{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,27]],"date-time":"2026-02-27T04:01:32Z","timestamp":1772164892458,"version":"3.50.1"},"reference-count":41,"publisher":"MIT Press","license":[{"start":{"date-parts":[[2024,12,18]],"date-time":"2024-12-18T00:00:00Z","timestamp":1734480000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Postdoctoral Fellowship Program of CPSF","award":["GZB20240565"],"award-info":[{"award-number":["GZB20240565"]}]},{"name":"Youth Science Foundation of the National Natural Science Foundation of China","award":["72004168"],"award-info":[{"award-number":["72004168"]}]}],"content-domain":{"domain":["direct.mit.edu"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,3,2]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>Topic analysis aims to study topic evolution and trends in order to help researchers understand the process of knowledge evolution and creation. This paper develops a novel topic evolution analysis framework, which we use to demonstrate, forecast, and explain topic evolution from the perspective of the geometrical motion of topic embeddings generated by pretrained language models. Our data set comprises approximately 15 million papers in the computer science field, with 7,000 \u201cfields of study\u201d to represent the topics. First, we demonstrate that over 80% of topics have undergone obvious motion in the semantic vector space, based on the hyperplane and its normal vector generated by a support vector machine. Subsequently, we verified the predictability of the motion based on three vector regression models by predicting topic embeddings. Finally, we employed a decoder to explain the predicted motion, whose forecast embeddings can capture about 50% of unseen topics. Our research framework shows that topic evolution can be analyzed via the geometrical motion of topic embeddings, and the semantic motion of old topics nurtures new topics. The current study opens new research pathways in topic analysis and sheds light on the topic evolution mechanism from a novel geometric perspective.<\/jats:p>","DOI":"10.1162\/qss_a_00344","type":"journal-article","created":{"date-parts":[[2024,12,18]],"date-time":"2024-12-18T13:41:53Z","timestamp":1734529313000},"page":"171-193","update-policy":"https:\/\/doi.org\/10.1162\/mitpressjournals.corrections.policy","source":"Crossref","is-referenced-by-count":0,"title":["A framework for demonstrating, forecasting, and explaining topic evolution by analyzing geometrical motion of topic embeddings"],"prefix":"10.1162","volume":"6","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7035-4627","authenticated-orcid":true,"given":"Shengzhi","family":"Huang","sequence":"first","affiliation":[{"name":"School of Information Management, Wuhan University, Wuhan, China"},{"name":"Information Retrieval and Knowledge Mining Laboratory, Wuhan University, Wuhan, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0929-7416","authenticated-orcid":true,"given":"Wei","family":"Lu","sequence":"additional","affiliation":[{"name":"School of Information Management, Wuhan University, Wuhan, China"},{"name":"Information Retrieval and Knowledge Mining Laboratory, Wuhan University, Wuhan, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3904-8901","authenticated-orcid":true,"given":"Qikai","family":"Cheng","sequence":"additional","affiliation":[{"name":"School of Information Management, Wuhan University, Wuhan, China"},{"name":"Information Retrieval and Knowledge Mining Laboratory, Wuhan University, Wuhan, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5953-6908","authenticated-orcid":true,"given":"Yong","family":"Huang","sequence":"additional","affiliation":[{"name":"School of Information Management, Wuhan University, Wuhan, China"},{"name":"Information Retrieval and Knowledge Mining Laboratory, Wuhan University, Wuhan, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-3779-4460","authenticated-orcid":true,"given":"Fan","family":"Yi","sequence":"additional","affiliation":[{"name":"School of Information Management, Wuhan University, Wuhan, China"},{"name":"Information Retrieval and Knowledge Mining Laboratory, Wuhan University, Wuhan, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2327-9329","authenticated-orcid":true,"given":"Liang","family":"Zhu","sequence":"additional","affiliation":[{"name":"School of Information Management, Wuhan University, Wuhan, China"},{"name":"Information Retrieval and Knowledge Mining Laboratory, Wuhan University, Wuhan, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"281","published-online":{"date-parts":[[2025,3,2]]},"reference":[{"key":"2025030615255447800_bib1","first-page":"993","article-title":"Latent Dirichlet allocation","volume":"3","author":"Blei","year":"2003","journal-title":"Journal of Machine Learning Research"},{"key":"2025030615255447800_bib2","doi-asserted-by":"publisher","first-page":"101253","DOI":"10.1016\/j.joi.2022.101253","article-title":"Empirical analysis of recent temporal dynamics of research fields: Annual publications in chemistry and related areas as an example","volume":"16","author":"Bornmann","year":"2022","journal-title":"Journal of Informetrics"},{"key":"2025030615255447800_bib3","doi-asserted-by":"publisher","first-page":"523","DOI":"10.1002\/asi.24433","article-title":"Topic diversity: A discipline scheme-free diversity measurement for journals","volume":"72","author":"Bu","year":"2021","journal-title":"Journal of the Association for Information Science and Technology"},{"key":"2025030615255447800_bib4","doi-asserted-by":"publisher","first-page":"1923","DOI":"10.1007\/s11192-020-03576-5","article-title":"Keyword-citation-keyword network: A new perspective of discipline knowledge structure analysis","volume":"124","author":"Cheng","year":"2020","journal-title":"Scientometrics"},{"key":"2025030615255447800_bib5","doi-asserted-by":"publisher","first-page":"27","DOI":"10.1016\/j.eswa.2018.07.051","article-title":"Emerging topic detection in Twitter stream based on high utility pattern mining","volume":"115","author":"Choi","year":"2019","journal-title":"Expert Systems with Applications"},{"key":"2025030615255447800_bib6","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1412.3555","article-title":"Empirical evaluation of gated recurrent neural networks on sequence modeling","author":"Chung","year":"2014","journal-title":"arXiv"},{"key":"2025030615255447800_bib7","doi-asserted-by":"publisher","first-page":"15","DOI":"10.1007\/s41109-016-0017-9","article-title":"Quantifying the diaspora of knowledge in the last century","volume":"1","author":"De Domenico","year":"2016","journal-title":"Applied Network Science"},{"key":"2025030615255447800_bib8","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1810.04805","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2018","journal-title":"arXiv"},{"key":"2025030615255447800_bib9","doi-asserted-by":"publisher","first-page":"1245","DOI":"10.1145\/3041021.3053064","article-title":"Analysing trends in computer science research: A preliminary study using the Microsoft Academic Graph","volume-title":"Proceedings of the 26th International Conference on World Wide Web Companion, WWW \u201917 Companion","author":"Effendy","year":"2017"},{"key":"2025030615255447800_bib10","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1810.04882","article-title":"Towards understanding linear word analogies","author":"Ethayarajh","year":"2018","journal-title":"arXiv"},{"key":"2025030615255447800_bib11","doi-asserted-by":"publisher","first-page":"122520","DOI":"10.1016\/j.techfore.2023.122520","article-title":"Technological forecasting based on estimation of word embedding matrix using LSTM networks","volume":"191","author":"Gozuacik","year":"2023","journal-title":"Technological Forecasting and Social Change"},{"key":"2025030615255447800_bib12","doi-asserted-by":"publisher","first-page":"1185","DOI":"10.1016\/j.ipm.2019.02.014","article-title":"Understanding the topic evolution of scientific literatures like an evolving city: Using Google Word2Vec model and spatial autocorrelation analysis","volume":"56","author":"Hu","year":"2019","journal-title":"Information Processing & Management"},{"key":"2025030615255447800_bib13","doi-asserted-by":"publisher","first-page":"1141","DOI":"10.1007\/s11192-017-2604-7","article-title":"Identifying the \u201cGhost City\u201d of domain topics in a keyword semantic space combining citations","volume":"114","author":"Hu","year":"2018","journal-title":"Scientometrics"},{"key":"2025030615255447800_bib14","doi-asserted-by":"publisher","first-page":"101409","DOI":"10.1016\/j.joi.2023.101409","article-title":"Disclosing the interactive mechanism behind scientists\u2019 topic selection behavior from the perspective of the productivity and the impact","volume":"17","author":"Huang","year":"2023","journal-title":"Journal of Informetrics"},{"key":"2025030615255447800_bib15","doi-asserted-by":"publisher","first-page":"103110","DOI":"10.1016\/j.ipm.2022.103110","article-title":"Revisiting the exploration-exploitation behavior of scholars\u2019 research topic selection: Evidence from a large-scale bibliographic database","volume":"59","author":"Huang","year":"2022","journal-title":"Information Processing & Management"},{"key":"2025030615255447800_bib16","doi-asserted-by":"publisher","first-page":"606","DOI":"10.1016\/j.joi.2016.04.002","article-title":"Generation of topic evolution trees from heterogeneous bibliographic networks","volume":"10","author":"Jensen","year":"2016","journal-title":"Journal of Informetrics"},{"key":"2025030615255447800_bib17","doi-asserted-by":"publisher","first-page":"0078","DOI":"10.1038\/s41562-017-0078","article-title":"Quantifying patterns of research-interest evolution","volume":"1","author":"Jia","year":"2017","journal-title":"Nature Human Behaviour"},{"key":"2025030615255447800_bib18","doi-asserted-by":"publisher","first-page":"291","DOI":"10.1016\/j.techfore.2017.10.002","article-title":"Early identification of emerging technologies: A machine learning approach using multiple patent indicators","volume":"127","author":"Lee","year":"2018","journal-title":"Technological Forecasting and Social Change"},{"key":"2025030615255447800_bib19","doi-asserted-by":"publisher","first-page":"102611","DOI":"10.1016\/j.ipm.2021.102611","article-title":"Combining deep neural network and bibliometric indicator for emerging research topic prediction","volume":"58","author":"Liang","year":"2021","journal-title":"Information Processing & Management"},{"key":"2025030615255447800_bib20","doi-asserted-by":"publisher","first-page":"1748","DOI":"10.1016\/j.ijforecast.2021.03.012","article-title":"Temporal fusion transformers for interpretable multi-horizon time series forecasting","volume":"37","author":"Lim","year":"2021","journal-title":"International Journal of Forecasting"},{"key":"2025030615255447800_bib21","doi-asserted-by":"publisher","first-page":"121218","DOI":"10.1016\/j.techfore.2021.121218","article-title":"Topics emerged in the biomedical field and their characteristics","volume":"174","author":"Lu","year":"2022","journal-title":"Technological Forecasting and Social Change"},{"key":"2025030615255447800_bib22","doi-asserted-by":"publisher","first-page":"102594","DOI":"10.1016\/j.ipm.2021.102594","article-title":"Detecting research topic trends by author-defined keyword frequency","volume":"58","author":"Lu","year":"2021","journal-title":"Information Processing & Management"},{"key":"2025030615255447800_bib23","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1301.3781","article-title":"Efficient estimation of word representations in vector space","author":"Mikolov","year":"2013","journal-title":"arXiv"},{"key":"2025030615255447800_bib24","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1802.05365","article-title":"Deep contextualized word representations","author":"Peters","year":"2018","journal-title":"arXiv"},{"key":"2025030615255447800_bib25","doi-asserted-by":"publisher","first-page":"101047","DOI":"10.1016\/j.joi.2020.101047","article-title":"Understanding hierarchical structural evolution in a scientific discipline: A case study of artificial intelligence","volume":"14","author":"Qian","year":"2020","journal-title":"Journal of Informetrics"},{"key":"2025030615255447800_bib26","doi-asserted-by":"publisher","DOI":"10.1145\/3448734.3450470","article-title":"Trend analysis of research direction in computer science based on Microsoft Academic Graph","volume-title":"The 2nd International Conference on Computing and Data Science (CONF-CDS 2021)","author":"Qin","year":"2021"},{"key":"2025030615255447800_bib27","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1908.10084","article-title":"Sentence-BERT: Sentence embeddings using Siamese BERT-networks","author":"Reimers","year":"2019","journal-title":"arXiv"},{"key":"2025030615255447800_bib28","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2308.05566","article-title":"AutoGluon-TimeSeries: AutoML for probabilistic time series forecasting","author":"Shchur","year":"2023","journal-title":"arXiv"},{"key":"2025030615255447800_bib29","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1805.12216","article-title":"A Web-scale system for scientific knowledge exploration","author":"Shen","year":"2018","journal-title":"arXiv"},{"key":"2025030615255447800_bib30","doi-asserted-by":"publisher","first-page":"849","DOI":"10.1007\/s11192-021-04240-2","article-title":"Research trend prediction in computer science publications: A deep neural network approach","volume":"127","author":"Taheri","year":"2022","journal-title":"Scientometrics"},{"issue":"26","key":"2025030615255447800_bib31","doi-asserted-by":"publisher","first-page":"e2011695118","DOI":"10.1073\/pnas.2011695118","article-title":"How quantifying the shape of stories predicts their success","volume":"118","author":"Toubia","year":"2021","journal-title":"Proceedings of the National Academy of Sciences"},{"key":"2025030615255447800_bib32","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1706.03762","article-title":"Attention is all you need","author":"Vaswani","year":"2017","journal-title":"arXiv"},{"key":"2025030615255447800_bib33","doi-asserted-by":"publisher","first-page":"101343","DOI":"10.1016\/j.joi.2022.101343","article-title":"MatrixSim: A new method for detecting the evolution paths of research topics","volume":"16","author":"Wang","year":"2022","journal-title":"Journal of Informetrics"},{"key":"2025030615255447800_bib34","doi-asserted-by":"publisher","first-page":"101055","DOI":"10.1016\/j.joi.2020.101055","article-title":"Monolingual and multilingual topic analysis using LDA and BERT embeddings","volume":"14","author":"Xie","year":"2020","journal-title":"Journal of Informetrics"},{"key":"2025030615255447800_bib35","doi-asserted-by":"publisher","first-page":"6331","DOI":"10.1002\/int.22846","article-title":"A scientific research topic trend prediction model based on multi-LSTM and graph convolutional network","volume":"37","author":"Xu","year":"2022","journal-title":"International Journal of Intelligent Systems"},{"key":"2025030615255447800_bib36","doi-asserted-by":"publisher","first-page":"100983","DOI":"10.1016\/j.joi.2019.100983","article-title":"Emerging research topics detection with multiple machine learning models","volume":"13","author":"Xu","year":"2019","journal-title":"Journal of Informetrics"},{"key":"2025030615255447800_bib37","doi-asserted-by":"publisher","first-page":"101422","DOI":"10.1016\/j.joi.2023.101422","article-title":"Developing a four-entities reinforced rank model to evaluate the topic influence in academic networks","volume":"17","author":"Yu","year":"2023","journal-title":"Journal of Informetrics"},{"key":"2025030615255447800_bib38","doi-asserted-by":"publisher","first-page":"120114","DOI":"10.1016\/j.eswa.2023.120114","article-title":"Discovering topics and trends in the field of artificial intelligence: Using LDA topic modeling","volume":"225","author":"Yu","year":"2023","journal-title":"Expert Systems with Applications"},{"key":"2025030615255447800_bib39","doi-asserted-by":"publisher","first-page":"2585","DOI":"10.1145\/3292500.3330785","article-title":"OAG: Toward linking large-scale heterogeneous entity graphs","volume-title":"Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining","author":"Zhang","year":"2019"},{"key":"2025030615255447800_bib40","doi-asserted-by":"publisher","first-page":"255","DOI":"10.1016\/j.knosys.2017.07.011","article-title":"Detecting and predicting the topic change of knowledge-based systems: A topic-based bibliometric analysis from 1991 to 2016","volume":"133","author":"Zhang","year":"2017","journal-title":"Knowledge-Based Systems"},{"key":"2025030615255447800_bib41","doi-asserted-by":"publisher","first-page":"179","DOI":"10.1016\/j.techfore.2016.01.015","article-title":"Topic analysis and forecasting for science, technology and innovation: Methodology with a case study focusing on big data research","volume":"105","author":"Zhang","year":"2016","journal-title":"Technological Forecasting and Social Change"}],"container-title":["Quantitative Science Studies"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/direct.mit.edu\/qss\/article-pdf\/doi\/10.1162\/qss_a_00344\/2485043\/qss_a_00344.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/direct.mit.edu\/qss\/article-pdf\/doi\/10.1162\/qss_a_00344\/2485043\/qss_a_00344.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,3,6]],"date-time":"2025-03-06T15:26:11Z","timestamp":1741274771000},"score":1,"resource":{"primary":{"URL":"https:\/\/direct.mit.edu\/qss\/article\/doi\/10.1162\/qss_a_00344\/125737\/A-framework-for-demonstrating-forecasting-and"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":41,"URL":"https:\/\/doi.org\/10.1162\/qss_a_00344","relation":{"has-review":[{"id-type":"doi","id":"10.1162\/QSS_A_00344\/v1\/review1","asserted-by":"object"},{"id-type":"doi","id":"10.1162\/QSS_A_00344\/v2\/response1","asserted-by":"object"},{"id-type":"doi","id":"10.1162\/QSS_A_00344\/v1\/decision1","asserted-by":"object"},{"id-type":"doi","id":"10.1162\/QSS_A_00344\/v1\/review2","asserted-by":"object"},{"id-type":"doi","id":"10.1162\/QSS_A_00344\/v2\/decision1","asserted-by":"object"}]},"ISSN":["2641-3337"],"issn-type":[{"value":"2641-3337","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2025]]},"published":{"date-parts":[[2025]]}}}