{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,26]],"date-time":"2026-03-26T09:18:18Z","timestamp":1774516698126,"version":"3.50.1"},"reference-count":45,"publisher":"PeerJ","license":[{"start":{"date-parts":[[2026,3,26]],"date-time":"2026-03-26T00:00:00Z","timestamp":1774483200000},"content-version":"unspecified","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"abstract":"<jats:sec>\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>The development of intelligent education has made student performance prediction based on student comments and course information an important direction for achieving personalized teaching. Student comments not only reflect knowledge mastery but also convey emotional attitudes and learning states. However, most existing approaches fail to capture the salient emotional cues and structural patterns in comments or to leverage course-level information effectively, leading to limited predictive performance and interpretability.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>To address these issues, we propose a position-aware sentiment enhancement framework (PSEF-Net) designed to capture the coupling between sentiment intensity and structural positioning. Specifically, PSEF-Net introduces three core mechanisms: (1) A emotion-guided structural fusion mechanism, which constructs a heterogeneous attention path to emphasize emotionally polarized expressions and mitigate the dilution of key feedback by neutral context; (2) A position-aware residual attention gate, which leverages local structural shifts and cross-modal discrepancy representations to dynamically enhance the model\u2019s sensitivity to sentiment transitions and structural discontinuities; (3) A dual-path context modeling module, which integrates global and local semantic flows to compress redundant features and improve the representation of course-level structure.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>\n                      Experimental results on two real-world datasets from MOOC and NetEase Cloud Classroom demonstrate that PSEF-Net consistently outperforms all baselines. Compared with the second-best model Multi-dimensional Student Performance Prediction (MSPP), PSEF-Net reduces mean absolute error (MAE) by 16.4% and root mean square error (RMSE) by 9.4% on the MOOC dataset, and decreases MAE by 18.0% and RMSE by 9.9% on the NetEase dataset. All differences are statistically significant (\n                      <jats:italic>p<\/jats:italic>\n                      &lt; 0.05). Visualization analyses further confirm that PSEF-Net effectively focuses on key feedback cues across diverse comment structures, highlighting its potential for interpretable student performance prediction.\n                    <\/jats:p>\n                  <\/jats:sec>","DOI":"10.7717\/peerj-cs.3661","type":"journal-article","created":{"date-parts":[[2026,3,26]],"date-time":"2026-03-26T08:00:28Z","timestamp":1774512028000},"page":"e3661","source":"Crossref","is-referenced-by-count":0,"title":["PSEF-Net: a position-aware sentiment enhancement framework for student performance and teaching quality understanding"],"prefix":"10.7717","volume":"12","author":[{"given":"Lei","family":"Shi","sequence":"first","affiliation":[{"name":"College of Arts, Sciences and Education, Trinity University of Asia, Quezon, Philippines"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wanting","family":"Zhang","sequence":"additional","affiliation":[{"name":"College of Arts, Sciences and Education, Trinity University of Asia, Quezon, Philippines"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhenfen","family":"Wang","sequence":"additional","affiliation":[{"name":"College of Agriculture and Hydraulic Engineering, Suihua University, Suihua, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Fengsong","family":"Geng","sequence":"additional","affiliation":[{"name":"College of Arts, Sciences and Education, Trinity University of Asia, Quezon, Philippines"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiaoxue","family":"Wang","sequence":"additional","affiliation":[{"name":"Institute of Media, Shanxi Technology and Business University, Taiyuan, Shanxi, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"4443","published-online":{"date-parts":[[2026,3,26]]},"reference":[{"issue":"3","key":"10.7717\/peerj-cs.3661\/ref-1","doi-asserted-by":"publisher","first-page":"59","DOI":"10.3390\/mca30030059","article-title":"Hybrid deep learning models for predicting student academic performance","volume":"30","author":"Adefemi","year":"2025","journal-title":"Mathematical and Computational Applications"},{"key":"10.7717\/peerj-cs.3661\/ref-2","first-page":"166","article-title":"Predicting students\u2019 performance employing educational data mining techniques, machine learning, and learning analytics","author":"Alam","year":"2022"},{"key":"10.7717\/peerj-cs.3661\/ref-3","doi-asserted-by":"publisher","first-page":"100473","DOI":"10.1016\/j.dajour.2024.100473","article-title":"A hybrid machine learning model for sentiment analysis and satisfaction assessment with Turkish universities using Twitter data","volume":"11","author":"Alawi","year":"2024","journal-title":"Decision Analytics Journal"},{"issue":"1","key":"10.7717\/peerj-cs.3661\/ref-4","first-page":"1329","article-title":"Multi-class LDA classifier and CNN feature extraction for student performance analysis during COVID-19 pandemic","volume":"13","author":"Ali","year":"2022","journal-title":"International Journal of Nonlinear Analysis and Applications"},{"key":"10.7717\/peerj-cs.3661\/ref-5","doi-asserted-by":"publisher","first-page":"103148","DOI":"10.1016\/j.mex.2024.103148","article-title":"A multi-dimensional student performance prediction model (MSPP): an advanced framework for accurate academic classification and analysis","volume":"14","author":"Balachandar","year":"2025","journal-title":"MethodsX"},{"issue":"13","key":"10.7717\/peerj-cs.3661\/ref-6","doi-asserted-by":"publisher","first-page":"16813","DOI":"10.1007\/s10639-024-12526-0","article-title":"A new sentiment analysis model to classify students\u2019 reviews on MOOCs","volume":"29","author":"Baqach","year":"2024","journal-title":"Education and Information Technologies"},{"key":"10.7717\/peerj-cs.3661\/ref-7","doi-asserted-by":"publisher","first-page":"106595","DOI":"10.1016\/j.chb.2020.106595","article-title":"Early prediction of undergraduate student\u2019s academic performance in completely online learning: a five-year study","volume":"115","author":"Bravo-Agapito","year":"2021","journal-title":"Computers in Human Behavior"},{"key":"10.7717\/peerj-cs.3661\/ref-8","doi-asserted-by":"publisher","first-page":"106908","DOI":"10.1016\/j.compeleceng.2020.106908","article-title":"Multi-source and multimodal data fusion for predicting academic performance in blended learning university courses","volume":"89","author":"Chango","year":"2021","journal-title":"Computers & Electrical Engineering"},{"issue":"4","key":"10.7717\/peerj-cs.3661\/ref-9","doi-asserted-by":"publisher","first-page":"1885","DOI":"10.3390\/app12041885","article-title":"Week-wise student performance early prediction in virtual learning environment using a deep explainable artificial intelligence","volume":"12","author":"Chen","year":"2022","journal-title":"Applied Sciences"},{"key":"10.7717\/peerj-cs.3661\/ref-10","doi-asserted-by":"publisher","first-page":"5260","DOI":"10.1016\/j.matpr.2021.05.646","article-title":"Educational data mining for predicting students\u2019 academic performance using machine learning algorithms","volume":"47","author":"Dabhade","year":"2021","journal-title":"Materials Today: Proceedings"},{"key":"10.7717\/peerj-cs.3661\/ref-11","doi-asserted-by":"publisher","first-page":"728708","DOI":"10.3389\/frai.2021.728708","article-title":"Sentiment analysis of students\u2019 feedback in MOOCs: a systematic literature review","volume":"4","author":"Dalip","year":"2021","journal-title":"Frontiers in Artificial Intelligence"},{"key":"10.7717\/peerj-cs.3661\/ref-12","doi-asserted-by":"publisher","first-page":"326","DOI":"10.1016\/j.protcy.2016.08.114","article-title":"Student academic performance prediction model using decision tree and fuzzy genetic algorithm","volume":"25","author":"Hamsa","year":"2016","journal-title":"Procedia Technology"},{"issue":"10","key":"10.7717\/peerj-cs.3661\/ref-13","doi-asserted-by":"publisher","first-page":"474","DOI":"10.3390\/info11100474","article-title":"Online at-risk student identification using RNN-GRU joint neural networks","volume":"11","author":"He","year":"2020","journal-title":"Information"},{"issue":"3","key":"10.7717\/peerj-cs.3661\/ref-14","doi-asserted-by":"publisher","first-page":"3557","DOI":"10.1007\/s40747-024-01344-z","article-title":"Improving academic performance predictions with dual graph neural networks","volume":"10","author":"Huang","year":"2024","journal-title":"Complex & Intelligent Systems"},{"issue":"1","key":"10.7717\/peerj-cs.3661\/ref-15","doi-asserted-by":"publisher","first-page":"241","DOI":"10.33093\/jiwe.2024.3.1.16","article-title":"Prediction of student\u2019s academic performance through data mining approach","volume":"3","author":"Hussain","year":"2024","journal-title":"Journal of Informatics and Web Engineering"},{"issue":"1","key":"10.7717\/peerj-cs.3661\/ref-16","doi-asserted-by":"publisher","first-page":"24605","DOI":"10.1038\/s41598-024-75242-2","article-title":"SAPPNet: students\u2019 academic performance prediction during COVID-19 using neural network","volume":"14","author":"Junejo","year":"2024","journal-title":"Scientific Reports"},{"issue":"3","key":"10.7717\/peerj-cs.3661\/ref-17","doi-asserted-by":"publisher","first-page":"2973","DOI":"10.1007\/s10639-023-11736-2","article-title":"Deep learning for opinion mining and topic classification of course reviews","volume":"29","author":"Koufakou","year":"2024","journal-title":"Education and Information Technologies"},{"issue":"8","key":"10.7717\/peerj-cs.3661\/ref-18","doi-asserted-by":"publisher","first-page":"9655","DOI":"10.1007\/s10639-022-11573-9","article-title":"Prediction of student academic performance based on their emotional wellbeing and interaction on various e-learning platforms","volume":"28","author":"Kukkar","year":"2023","journal-title":"Education and Information Technologies"},{"issue":"1","key":"10.7717\/peerj-cs.3661\/ref-19","doi-asserted-by":"publisher","first-page":"159","DOI":"10.2307\/2529310","article-title":"The measurement of observer agreement for categorical data on JSTOR","volume":"33","author":"Landis","year":"1977","journal-title":"Biometrics"},{"issue":"3","key":"10.7717\/peerj-cs.3661\/ref-20","doi-asserted-by":"publisher","first-page":"130","DOI":"10.1504\/ijlt.2016.079035","article-title":"Prediction of student performance in massive open online courses using deep learning system based on learning behaviors","volume":"24","author":"Lee","year":"2021","journal-title":"Educational Technology & Society"},{"issue":"6","key":"10.7717\/peerj-cs.3661\/ref-21","doi-asserted-by":"publisher","first-page":"3092","DOI":"10.1080\/10494820.2023.2167836","article-title":"Academic performance prediction associated with synchronous online interactive learning behaviors based on the machine learning approach","volume":"32","author":"Liang","year":"2024","journal-title":"Interactive Learning Environments"},{"key":"10.7717\/peerj-cs.3661\/ref-22","doi-asserted-by":"publisher","first-page":"194894\u2013194903","DOI":"10.1109\/access.2020.3033200","article-title":"Multiple features fusion attention mechanism enhanced deep knowledge tracing for student performance prediction","volume":"8","author":"Liu","year":"2020","journal-title":"IEEE Access"},{"issue":"1","key":"10.7717\/peerj-cs.3661\/ref-23","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3458023","article-title":"Jointly modeling heterogeneous student behaviors and interactions among multiple prediction tasks","volume":"16","author":"Liu","year":"2021","journal-title":"ACM Transactions on Knowledge Discovery from Data (TKDD)"},{"key":"10.7717\/peerj-cs.3661\/ref-24","doi-asserted-by":"publisher","first-page":"e1655","DOI":"10.7717\/peerj-cs.1655","article-title":"Early prediction of student performance in CS1 programming courses","volume":"9","author":"Llanos","year":"2023","journal-title":"PeerJ Computer Science"},{"key":"10.7717\/peerj-cs.3661\/ref-25","doi-asserted-by":"publisher","first-page":"141960\u2013141969","DOI":"10.1109\/access.2019.2942614","article-title":"Sentiment analysis of text based on bidirectional LSTM with multi-head attention","volume":"7","author":"Long","year":"2019","journal-title":"IEEE Access"},{"key":"10.7717\/peerj-cs.3661\/ref-26","doi-asserted-by":"publisher","first-page":"e2576","DOI":"10.7717\/peerj-cs.2576","article-title":"Enhancing e-learning through AI: advanced techniques for optimizing student performance","volume":"10","author":"Mahafdah","year":"2024","journal-title":"PeerJ Computer Science"},{"issue":"4","key":"10.7717\/peerj-cs.3661\/ref-27","doi-asserted-by":"publisher","first-page":"4639","DOI":"10.1007\/s10639-024-12976-6","article-title":"Empowering education: harnessing ensemble machine learning approach and ACO-DT classifier for early student academic performance prediction","volume":"30","author":"Mahawar","year":"2025","journal-title":"Education and Information Technologies"},{"key":"10.7717\/peerj-cs.3661\/ref-28","first-page":"779","article-title":"An effective BiLSTM-CRF based approach to predict student achievement: an experimental evaluation","author":"Manigandan","year":"2024"},{"key":"10.7717\/peerj-cs.3661\/ref-29","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2601.06729","article-title":"Predicting student success with heterogeneous graph deep learning and machine learning models","author":"Muresan","year":"2026"},{"key":"10.7717\/peerj-cs.3661\/ref-30","first-page":"156","article-title":"Graph-based knowledge tracing: modeling student proficiency using graph neural network","author":"Nakagawa","year":"2019"},{"issue":"7","key":"10.7717\/peerj-cs.3661\/ref-31","doi-asserted-by":"publisher","first-page":"1005","DOI":"10.3390\/electronics11071005","article-title":"Prediction of student academic performance using a hybrid 2D CNN model","volume":"11","author":"Poudyal","year":"2022","journal-title":"Electronics"},{"issue":"13","key":"10.7717\/peerj-cs.3661\/ref-32","doi-asserted-by":"publisher","first-page":"e6244","DOI":"10.1002\/cpe.6244","article-title":"Minkowski Sommon feature map-based densely connected deep convolution network with LSTM for academic performance prediction","volume":"33","author":"Ramanathan","year":"2021","journal-title":"Concurrency and Computation: Practice and Experience"},{"issue":"6","key":"10.7717\/peerj-cs.3661\/ref-33","doi-asserted-by":"publisher","first-page":"601","DOI":"10.1109\/tsmcc.2010.2053532","article-title":"Educational data mining: a review of the state of the art","volume":"40","author":"Romero","year":"2010","journal-title":"IEEE Transactions on Systems, Man, and Cybernetics, Part C (Applications and Reviews)"},{"key":"10.7717\/peerj-cs.3661\/ref-34","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2204.13607","article-title":"Process-BERT: a framework for representation learning on educational process data","author":"Scarlatos","year":"2022"},{"key":"10.7717\/peerj-cs.3661\/ref-35","doi-asserted-by":"publisher","first-page":"108274","DOI":"10.1016\/j.knosys.2022.108274","article-title":"Bi-CLKT: bi-graph contrastive learning based knowledge tracing","volume":"241","author":"Song","year":"2022","journal-title":"Knowledge-Based Systems"},{"key":"10.7717\/peerj-cs.3661\/ref-36","doi-asserted-by":"publisher","first-page":"109547","DOI":"10.1016\/j.knosys.2022.109547","article-title":"Graph-based cognitive diagnosis for intelligent tutoring systems","volume":"253","author":"Su","year":"2022","journal-title":"Knowledge-Based Systems"},{"key":"10.7717\/peerj-cs.3661\/ref-37","doi-asserted-by":"publisher","first-page":"112307\u2013112319","DOI":"10.1109\/access.2023.3323365","article-title":"A university student performance prediction model and experiment based on multi-feature fusion and attention mechanism","volume":"11","author":"Sun","year":"2023","journal-title":"IEEE Access"},{"issue":"3","key":"10.7717\/peerj-cs.3661\/ref-38","doi-asserted-by":"publisher","first-page":"224","DOI":"10.14569\/ijacsa.2024.0150323","article-title":"Beyond BERT: exploring the efficacy of RoBERTa and ALBERT in supervised multiclass text classification","volume":"15","author":"Sy","year":"2024","journal-title":"International Journal of Advanced Computer Science & Applications"},{"key":"10.7717\/peerj-cs.3661\/ref-39","doi-asserted-by":"publisher","first-page":"106189","DOI":"10.1016\/j.chb.2019.106189","article-title":"Predicting academic performance of students from VLE big data using deep learning models","volume":"104","author":"Waheed","year":"2020","journal-title":"Computers in Human Behavior"},{"issue":"1","key":"10.7717\/peerj-cs.3661\/ref-40","doi-asserted-by":"publisher","first-page":"11","DOI":"10.1186\/s40561-022-00192-z","article-title":"Educational data mining: prediction of students\u2019 academic performance using machine learning algorithms","volume":"9","author":"Ya\u011fc\u0131","year":"2022","journal-title":"Smart Learning Environments"},{"issue":"5","key":"10.7717\/peerj-cs.3661\/ref-41","doi-asserted-by":"publisher","first-page":"716","DOI":"10.1109\/jstsp.2017.2700227","article-title":"Behavior-based grade prediction for MOOCs via time series neural networks","volume":"11","author":"Yang","year":"2017","journal-title":"IEEE Journal of Selected Topics in Signal Processing"},{"issue":"1","key":"10.7717\/peerj-cs.3661\/ref-42","doi-asserted-by":"publisher","first-page":"119","DOI":"10.1186\/s40537-025-01170-1","article-title":"Student academic performance prediction via hypergraph and TabNet","volume":"12","author":"Yang","year":"2025","journal-title":"Journal of Big Data"},{"issue":"1","key":"10.7717\/peerj-cs.3661\/ref-43","doi-asserted-by":"publisher","first-page":"511","DOI":"10.1515\/jisys-2021-0016","article-title":"Student performance prediction with optimum multilabel ensemble model","volume":"30","author":"Yekun","year":"2021","journal-title":"Journal of Intelligent Systems"},{"key":"10.7717\/peerj-cs.3661\/ref-44","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2505.09287","article-title":"Ranking-based at-risk student prediction using federated learning and differential features","author":"Yoneda","year":"2025"},{"key":"10.7717\/peerj-cs.3661\/ref-45","doi-asserted-by":"publisher","first-page":"e2509","DOI":"10.7717\/peerj-cs.2509","article-title":"Evaluating the effectiveness of online courses in international trade using deep learning","volume":"10","author":"Zhang","year":"2024","journal-title":"PeerJ Computer Science"}],"container-title":["PeerJ Computer Science"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/peerj.com\/articles\/cs-3661.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/peerj.com\/articles\/cs-3661.xml","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/peerj.com\/articles\/cs-3661.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/peerj.com\/articles\/cs-3661.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,26]],"date-time":"2026-03-26T08:00:32Z","timestamp":1774512032000},"score":1,"resource":{"primary":{"URL":"https:\/\/peerj.com\/articles\/cs-3661"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,26]]},"references-count":45,"alternative-id":["10.7717\/peerj-cs.3661"],"URL":"https:\/\/doi.org\/10.7717\/peerj-cs.3661","archive":["CLOCKSS","LOCKSS","Portico"],"relation":{},"ISSN":["2376-5992"],"issn-type":[{"value":"2376-5992","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,3,26]]},"article-number":"e3661"}}