430079, Peoples R China.;[Liu, Hai] Cent China Normal Univ, Shenzhen Res Inst, Shenzhen 518051, Peoples R China.
通讯机构：
[Chen, ZZ ] C;Cent China Normal Univ, Fac Artificial Intelligence Educ, Wuhan 430079, Peoples R China.;Cent China Normal Univ, Natl Engn Res Ctr E Learning, Wuhan 430079, Peoples R China.
摘要：
The pre-trained language model based on Transformers possesses exceptional general text-understanding capabilities, empowering it to adeptly manage a variety of tasks. However, the topic classification ability of the pre-trained language model will be seriously affected in the face of long colloquial texts, expressions with similar semantics but completely different expressions, and text errors caused by partial speech recognition. We propose a long-text topic classification method called RQ-OSPTrans to effectively address these challenges. To this end, two parallel learning modules are proposed to learn long texts, namely, the repeat question module and the overall semantic perception module. The overall semantic perception module will conduct average pooling on the semantic embeddings produced by BERT, in addition to multi-layer perceptron learning. The repeat question module will learn the text-embedding matrix, extracting detailed clues for classification based on words as fundamental elements. Comprehensive experiments demonstrate that RQ-OSPTrans can achieve a generalization performance of 98.5% on the Chinese dataset THUCNews. Moreover, RQ-OSPTrans can achieve state-of-the-art performance on the arXiv-10 dataset (84.4%) and has a comparable performance with other state-of-the-art pre-trained models on the AG’s News dataset. Finally, the results indicate that our method exhibits a superior performance compared with the baseline methods on small-scale domain-specific datasets by validating RQ-OSPTrans on a specific task scenario by using our custom-built dataset CCIPC.
