{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,16]],"date-time":"2026-04-16T15:34:31Z","timestamp":1776353671720,"version":"3.51.2"},"reference-count":19,"publisher":"Emerald","issue":"2","license":[{"start":{"date-parts":[[2020,8,13]],"date-time":"2020-08-13T00:00:00Z","timestamp":1597276800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.emerald.com\/insight\/site-policies"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["GS"],"published-print":{"date-parts":[[2020,8,13]]},"abstract":"Purpose<\/jats:title>The purpose of this paper is to solve the problems existing in topic popularity prediction in online social networks and advance a fine-grained and long-term prediction model for lack of sufficient data.<\/jats:p><\/jats:sec>Design\/methodology\/approach<\/jats:title>Based on GM(1,1) and neural networks, a co-training model for topic tendency prediction is proposed in this paper. The interpolation based on GM(1,1) is employed to generate fine-grained prediction values of topic popularity time series and two neural network models are considered to achieve convergence by transmitting training parameters via their loss functions.<\/jats:p><\/jats:sec>Findings<\/jats:title>The experiment results indicate that the integrated model can effectively predict dense sequence with higher performance than other algorithms, such as NN and RBF_LSSVM. Furthermore, the Markov chain state transition probability matrix model is used to improve the prediction results.<\/jats:p><\/jats:sec>Practical implications<\/jats:title>Fine-grained and long-term topic popularity prediction, further improvement could be made by predicting any interpolation in the time interval of popularity data points.<\/jats:p><\/jats:sec>Originality\/value<\/jats:title>The paper succeeds in constructing a co-training model with GM(1,1) and neural networks. Markov chain state transition probability matrix is deployed for further improvement of popularity tendency prediction.<\/jats:p><\/jats:sec>","DOI":"10.1108\/gs-02-2020-0024","type":"journal-article","created":{"date-parts":[[2020,8,12]],"date-time":"2020-08-12T23:18:00Z","timestamp":1597274280000},"page":"327-338","source":"Crossref","is-referenced-by-count":3,"title":["Grey theory\u2013based BP-NN co-training for dense sequence long-term tendency prediction"],"prefix":"10.1108","volume":"11","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3038-4546","authenticated-orcid":false,"given":"Yuling","family":"Hong","sequence":"first","affiliation":[]},{"given":"Yingjie","family":"Yang","sequence":"additional","affiliation":[]},{"given":"Qishan","family":"Zhang","sequence":"additional","affiliation":[]}],"member":"140","reference":[{"key":"key2021031005045898800_ref001","first-page":"19","article-title":"Learning from labeled and unlabeled data using graph mincuts","year":"2001"},{"key":"key2021031005045898800_ref002","first-page":"92","article-title":"Combining labeled and unlabeled data with co-training","year":"1998"},{"issue":"3","key":"key2021031005045898800_ref003","first-page":"1541","article-title":"Time series interval forecast using GM(1,1) and NGBM(1,1) models","volume":"23","year":"2019","journal-title":"Soft computing"},{"issue":"1","key":"key2021031005045898800_ref004","first-page":"1","article-title":"Introduction to grey system theory","volume":"1","year":"1989","journal-title":"The Journal of Grey System"},{"issue":"2","key":"key2021031005045898800_ref005","doi-asserted-by":"crossref","first-page":"1691","DOI":"10.3233\/JIFS-18804","article-title":"Prediction of a multi-mode coupling model based on traffic flow tensor data[J]","volume":"36","year":"2019","journal-title":"Journal of Intelligent and Fuzzy Systems"},{"issue":"9","key":"key2021031005045898800_ref006","first-page":"251","article-title":"Neural network model for recognizing joint offset during fiber laser welding","volume":"92","year":"2013","journal-title":"Weld Journal"},{"key":"key2021031005045898800_ref007","article-title":"An integrated model combining grey methods and neural networks and its application to burst topic tendency prediction","year":"2020","journal-title":"Journal of Grey System"},{"key":"key2021031005045898800_ref008","doi-asserted-by":"crossref","first-page":"390","DOI":"10.1016\/j.apm.2018.08.017","article-title":"A new method to mitigate data fluctuations for time series prediction","volume":"65","year":"2019","journal-title":"Applied Mathematical Modelling"},{"issue":"2","key":"key2021031005045898800_ref009","first-page":"97","article-title":"Commodity market state prediction based on Markov chain state transition probability matrix","volume":"422","year":"2015","journal-title":"Statistics and Decision"},{"key":"key2021031005045898800_ref010","first-page":"92","volume-title":"Grey Systems: Theory and Applications. Understanding Complex Systems","year":"2010"},{"issue":"4","key":"key2021031005045898800_ref011","doi-asserted-by":"crossref","first-page":"765","DOI":"10.1016\/j.dss.2008.01.003","article-title":"Predicting going concern opinion with data mining","volume":"45","year":"2008","journal-title":"Decision Support Systems"},{"issue":"5","key":"key2021031005045898800_ref012","first-page":"6","article-title":"Study on prediction and early warning model of public opinion basing on K-harmonic means and Particle Swarm Optimization","volume":"235","year":"2017","journal-title":"Information Research"},{"issue":"8","key":"key2021031005045898800_ref013","doi-asserted-by":"crossref","first-page":"80","DOI":"10.1145\/1787234.1787254","article-title":"Predicting the popularity of online content","volume":"53","year":"2010","journal-title":"Communications of the ACM"},{"issue":"3","key":"key2021031005045898800_ref014","first-page":"191","article-title":"Grey system theory based prediction for topic trend on internet","volume":"29","year":"2014","journal-title":"Engineering Applications of Artificial Intelligence"},{"issue":"5","key":"key2021031005045898800_ref015","doi-asserted-by":"crossref","first-page":"1301","DOI":"10.1109\/TKDE.2014.2345379","article-title":"On summarization and timeline generation for evolutionary tweet streams","volume":"27","year":"2015","journal-title":"Knowledge and Data Engineering"},{"key":"key2021031005045898800_ref016","first-page":"6283","article-title":"Research on subway passenger flow combination prediction model based on RBF neural networks and LSSVM","year":"2016"},{"key":"key2021031005045898800_ref017","first-page":"471","article-title":"Research and application of improved gas concentration prediction model based on grey theory and BP neural network in digital mine","year":"2016"},{"key":"key2021031005045898800_ref018","first-page":"123","article-title":"\u2018DGM-AMSAA\u2019 Model of reliability growth based on the small sample [C]","year":"2013"},{"key":"key2021031005045898800_ref019","first-page":"591","article-title":"What is Twitter, a social network or a news media?","year":"2010"}],"container-title":["Grey Systems: Theory and Application"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.emerald.com\/insight\/content\/doi\/10.1108\/GS-02-2020-0024\/full\/xml","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.emerald.com\/insight\/content\/doi\/10.1108\/GS-02-2020-0024\/full\/html","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,7,25]],"date-time":"2025-07-25T00:45:33Z","timestamp":1753404333000},"score":1,"resource":{"primary":{"URL":"http:\/\/www.emerald.com\/gs\/article\/11\/2\/327-338\/206262"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,8,13]]},"references-count":19,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2020,8,13]]}},"alternative-id":["10.1108\/GS-02-2020-0024"],"URL":"https:\/\/doi.org\/10.1108\/gs-02-2020-0024","relation":{},"ISSN":["2043-9377"],"issn-type":[{"value":"2043-9377","type":"print"}],"subject":[],"published":{"date-parts":[[2020,8,13]]}}}