{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,28]],"date-time":"2026-03-28T13:28:15Z","timestamp":1774704495981,"version":"3.50.1"},"reference-count":47,"publisher":"Emerald","issue":"2","license":[{"start":{"date-parts":[[2021,6,24]],"date-time":"2021-06-24T00:00:00Z","timestamp":1624492800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.emerald.com\/insight\/site-policies"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["INTR"],"published-print":{"date-parts":[[2022,3,15]]},"abstract":"<jats:sec><jats:title content-type=\"abstract-subheading\">Purpose<\/jats:title><jats:p>Course recommendations are important for improving learner satisfaction and reducing dropout rates on massive open online course (MOOC) platforms. This study aims to propose an interpretable method of analyzing students' learning behaviors and recommending MOOCs by integrating multiple data sources.<\/jats:p><\/jats:sec><jats:sec><jats:title content-type=\"abstract-subheading\">Design\/methodology\/approach<\/jats:title><jats:p>The study proposes a deep learning method of recommending MOOCs to students based on a multi-attention mechanism comprising learning records attention, word-level review attention, sentence-level review attention and course description attention. The proposed model is validated using real-world data consisting of the learning records of 6,628 students for 1,789 courses and 65,155 reviews.<\/jats:p><\/jats:sec><jats:sec><jats:title content-type=\"abstract-subheading\">Findings<\/jats:title><jats:p>The main contribution of this study is its exploration of multiple unstructured information using the proposed multi-attention network model. It provides an interpretable strategy for analyzing students' learning behaviors and conducting personalized MOOC recommendations.<\/jats:p><\/jats:sec><jats:sec><jats:title content-type=\"abstract-subheading\">Practical implications<\/jats:title><jats:p>The findings suggest that MOOC platforms must fully utilize the information implied in course reviews to extract personalized learning preferences.<\/jats:p><\/jats:sec><jats:sec><jats:title content-type=\"abstract-subheading\">Originality\/value<\/jats:title><jats:p>This study is the first attempt to recommend MOOCs by exploring students' preferences in course reviews. The proposed multi-attention mechanism improves the interpretability of MOOC recommendations.<\/jats:p><\/jats:sec>","DOI":"10.1108\/intr-08-2020-0477","type":"journal-article","created":{"date-parts":[[2021,6,24]],"date-time":"2021-06-24T01:15:55Z","timestamp":1624497355000},"page":"588-605","source":"Crossref","is-referenced-by-count":41,"title":["Interpretable MOOC recommendation: a multi-attention network for personalized learning behavior analysis"],"prefix":"10.1108","volume":"32","author":[{"given":"Ju","family":"Fan","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0886-3647","authenticated-orcid":false,"given":"Yuanchun","family":"Jiang","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9193-5236","authenticated-orcid":false,"given":"Yezheng","family":"Liu","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6361-1456","authenticated-orcid":false,"given":"Yonghang","family":"Zhou","sequence":"additional","affiliation":[]}],"member":"140","published-online":{"date-parts":[[2021,6,24]]},"reference":[{"issue":"3","key":"key2022031415450606200_ref001","doi-asserted-by":"crossref","first-page":"170","DOI":"10.1016\/j.iheduc.2012.01.006","article-title":"Exploring the complex relations between achievement emotions and self-regulated learning behaviors in online learning","volume":"15","year":"2012","journal-title":"The Internet and Higher Education"},{"key":"key2022031415450606200_ref002","first-page":"201","article-title":"A framework for topic generation and labeling from MOOC discussions","year":"2016"},{"key":"key2022031415450606200_ref003","first-page":"1","article-title":"Using association rules for course recommendation","year":"2006"},{"key":"key2022031415450606200_ref004","first-page":"43","article-title":"Empirical analysis of predictive algorithms for collaborative filtering","year":"2013","journal-title":"Proceedings of the Fourteenth Conference on Uncertainty in Artificial Intelligence"},{"key":"key2022031415450606200_ref005","doi-asserted-by":"crossref","first-page":"209","DOI":"10.1016\/j.chb.2018.08.016","article-title":"How attention level and cognitive style affect learning in a MOOC environment? Based on the perspective of brainwave analysis","volume":"100","year":"2019","journal-title":"Computers in Human Behavior"},{"key":"key2022031415450606200_ref006","article-title":"Scene dynamics: counterfactual critic multi-agent training for scene graph generation","year":"2018"},{"key":"key2022031415450606200_ref007","first-page":"4613","article-title":"Counterfactual critic multi-agent training for scene graph generation","year":"2019"},{"key":"key2022031415450606200_ref008","first-page":"39","article-title":"Performance of recommender algorithms on top-n recommendation tasks","year":"2010"},{"issue":"1","key":"key2022031415450606200_ref009","doi-asserted-by":"crossref","first-page":"101","DOI":"10.1111\/bjet.12595","article-title":"Big Data and data science: a critical review of issues for educational research","volume":"50","year":"2019","journal-title":"British Journal of Educational Technology"},{"key":"key2022031415450606200_ref010","first-page":"293","article-title":"The YouTube video recommendation system","year":"2010"},{"key":"key2022031415450606200_ref011","doi-asserted-by":"crossref","first-page":"312","DOI":"10.1016\/j.compedu.2014.06.018","article-title":"Effects of interactivity and instructional scaffolding on learning: self-regulation in online video-based environments","volume":"78","year":"2014","journal-title":"Computers and Education"},{"issue":"1","key":"key2022031415450606200_ref012","doi-asserted-by":"crossref","first-page":"143","DOI":"10.1145\/963770.963776","article-title":"Item-based top-n recommendation algorithms","volume":"22","year":"2004","journal-title":"ACM Transactions on Information Systems"},{"issue":"1","key":"key2022031415450606200_ref013","doi-asserted-by":"crossref","first-page":"68","DOI":"10.1145\/3359786","article-title":"Techniques for interpretable machine learning","volume":"63","year":"2019","journal-title":"Communications of the ACM"},{"issue":"July","key":"key2022031415450606200_ref014","first-page":"2121","article-title":"Adaptive subgradient methods for online learning and stochastic optimization","volume":"12","year":"2011","journal-title":"Journal of Machine Learning Research"},{"key":"key2022031415450606200_ref015","first-page":"183","article-title":"Domain-aware grade prediction and top-n course recommendation","year":"2016"},{"issue":"5","key":"key2022031415450606200_ref016","doi-asserted-by":"crossref","first-page":"1785","DOI":"10.1111\/bjet.12999","article-title":"Understanding the focal points and sentiment of learners in MOOC reviews: a machine learning and SC-LIWC-based approach","volume":"51","year":"2020","journal-title":"British Journal of Educational Technology"},{"key":"key2022031415450606200_ref017","first-page":"21","article-title":"Demographic differences in how students navigate through MOOCs","year":"2014"},{"key":"key2022031415450606200_ref018","first-page":"144","article-title":"VBPR: visual Bayesian personalized ranking from implicit feedback","year":"2016"},{"key":"key2022031415450606200_ref019","first-page":"1661","article-title":"Trirank: review-aware explainable recommendation by modeling aspects","year":"2015"},{"issue":"1","key":"key2022031415450606200_ref020","first-page":"57","article-title":"BiRank: towards ranking on bipartite graphs","volume":"29","year":"2016","journal-title":"IEEE Transactions on Knowledge and Data Engineering"},{"key":"key2022031415450606200_ref021","first-page":"549","article-title":"Fast matrix factorization for online recommendation with implicit feedback","year":"2016"},{"key":"key2022031415450606200_ref022","first-page":"173","article-title":"Neural collaborative filtering","year":"2017"},{"issue":"12","key":"key2022031415450606200_ref023","doi-asserted-by":"crossref","first-page":"2354","DOI":"10.1109\/TKDE.2018.2831682","article-title":"NAIS: neural attentive item similarity model for recommendation","volume":"30","year":"2018","journal-title":"IEEE Transactions on Knowledge and Data Engineering"},{"key":"key2022031415450606200_ref024","first-page":"700","article-title":"Discovering learning behavior patterns to predict dropout in MOOC","year":"2017"},{"key":"key2022031415450606200_ref025","first-page":"659","article-title":"FISM: factored item similarity models for top-n recommender systems","year":"2013"},{"issue":"3","key":"key2022031415450606200_ref026","doi-asserted-by":"crossref","first-page":"2584","DOI":"10.1016\/j.eswa.2011.08.113","article-title":"Mining sentiments in SMS texts for teaching evaluation","volume":"39","year":"2012","journal-title":"Expert Systems with Applications"},{"key":"key2022031415450606200_ref027","doi-asserted-by":"crossref","first-page":"16","DOI":"10.1016\/j.compedu.2019.01.003","article-title":"MOOC learners' demographics, self-regulated learning strategy, perceived learning and satisfaction: a structural equation modeling approach","volume":"132","year":"2019","journal-title":"Computers and Education"},{"key":"key2022031415450606200_ref028","first-page":"503","article-title":"A case study of the characteristics of MOOCs completers: taking an online professional training MOOC for example","year":"2016"},{"issue":"2","key":"key2022031415450606200_ref029","doi-asserted-by":"crossref","first-page":"1273","DOI":"10.1109\/TII.2014.2308433","article-title":"An efficient non-negative matrix-factorization-based approach to collaborative filtering for recommender systems","volume":"10","year":"2014","journal-title":"IEEE Transactions on Industrial Informatics"},{"issue":"8","key":"key2022031415450606200_ref030","doi-asserted-by":"crossref","first-page":"426","DOI":"10.1038\/s42256-020-0218-x","article-title":"When causal inference meets deep learning","volume":"2","year":"2020","journal-title":"Nature Machine Intelligence"},{"issue":"1","key":"key2022031415450606200_ref031","doi-asserted-by":"crossref","first-page":"120","DOI":"10.1002\/cae.21785","article-title":"Collaborative filtering recommendation for MOOC application","volume":"25","year":"2017","journal-title":"Computer Applications in Engineering Education"},{"issue":"4","key":"key2022031415450606200_ref032","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/2037661.2037665","article-title":"Recommendation systems with complex constraints: a course recommendation perspective","volume":"29","year":"2011","journal-title":"ACM Transactions on Information Systems"},{"issue":"114","key":"key2022031415450606200_ref033","first-page":"1","article-title":"Modeling MOOC dropouts","volume":"10","year":"2015","journal-title":"Entropy"},{"key":"key2022031415450606200_ref034","doi-asserted-by":"crossref","first-page":"103673","DOI":"10.1016\/j.compedu.2019.103673","article-title":"Investigating learners' behaviors and discourse content in MOOC course reviews","volume":"143","year":"2020","journal-title":"Computers and Education"},{"key":"key2022031415450606200_ref035","first-page":"93","article-title":"Modeling and predicting learning behavior in MOOCs","year":"2016"},{"key":"key2022031415450606200_ref036","doi-asserted-by":"crossref","first-page":"458","DOI":"10.1016\/j.compedu.2013.06.009","article-title":"Predicting students' final performance from participation in on-line discussion forums","volume":"68","year":"2013","journal-title":"Computers and Education"},{"key":"key2022031415450606200_ref037","first-page":"1519","article-title":"Algorithms for interpretable machine learning","year":"2014"},{"key":"key2022031415450606200_ref038","first-page":"8676","article-title":"Causal strategic linear regression","year":"2020"},{"key":"key2022031415450606200_ref039","first-page":"979","article-title":"Modeling student learning styles in MOOCs","year":"2017"},{"key":"key2022031415450606200_ref040","article-title":"Understanding the determinants of learner engagement in MOOCs: an adaptive structuration perspective","volume":"157","year":"2020","journal-title":"Computers and Education"},{"key":"key2022031415450606200_ref041","article-title":"Modelling MOOC learners' social behaviours","volume":"107","year":"2020","journal-title":"Computers in Human Behavior"},{"issue":"3","key":"key2022031415450606200_ref042","doi-asserted-by":"crossref","first-page":"570","DOI":"10.1111\/bjet.12297","article-title":"Digging deeper into learners' experiences in MOOCs: participation in social networks outside of MOOCs, notetaking and contexts surrounding content consumption","volume":"46","year":"2015","journal-title":"British Journal of Educational Technology"},{"key":"key2022031415450606200_ref043","first-page":"202","article-title":"Causal association analysis algorithm for MOOC learning behavior and learning effect","year":"2016"},{"key":"key2022031415450606200_ref044","first-page":"1983","article-title":"Identifying latent study habits by mining learner behavior patterns in massive open online courses","year":"2014"},{"issue":"3","key":"key2022031415450606200_ref045","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3314578","article-title":"Deep item-based collaborative filtering for top-n recommendation","volume":"37","year":"2019","journal-title":"ACM Transactions on Information Systems"},{"issue":"9","key":"key2022031415450606200_ref046","first-page":"2240","article-title":"Multi-source causal feature selection","volume":"42","year":"2019","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"issue":"1","key":"key2022031415450606200_ref047","doi-asserted-by":"crossref","first-page":"34","DOI":"10.1007\/s11036-018-1131-y","article-title":"MOOCRC: a highly accurate resource recommendation model for use in MOOC environments","volume":"24","year":"2019","journal-title":"Mobile Networks and Applications"}],"container-title":["Internet Research"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.emerald.com\/insight\/content\/doi\/10.1108\/INTR-08-2020-0477\/full\/xml","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.emerald.com\/insight\/content\/doi\/10.1108\/INTR-08-2020-0477\/full\/html","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,7,24]],"date-time":"2025-07-24T21:36:38Z","timestamp":1753392998000},"score":1,"resource":{"primary":{"URL":"http:\/\/www.emerald.com\/intr\/article\/32\/2\/588-605\/185563"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,6,24]]},"references-count":47,"journal-issue":{"issue":"2","published-online":{"date-parts":[[2021,6,24]]},"published-print":{"date-parts":[[2022,3,15]]}},"alternative-id":["10.1108\/INTR-08-2020-0477"],"URL":"https:\/\/doi.org\/10.1108\/intr-08-2020-0477","relation":{},"ISSN":["1066-2243"],"issn-type":[{"value":"1066-2243","type":"print"}],"subject":[],"published":{"date-parts":[[2021,6,24]]}}}