{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,3]],"date-time":"2025-12-03T17:47:47Z","timestamp":1764784067468,"version":"3.41.2"},"reference-count":56,"publisher":"Emerald","issue":"4","license":[{"start":{"date-parts":[[2018,5,14]],"date-time":"2018-05-14T00:00:00Z","timestamp":1526256000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.emerald.com\/insight\/site-policies"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IMDS"],"published-print":{"date-parts":[[2018,5,14]]},"abstract":"\nPurpose<\/jats:title>\nInternet technology allows millions of people to find high quality medical resources online, with the result that personal healthcare and medical services have become one of the fastest growing markets in China. Data relating to healthcare search behavior may provide insights that could lead to better provision of healthcare services. However, discrepancies often arise between terminologies derived from professional medical domain knowledge and the more colloquial terms that users adopt when searching for information about ailments. This can make it difficult to match healthcare queries with doctors\u2019 keywords in online medical searches. The paper aims to discuss these issues.<\/jats:p>\n<\/jats:sec>\n\nDesign\/methodology\/approach<\/jats:title>\nTo help address this problem, the authors propose a transfer learning using latent factor graph (TLLFG), which can learn the descriptions of ailments used in internet searches and match them to the most appropriate formal medical keywords.<\/jats:p>\n<\/jats:sec>\n\nFindings<\/jats:title>\nExperiments show that the TLLFG outperforms competing algorithms in incorporating both medical domain knowledge and patient-doctor Q&A data from online services into a unified latent layer capable of bridging the gap between lay enquiries and professionally expressed information sources, and make more accurate analysis of online users\u2019 symptom descriptions. The authors conclude with a brief discussion of some of the ways in which the model may support online applications and connect offline medical services.<\/jats:p>\n<\/jats:sec>\n\nPractical implications<\/jats:title>\nThe authors used an online medical searching application to verify the proposed model. The model can bridge users\u2019 long-tailed description with doctors\u2019 formal medical keywords. Online experiments show that TLLFG can significantly improve the searching experience of both users and medical service providers compared with traditional machine learning methods. The research provides a helpful example of the use of domain knowledge to optimize searching or recommendation experiences.<\/jats:p>\n<\/jats:sec>\n\nOriginality\/value<\/jats:title>\nThe authors use transfer learning to map online users\u2019 long-tail queries onto medical domain knowledge, significantly improving the relevance of queries and keywords in a search system reliant on sponsored links.<\/jats:p>\n<\/jats:sec>","DOI":"10.1108\/imds-07-2017-0309","type":"journal-article","created":{"date-parts":[[2018,4,13]],"date-time":"2018-04-13T07:38:05Z","timestamp":1523605085000},"page":"889-911","source":"Crossref","is-referenced-by-count":12,"title":["Modelling online user behavior for medical knowledge learning"],"prefix":"10.1108","volume":"118","author":[{"given":"Daifeng","family":"Li","sequence":"first","affiliation":[],"role":[{"role":"author","vocab":"crossref"}]},{"given":"Andrew","family":"Madden","sequence":"additional","affiliation":[],"role":[{"role":"author","vocab":"crossref"}]},{"given":"Chaochun","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocab":"crossref"}]},{"given":"Ying","family":"Ding","sequence":"additional","affiliation":[],"role":[{"role":"author","vocab":"crossref"}]},{"given":"Liwei","family":"Qian","sequence":"additional","affiliation":[],"role":[{"role":"author","vocab":"crossref"}]},{"given":"Enguo","family":"Zhou","sequence":"additional","affiliation":[],"role":[{"role":"author","vocab":"crossref"}]}],"member":"140","reference":[{"key":"key2020092901284497000_ref001","unstructured":"Anderson, C. (2004), \u201cThe long tail\u201d, Wired, October, p. 1, available at: www.wired.com\/2004\/10\/tail\/ ((accessed September 2016)."},{"first-page":"41","article-title":"Multi-task feature learning","year":"2006","key":"key2020092901284497000_ref002"},{"key":"key2020092901284497000_ref003","unstructured":"Asmussen, S.R. (2003), \u201cSteady-state properties of GI\/G\/1\u201d, Applied Probability and Queues, Stochastic Modelling and Applied Probability, Springer, New York, NY, pp. 266-301."},{"first-page":"237","article-title":"Direct answers for search queries in the long tail","year":"2012","key":"key2020092901284497000_ref004"},{"first-page":"301","article-title":"Learning structured embeddings of knowledge bases","year":"2011","key":"key2020092901284497000_ref005"},{"key":"key2020092901284497000_ref006","first-page":"59","article-title":"Applications of machine learning in cancer prediction and prognosis","volume":"2","year":"2007","journal-title":"Cancer Informatics"},{"key":"key2020092901284497000_ref007","unstructured":"DeepMind (2017), \u201cSupporting medical research\u201d, available at: https:\/\/deepmind.com\/applied\/deepmind-health\/research\/ ((accessed July 5, 2017)."},{"year":"2012","key":"key2020092901284497000_ref008","article-title":"Link prediction and recommendation across heterogeneous social networks"},{"year":"2013","key":"key2020092901284497000_ref009","article-title":"Using deep learning to enhance cancer diagnosis and classification"},{"year":"2013","key":"key2020092901284497000_ref010","article-title":"Health online"},{"first-page":"283","article-title":"Knowledge transfer via multiple model local structure mapping","year":"2008","key":"key2020092901284497000_ref011"},{"issue":"7641","key":"key2020092901284497000_ref012","doi-asserted-by":"crossref","first-page":"348","DOI":"10.1038\/nature21369","article-title":"Early brain development in infants at high risk for autism spectrum disorder","volume":"542","year":"2017","journal-title":"Nature"},{"key":"key2020092901284497000_ref013","unstructured":"Hill Web Marketing (2017), \u201cMedical search technology relies on Google Alphabet\u201d, Hill Web Creation, available at: www.hillwebcreations.com\/medical-search-technology-relies-on-google-alphabet-big-data\/ ((accessed July 5, 2017)."},{"key":"key2020092901284497000_ref014","unstructured":"Huo, S. (2015), \u201cImproving search engine performance based on intention comprehending of tail query\u201d, thesis, Tsinghua University, Beijing, available at: https:\/\/max.book118.com\/html\/2017\/0920\/134507220.shtm 6:2 (accessed November 2016)."},{"issue":"12","key":"key2020092901284497000_ref015","first-page":"2297","article-title":"Proximal methods for hierarchical sparse coding","volume":"12","year":"2011","journal-title":"Journal of Machine Learning Research"},{"first-page":"985","article-title":"Knowledge graph completion with adaptive sparse transfer matrix","year":"2016","key":"key2020092901284497000_ref016"},{"article-title":"Semantic similarity based on corpus statistics and lexical taxonomy","volume-title":"Proceedings of International Conference Research on Computational Linguistics (ROCLING X)","year":"1997","key":"key2020092901284497000_ref017"},{"year":"2002","key":"key2020092901284497000_ref018","article-title":"Learning to classify text using support vector machines"},{"issue":"1","key":"key2020092901284497000_ref019","doi-asserted-by":"crossref","first-page":"89","DOI":"10.1016\/S0933-3657(01)00077-X","article-title":"Machine learning for medical diagnosis: history, state of the art and perspective","volume":"23","year":"2001","journal-title":"Artificial Intelligence in Medicine"},{"issue":"2","key":"key2020092901284497000_ref020","first-page":"498","article-title":"Factor graphs and the sum-product algorithm","volume":"47","year":"2011","journal-title":"IEEE Transactions on Information Theory"},{"first-page":"801","article-title":"Efficient sparse coding algorithms","year":"2006","key":"key2020092901284497000_ref021"},{"key":"key2020092901284497000_ref022","unstructured":"Li, R. (2016), \u201cThe medical requests of Baidu have exceeded 60 million each day\u201d, November 24, available at: http:\/\/tech.huanqiu.com\/per\/2016-11\/9727590.html (accessed November 29, 2016)."},{"key":"key2020092901284497000_ref023","doi-asserted-by":"crossref","unstructured":"Li, Y., Chen, C.Y. and Wasserman, W.W. (2015), \u201cDeep feature selection: theory and application to identify enhancers and promoters\u201d, in Przytycka, T. (Ed.), Research in Computational Molecular Biology, RECOMB, Lecture Notes in Computer Science, Warsaw, April 12-15, p. 9029.","DOI":"10.1007\/978-3-319-16706-0_20"},{"first-page":"2181","article-title":"Learning entity and relation embeddings for knowledge graph completion","year":"2015","key":"key2020092901284497000_ref024"},{"issue":"3","key":"key2020092901284497000_ref025","article-title":"Deep learning based syndrome diagnosis of chronic gastritis","volume":"2014","year":"2014","journal-title":"Computational and Mathematical Methods in Medicine"},{"article-title":"An introduction to factor graphs","volume-title":"IEEE Signal Processing Magazine","year":"2004","key":"key2020092901284497000_ref026"},{"key":"key2020092901284497000_ref300","first-page":"267","article-title":"Active learning for ranking through expected loss optimization","volume":"27","year":"2015","journal-title":"Proceeding of the International ACM Sigir Conference on Research & Development in Information Retrieval"},{"first-page":"837","article-title":"Mining structural hole spanners through information diffusion in social networks","year":"2013","key":"key2020092901284497000_ref027"},{"year":"2013","key":"key2020092901284497000_ref028","article-title":"Efficient estimation of word representations in vector space"},{"year":"1999","key":"key2020092901284497000_ref029","article-title":"Loopy belief propagation for approximate inference: an empirical study"},{"issue":"4","key":"key2020092901284497000_ref030","doi-asserted-by":"crossref","first-page":"702","DOI":"10.1016\/j.dsp.2006.09.005","article-title":"An expert system approach based on principal component analysis and adaptive neuro-fuzzy inference system to diagnosis of diabetes disease","volume":"17","year":"2007","journal-title":"Digital Signal Processing"},{"volume-title":"Modern Information Retrieval","year":"2000","key":"key2020092901284497000_ref031"},{"year":"2013","key":"key2020092901284497000_ref053","article-title":"Diffusion of innovations revisited: from social network to innovation"},{"key":"key2020092901284497000_ref032","doi-asserted-by":"crossref","first-page":"537","DOI":"10.1146\/annurev.bioeng.8.061505.095802","article-title":"Machine learning for detection and diagnosis of disease","volume":"8","year":"2006","journal-title":"Annual Review of Biomedical Engineering"},{"key":"key2020092901284497000_ref033","unstructured":"Shiji Wenkang (Beijing) Technology Development Co., Ltd. (2017), \u201cLegend Holdings\u201d, available at: www.legendholdings.com.cn\/en\/Biz\/CoreAsset\/Cons\/Xunyiwenyaowang.aspx (accessed July 5, 2017)."},{"key":"key2020092901284497000_ref034","doi-asserted-by":"crossref","first-page":"569","DOI":"10.1016\/j.neuroimage.2014.06.077","article-title":"Hierarchical feature representation and multimodal fusion with deep learning for AD\/MCI diagnosis","volume":"101","year":"2014","journal-title":"Neuroimage"},{"key":"key2020092901284497000_ref035","first-page":"848","article-title":"Overview of Baidu Cup 2016: challenge on entity search","year":"2016","journal-title":"NLPCC\/ICCPOL"},{"first-page":"47","article-title":"Improving recommendation for long-tail queries via templates","year":"2011","key":"key2020092901284497000_ref036"},{"issue":"7","key":"key2020092901284497000_ref037","first-page":"124","article-title":"Failure diagnosis using deep belief learning based health state classification","volume":"115","year":"2013","journal-title":"Reliability Engineering & System Safety"},{"year":"2010","key":"key2020092901284497000_ref038","article-title":"Social action tracking via noise tolerant time-varying factor graphs"},{"year":"2012","key":"key2020092901284497000_ref039","article-title":"Convex matching pursuit for large-scale sparse coding and subset selection"},{"article-title":"Cross-domain ranking via latent space learning","volume-title":"San Francisco, CA, February 4-9","year":"2017","key":"key2020092901284497000_ref040"},{"first-page":"807","article-title":"Social influence analysis in large-scale networks","year":"2009","key":"key2020092901284497000_ref041"},{"key":"key2020092901284497000_ref042","first-page":"743","article-title":"Inferring social ties across heterogenous networks","year":"2012","journal-title":"WSDM\u201912"},{"first-page":"62","volume-title":"Using R for Introductory Statistics","year":"2004","key":"key2020092901284497000_ref043"},{"first-page":"1288","article-title":"Inner attention based recurrent neural networks for answer selection","year":"2016","key":"key2020092901284497000_ref044"},{"key":"key2020092901284497000_ref045","first-page":"386","article-title":"Integrated feature preprocessing for classification based on neural incremental attribute learning","year":"2016","journal-title":"FUSION"},{"first-page":"459","article-title":"Cross-lingual knowledge linking across Wiki knowledge bases","year":"2012","key":"key2020092901284497000_ref046"},{"year":"2013","key":"key2020092901284497000_ref047","article-title":"Predicting advertiser bidding behaviors in sponsored search by rationality modeling"},{"year":"2012","key":"key2020092901284497000_ref048","article-title":"Mining competitive relationships by learning across heterogeneous networks"},{"year":"2014","key":"key2020092901284497000_ref049","article-title":"Forecasting potential diabetes complications"},{"first-page":"1771","article-title":"Bayesian learning in sparse graphical factor models via variational mean-field annealing","year":"2010","key":"key2020092901284497000_ref050"},{"issue":"3","key":"key2020092901284497000_ref055","first-page":"368","article-title":"Measuring the diffusion of an innovation: a citation analysis","volume":"69","year":"2017","journal-title":"Journal of the Association for Information Science and Technology"},{"year":"2011","key":"key2020092901284497000_ref051","article-title":"Convex sparse coding subspace learning, and semi-supervised extensions"},{"first-page":"193","article-title":"Boosting for transfer learning","year":"2007","key":"key2020092901284497000_ref052"},{"first-page":"381","article-title":"Learning to infer social ties in large networks","year":"2011","key":"key2020092901284497000_ref054"}],"container-title":["Industrial Management & Data Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.emerald.com\/insight\/content\/doi\/10.1108\/IMDS-07-2017-0309\/full\/xml","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.emerald.com\/insight\/content\/doi\/10.1108\/IMDS-07-2017-0309\/full\/html","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,7,24]],"date-time":"2025-07-24T21:52:44Z","timestamp":1753393964000},"score":1,"resource":{"primary":{"URL":"http:\/\/www.emerald.com\/imds\/article\/118\/4\/889-911\/175583"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,5,14]]},"references-count":56,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2018,5,14]]}},"alternative-id":["10.1108\/IMDS-07-2017-0309"],"URL":"https:\/\/doi.org\/10.1108\/imds-07-2017-0309","relation":{},"ISSN":["0263-5577"],"issn-type":[{"type":"print","value":"0263-5577"}],"subject":[],"published":{"date-parts":[[2018,5,14]]}}}