{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,28]],"date-time":"2026-03-28T17:02:43Z","timestamp":1774717363753,"version":"3.50.1"},"reference-count":49,"publisher":"Springer Science and Business Media LLC","issue":"9","license":[{"start":{"date-parts":[[2025,11,1]],"date-time":"2025-11-01T00:00:00Z","timestamp":1761955200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2025,11,4]],"date-time":"2025-11-04T00:00:00Z","timestamp":1762214400000},"content-version":"vor","delay-in-days":3,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/501100001809","name":"The National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["61902016"],"award-info":[{"award-number":["61902016"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"name":"Beijing Education Science 14th Five Year Plan Project","award":["CDDB24252"],"award-info":[{"award-number":["CDDB24252"]}]},{"name":"Beijing University of Civil Engineering and Architecture Master\u2019s Innovation Project for the Year 2025","award":["PG2025112"],"award-info":[{"award-number":["PG2025112"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["J. King Saud Univ. Comput. Inf. Sci."],"published-print":{"date-parts":[[2025,11]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>In large-scale e-learning learning platforms, precisely assessing learners\u2019 knowledge states is crucial for achieving personalized exercise recommendation. However, most existing studies only rely on answer accuracy to evaluate knowledge states, ignoring the cognitive abilities implied in answering behaviors. Meanwhile, the impact of learning ability on exercise recommendation has received little attention. Additionally, traditional knowledge graphs rely on preset relationships for topological evolution, making it difficult to capture deep semantics, and their dynamic evolution also poses challenges to graph embedding. Based on the above motivations, we propose an exercise recommendation approach via multi-behavior interaction perception and semantic-enhanced knowledge graph (MBSE). First, a time-sensitive multi-behavior conjugate knowledge tracing model is constructed: a GRU with behavior focus-temporal decay dual attention is used to analyze the evolution of learning behaviors, and a conjugate deep cross-network is employed to build behavior synergy\/opposition coupling interactions to achieve accurate evaluation of knowledge states. Second, a dual-dimensional learner ability assessment framework is proposed to evaluate problem-solving ability and knowledge-acquisition ability. Third, an incremental progressive relational aggregation graph convolutional network is proposed to progressively represent relationships in knowledge graph, achieving deep semantic modeling of knowledge graph. Finally, a multi-task balanced recommendation model is constructed to realize accurate exercise selection and recommendation. Experimental results show that, compared with the second-best model, MBSE achieved maximum improvements of 1.35%, 1.15%, and 2.39% in Precision, Recall, and F1 respectively, with comparable Diversity, on the ASSIST2012-13 and ASSIST2009-10 datasets. These improvements indicate higher recommendation quality, helping reduce redundant practice, accelerate mastery, and improve learning outcomes.<\/jats:p>","DOI":"10.1007\/s44443-025-00322-w","type":"journal-article","created":{"date-parts":[[2025,11,4]],"date-time":"2025-11-04T13:50:16Z","timestamp":1762264216000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["An exercise recommendation approach via multi-behavior interactive perception and semantic-enhanced knowledge graph"],"prefix":"10.1007","volume":"37","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3421-4387","authenticated-orcid":false,"given":"Shanshan","family":"Wan","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-2570-7051","authenticated-orcid":false,"given":"Zebin","family":"Fu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0352-3002","authenticated-orcid":false,"given":"Chuyuan","family":"Wei","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,11,4]]},"reference":[{"key":"322_CR1","unstructured":"Bin Z, Zhenghu Y, Wenxue S, Lei Y, Ligang D, Xian J (2022) Student knowledge tracking based multi-indicator exercise recommendation algorithm. Telecommun Sci 38(9)"},{"key":"322_CR2","unstructured":"Bordes A, Usunier N, Garcia-Duran A, Weston J, Yakhnenko O (2013) Translating embeddings for modeling multi-relational data. Adv Neural Inf Process Syst 26"},{"issue":"3","key":"322_CR3","doi-asserted-by":"publisher","first-page":"256","DOI":"10.1109\/TEVC.2004.826067","volume":"8","author":"CAC Coello","year":"2004","unstructured":"Coello CAC, Pulido GT, Lechuga MS (2004) Handling multiple objectives with particle swarm optimization. IEEE Trans Evol Comput 8(3):256\u2013279","journal-title":"IEEE Trans Evol Comput"},{"issue":"4","key":"322_CR4","doi-asserted-by":"publisher","first-page":"577","DOI":"10.1109\/TEVC.2013.2281535","volume":"18","author":"K Deb","year":"2013","unstructured":"Deb K, Jain H (2013) An evolutionary many-objective optimization algorithm using reference-point-based nondominated sorting approach, part i: solving problems with box constraints. IEEE Trans Evol Comput 18(4):577\u2013601","journal-title":"IEEE Trans Evol Comput"},{"key":"322_CR5","doi-asserted-by":"publisher","first-page":"776","DOI":"10.1109\/TLT.2023.3333669","volume":"17","author":"S Dong","year":"2023","unstructured":"Dong S, Tao X, Zhong R, Wang Z, Zuo M, Sun J (2023) Advanced mathematics exercise recommendation based on automatic knowledge extraction and multilayer knowledge graph. IEEE Trans Learn Technol 17:776\u2013793","journal-title":"IEEE Trans Learn Technol"},{"key":"322_CR6","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2024.111521","volume":"291","author":"Y Dong","year":"2024","unstructured":"Dong Y, Liu Y, Dong Y, Wang Y, Chen M (2024) Multi-knowledge enhanced graph convolution for learning resource recommendation. Knowl-Based Syst 291:111521","journal-title":"Knowl-Based Syst"},{"key":"322_CR7","unstructured":"Ebbinghaus H (1885) \u00dcber Das Ged\u00e4chtnis: untersuchungen zur Experimentellen Psychologie. Duncker & Humblot, ???"},{"issue":"23","key":"322_CR8","doi-asserted-by":"publisher","first-page":"8410","DOI":"10.1073\/pnas.1319030111","volume":"111","author":"S Freeman","year":"2014","unstructured":"Freeman S, Eddy SL, McDonough M, Smith MK, Okoroafor N, Jordt H, Wenderoth MP (2014) Active learning increases student performance in science, engineering, and mathematics. Proc Natl Acad Sci 111(23):8410\u20138415","journal-title":"Proc Natl Acad Sci"},{"key":"322_CR9","doi-asserted-by":"crossref","unstructured":"Grover A, Leskovec J (2016) node2vec: scalable feature learning for networks. In: Proceedings of the 22nd ACM SIGKDD international conference on knowledge discovery and data mining, pp 855\u2013864","DOI":"10.1145\/2939672.2939754"},{"key":"322_CR10","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2024.106954","volume":"183","author":"Q Guan","year":"2025","unstructured":"Guan Q, Cheng X, Xiao F, Li Z, He C, Fang L, Chen G, Gong Z, Luo W (2025) Explainable exercise recommendation with knowledge graph. Neural Netw 183:106954","journal-title":"Neural Netw"},{"key":"322_CR11","doi-asserted-by":"crossref","unstructured":"Guan Q, Xiao F, Cheng X, Fang L, Chen Z, Chen G, Luo W (2023) Kg4ex: an explainable knowledge graph-based approach for exercise recommendation. In: Proceedings of the 32nd ACM international conference on information and knowledge management, pp 597\u2013607","DOI":"10.1145\/3583780.3614943"},{"issue":"8","key":"322_CR12","doi-asserted-by":"publisher","first-page":"3549","DOI":"10.1109\/TKDE.2020.3028705","volume":"34","author":"Q Guo","year":"2020","unstructured":"Guo Q, Zhuang F, Qin C, Zhu H, Xie X, Xiong H, He Q (2020) A survey on knowledge graph-based recommender systems. IEEE Trans Knowl Data Eng 34(8):3549\u20133568","journal-title":"IEEE Trans Knowl Data Eng"},{"issue":"4","key":"322_CR13","doi-asserted-by":"publisher","first-page":"452","DOI":"10.1007\/s42486-022-00109-2","volume":"4","author":"Y He","year":"2022","unstructured":"He Y, Wang H, Pan Y, Zhou Y, Sun G (2022) Exercise recommendation method based on knowledge tracing and concept prerequisite relations. CCF Trans Pervasive Comput Interact 4(4):452\u2013464","journal-title":"CCF Trans Pervasive Comput Interact"},{"key":"322_CR14","doi-asserted-by":"crossref","unstructured":"Huang C-Q, Huang Q-H, Huang X, Wang H, Li M, Lin K-J, Chang Y (2024) Xkt: towards explainable knowledge tracing model with cognitive learning theories for questions of multiple knowledge concepts. IEEE Trans Knowl Data Eng","DOI":"10.1109\/TKDE.2024.3418098"},{"key":"322_CR15","doi-asserted-by":"publisher","first-page":"266","DOI":"10.1016\/j.ins.2020.03.014","volume":"523","author":"Y Huo","year":"2020","unstructured":"Huo Y, Wong DF, Ni LM, Chao LS, Zhang J (2020) Knowledge modeling via contextualized representations for lstm-based personalized exercise recommendation. Inf Sci 523:266\u2013278","journal-title":"Inf Sci"},{"key":"322_CR16","doi-asserted-by":"crossref","unstructured":"Jin W (2023) User interest modeling and collaborative filtering algorithms application in english personalized learning resource recommendation. Soft Comput, 1\u201314","DOI":"10.1007\/s00500-023-08700-0"},{"key":"322_CR17","unstructured":"Kingma DP, Welling M (2013) Auto-encoding variational bayes. arXiv:1312.6114"},{"key":"322_CR18","doi-asserted-by":"crossref","unstructured":"Li J, Deng Y, Qin Y, Mao S, Jiang Y (2024) Dual-channel adaptive scale hypergraph encoders with cross-view contrastive learning for knowledge tracing. IEEE Trans Neural Netw Learn Syst","DOI":"10.1109\/TNNLS.2024.3386810"},{"key":"322_CR19","doi-asserted-by":"crossref","unstructured":"Li S, Liu X, Tang X, Chen X, Pu J (2024) Mlkt4rec: enhancing exercise recommendation through multitask learning with knowledge tracing. IEEE Trans Comput Soc Syst","DOI":"10.1109\/TCSS.2024.3515254"},{"issue":"1","key":"322_CR20","doi-asserted-by":"publisher","first-page":"100","DOI":"10.1109\/TKDE.2019.2924374","volume":"33","author":"Q Liu","year":"2019","unstructured":"Liu Q, Huang Z, Yin Y, Chen E, Xiong H, Su Y, Hu G (2019) Ekt: exercise-aware knowledge tracing for student performance prediction. IEEE Trans Knowl Data Eng 33(1):100\u2013115","journal-title":"IEEE Trans Knowl Data Eng"},{"issue":"3","key":"322_CR21","doi-asserted-by":"publisher","first-page":"104051","DOI":"10.1016\/j.ipm.2024.104051","volume":"62","author":"G Liu","year":"2025","unstructured":"Liu G, Ren M, Guo L, Li J, Ma M (2025) Comprehensive exercise recommendation with practicality, generalizability, and versatility in ai-driven education. Inf Process Manag 62(3):104051","journal-title":"Inf Process Manag"},{"key":"322_CR22","doi-asserted-by":"crossref","unstructured":"Liu Z, Li Y, Wei L, Wang W (2022) Adaptive exercise recommendation based on cognitive level and collaborative filtering. In: International conference on computer science and education. Springer, pp 503\u2013518","DOI":"10.1007\/978-981-99-2446-2_46"},{"issue":"5","key":"322_CR23","doi-asserted-by":"publisher","first-page":"1403","DOI":"10.1002\/cae.22395","volume":"29","author":"P Lv","year":"2021","unstructured":"Lv P, Wang X, Xu J, Wang J (2021) Intelligent personalised exercise recommendation: a weighted knowledge graph-based approach. Comput Appl Eng Educ 29(5):1403\u20131419","journal-title":"Comput Appl Eng Educ"},{"issue":"5","key":"322_CR24","first-page":"8053","volume":"44","author":"H Ma","year":"2023","unstructured":"Ma H, Tang Y, Zhang X, Zhu H, Huang P, Zhang H (2023) Learning resource recommendation via knowledge graphs and learning style clustering. J Intell Fuzzy Syst 44(5):8053\u20138069","journal-title":"J Intell Fuzzy Syst"},{"key":"322_CR25","doi-asserted-by":"crossref","unstructured":"Ma H, Huang Z, Tang W, Zhang X (2022) Exercise recommendation based on cognitive diagnosis and neutrosophic set. In: 2022 IEEE 25th International Conference on Computer Supported Cooperative Work in Design (CSCWD). IEEE, pp 1467\u20131472","DOI":"10.1109\/CSCWD54268.2022.9776197"},{"key":"322_CR26","doi-asserted-by":"crossref","unstructured":"Mirjalili S, Saremi S, Mirjalili SM, Coelho LdS (2016) Multi-objective grey wolf optimizer: a novel algorithm for multi-criterion optimization. Expert Syst Appl 47:106\u2013119","DOI":"10.1016\/j.eswa.2015.10.039"},{"issue":"1","key":"322_CR27","first-page":"13","volume":"10","author":"P Pei","year":"2024","unstructured":"Pei P, Raga Jr RC, Abisado M (2024) Enhanced personalized learning exercise question recommendation model based on knowledge tracing. Int J Adv Intell Inf 10(1):13\u201326","journal-title":"Int J Adv Intell Inf"},{"key":"322_CR28","doi-asserted-by":"crossref","unstructured":"Qian F, Hu Y, Li G, Chen J, Wang S, Zhao S (2024) Enhanced knowledge tracing with learnable filter. IEEE Trans Comput Soc Syst","DOI":"10.1109\/TCSS.2024.3452130"},{"key":"322_CR29","doi-asserted-by":"crossref","unstructured":"Qin C, Hu W, Du F, Wang S (2024) Graph attention-enhanced knowledge tracing: Unveiling exercise variability and long-term dependencies. In: 2024 12th International Conference on Information and Education Technology (ICIET). IEEE, pp 482\u2013488","DOI":"10.1109\/ICIET60671.2024.10542821"},{"key":"322_CR30","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2022.110117","volume":"260","author":"Y Ren","year":"2023","unstructured":"Ren Y, Liang K, Shang Y, Zhang Y (2023) Muloer-san: 2-layer multi-objective framework for exercise recommendation with self-attention networks. Knowl-Based Syst 260:110117","journal-title":"Knowl-Based Syst"},{"key":"322_CR31","doi-asserted-by":"crossref","unstructured":"Shen G, He X (2024) Research on the application of exercise recommendation based on knowledge graph and kmakt prediction model. In: 2024 14th International Conference on Information Technology in Medicine and Education (ITME). IEEE, pp 953\u2013957","DOI":"10.1109\/ITME63426.2024.00192"},{"key":"322_CR32","doi-asserted-by":"crossref","unstructured":"Shen S, Liu Q, Huang Z, Zheng Y, Yin M, Wang M, Chen E (2024) A survey of knowledge tracing: models, variants, and applications. IEEE Trans Learn Technol","DOI":"10.1109\/TLT.2024.3383325"},{"issue":"3\u20134","key":"322_CR33","first-page":"309","volume":"24","author":"Y Song","year":"2024","unstructured":"Song Y (2024) Personalised recommendation of educational resources based on collaborative filtering. Int J Bus Intell Data Min 24(3\u20134):309\u2013323","journal-title":"Int J Bus Intell Data Min"},{"issue":"3","key":"322_CR34","doi-asserted-by":"publisher","first-page":"431","DOI":"10.1109\/TLT.2023.3242712","volume":"16","author":"H Wan","year":"2023","unstructured":"Wan H, Zhong Z, Tang L, Gao X (2023) Pedagogical interventions in spocs: learning behavior dashboards and knowledge tracing support exercise recommendation. IEEE Trans Learn Technol 16(3):431\u2013442","journal-title":"IEEE Trans Learn Technol"},{"key":"322_CR35","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2024.112834","volume":"309","author":"J Wang","year":"2025","unstructured":"Wang J, Ma H, Zhang M, Zhang L, Chang L (2025) Multi-granularity ensemble interaction graph modeling for knowledge tracing. Knowl-Based Syst 309:112834","journal-title":"Knowl-Based Syst"},{"key":"322_CR36","doi-asserted-by":"crossref","unstructured":"Wang R, Fu B, Fu G, Wang M (2017) Deep & cross network for ad click predictions. In: Proceedings of the ADKDD\u201917, pp 1\u20137","DOI":"10.1145\/3124749.3124754"},{"key":"322_CR37","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2020.106481","volume":"210","author":"Z Wu","year":"2020","unstructured":"Wu Z, Li M, Tang Y, Liang Q (2020) Exercise recommendation based on knowledge concept prediction. Knowl-Based Syst 210:106481","journal-title":"Knowl-Based Syst"},{"key":"322_CR38","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2022.117681","volume":"206","author":"Z Wu","year":"2022","unstructured":"Wu Z, Huang L, Huang Q, Huang C, Tang Y (2022) Sgkt: session graph-based knowledge tracing for student performance prediction. Expert Syst Appl 206:117681","journal-title":"Expert Syst Appl"},{"key":"322_CR39","doi-asserted-by":"publisher","first-page":"691","DOI":"10.1109\/TLT.2023.3326449","volume":"17","author":"S Wu","year":"2023","unstructured":"Wu S, Wang J, Zhang W (2023) Contrastive personalized exercise recommendation with reinforcement learning. IEEE Trans Learn Technol 17:691\u2013703","journal-title":"IEEE Trans Learn Technol"},{"issue":"1","key":"322_CR40","doi-asserted-by":"publisher","first-page":"9590502","DOI":"10.1155\/2021\/9590502","volume":"2021","author":"G Xu","year":"2021","unstructured":"Xu G, Jia G, Shi L, Zhang Z (2021) Personalized course recommendation system fusing with knowledge graph and collaborative filtering. Comput Intell Neurosci 2021(1):9590502","journal-title":"Comput Intell Neurosci"},{"issue":"2","key":"322_CR41","doi-asserted-by":"publisher","first-page":"857","DOI":"10.2298\/CSIS220706024Y","volume":"20","author":"Z Yan","year":"2023","unstructured":"Yan Z, Du H, Lin Z, Jianhua Z (2023) Personalization exercise recommendation framework based on knowledge concept graph. Comput Sci Inf Syst 20(2):857\u2013878","journal-title":"Comput Sci Inf Syst"},{"issue":"1","key":"322_CR42","first-page":"93","volume":"12","author":"IHY Yim","year":"2025","unstructured":"Yim IHY, Su J (2025) Artificial intelligence (ai) learning tools in k-12 education: a scoping review. J Comput Ed 12(1):93\u2013131","journal-title":"J Comput Ed"},{"issue":"1","key":"322_CR43","first-page":"9531111","volume":"2021","author":"Z Zhang","year":"2021","unstructured":"Zhang Z (2021) A method of recommending physical education network course resources based on collaborative filtering technology. Sci Program 2021(1):9531111","journal-title":"Sci Program"},{"key":"322_CR44","doi-asserted-by":"crossref","unstructured":"Zhang Z, Liu L, Liu H, Wu Z (2023) Student profile clustering based personalized exercise recommendation: taking data structures course as an example. In: 2023 IEEE International Conference on Advanced Learning Technologies (ICALT). IEEE, pp 68\u201370","DOI":"10.1109\/ICALT58122.2023.00026"},{"key":"322_CR45","doi-asserted-by":"crossref","unstructured":"Zhao H, Fu T (2025) Incorporate global information from entire datasets for knowledge tracing via mini-batch input. In: ICASSP 2025-2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE, pp 1\u20135","DOI":"10.1109\/ICASSP49660.2025.10887970"},{"issue":"1","key":"322_CR46","first-page":"5042286","volume":"2021","author":"L Zhou","year":"2021","unstructured":"Zhou L, Wang C (2021) Research on recommendation of personalized exercises in english learning based on data mining. Sci Program 2021(1):5042286","journal-title":"Sci Program"},{"key":"322_CR47","doi-asserted-by":"crossref","unstructured":"Zhou H, Rong W, Zhang J, Sun Q, Ouyang Y, Xiong Z (2024) Aakt: enhancing knowledge tracing with alternate autoregressive modeling. IEEE Trans Learn Technol","DOI":"10.36227\/techrxiv.24487747.v2"},{"key":"322_CR48","doi-asserted-by":"crossref","unstructured":"Zhu L, Liu Y, Hei X, Wang Y, Meng H, Jiao J, Pan L (2020) A study on exercise recommendation method using knowledge graph for computer network course. In: 2020 International Conference on Networking and Network Applications (NaNA). IEEE, pp 436\u2013442","DOI":"10.1109\/NaNA51271.2020.00080"},{"key":"322_CR49","unstructured":"Zitzler E, Laumanns M, Thiele L (2001) Spea2: improving the strength pareto evolutionary algorithm. TIK Report 103"}],"container-title":["Journal of King Saud University Computer and Information Sciences"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s44443-025-00322-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s44443-025-00322-w\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s44443-025-00322-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,19]],"date-time":"2025-11-19T15:46:15Z","timestamp":1763567175000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s44443-025-00322-w"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11]]},"references-count":49,"journal-issue":{"issue":"9","published-print":{"date-parts":[[2025,11]]}},"alternative-id":["322"],"URL":"https:\/\/doi.org\/10.1007\/s44443-025-00322-w","relation":{},"ISSN":["1319-1578","2213-1248"],"issn-type":[{"value":"1319-1578","type":"print"},{"value":"2213-1248","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,11]]},"assertion":[{"value":"25 May 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"2 October 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"4 November 2025","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare that there are no conflict of interests.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"297"}}