{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,8]],"date-time":"2026-04-08T18:02:43Z","timestamp":1775671363202,"version":"3.50.1"},"reference-count":50,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,12,15]],"date-time":"2021-12-15T00:00:00Z","timestamp":1639526400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,12,15]],"date-time":"2021-12-15T00:00:00Z","timestamp":1639526400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100007040","name":"Singapore University of Technology and Design","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100007040","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021,12,15]]},"DOI":"10.1109\/bigdata52589.2021.9671598","type":"proceedings-article","created":{"date-parts":[[2022,1,13]],"date-time":"2022-01-13T20:39:16Z","timestamp":1642106356000},"page":"4965-4973","source":"Crossref","is-referenced-by-count":7,"title":["Analyzing Scientific Publications using Domain-Specific Word Embedding and Topic Modelling"],"prefix":"10.1109","author":[{"given":"Trisha","family":"Singhal","sequence":"first","affiliation":[{"name":"Singapore University of Technology and Design,SUTD-MIT International Design Centre,Singapore"}]},{"given":"Junhua","family":"Liu","sequence":"additional","affiliation":[{"name":"Singapore University of Technology and Design,Information Systems Technology and Design Pillar,Singapore"}]},{"given":"Lucienne T. M.","family":"Blessing","sequence":"additional","affiliation":[{"name":"Singapore University of Technology and Design,Engineering Product Development Pillar,Singapore"}]},{"given":"Kwan Hui","family":"Lim","sequence":"additional","affiliation":[{"name":"Singapore University of Technology and Design,Information Systems Technology and Design Pillar,Singapore"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1145\/2658537.2658708"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1145\/3173574.3173704"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1145\/3397482.3450733"},{"key":"ref32","article-title":"Exploratory analysis of covid-19 tweets using topic modeling, umap, and digraphs","author":"ordun","year":"2020"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1145\/2910896.2910904"},{"key":"ref30","article-title":"Looking beyond text: Extracting figures, tables and captions from computer science papers","author":"clark","year":"2015","journal-title":"Workshops at the Twenty-Ninth AAAI Conference on Artificial Intelligence"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/BigData47090.2019.9005497"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1017\/dsi.2019.283"},{"key":"ref35","article-title":"Topic modeling genre: An exploration of french classical and enlightenment drama","volume":"11","author":"sch\u00f6ch","year":"2017","journal-title":"Digital Humanities Quarterly"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ASONAM49781.2020.9381384"},{"key":"ref28","article-title":"Deeppdf: A deep learning approach to extracting text from pdfs","author":"stahl","year":"2018","journal-title":"Tech Rep"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1016\/j.wpi.2018.07.006"},{"key":"ref29","first-page":"5315","article-title":"Learning to extract semantic structure from documents using multi-modal fully convolutional neural networks","author":"yang","year":"2017","journal-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1002\/sres.2619"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.22323\/2.16020202"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1117\/12.476326"},{"key":"ref22","first-page":"473","article-title":"Grobid: Combining automatic bibliographic data recognition and term extraction for scholarship publications","author":"lopez","year":"2009","journal-title":"International Conference on Theory and Practice of Digital Libraries"},{"key":"ref21","first-page":"661","article-title":"Parscit: an open-source crf reference string parsing package","volume":"8","author":"councill","year":"2008","journal-title":"LREC"},{"key":"ref24","article-title":"Ocr++: a robust framework for information extraction from scholarly articles","author":"singh","year":"2016"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/DAS.2014.63"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/JCDL.2003.1204842"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/JCDL.2003.1204843"},{"key":"ref50","first-page":"262","article-title":"Optimizing semantic coherence in topic models","author":"mimno","year":"2011","journal-title":"Proceedings of the 2011 Conference on Empirical Methods in Natural Language Processing"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.327"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.iwslt-1.27"},{"key":"ref40","first-page":"31","article-title":"Trends and changes in the field of hci the last decade from the perspective of hcii conference","author":"valdez","year":"2019","journal-title":"International conference on human-computer interaction"},{"key":"ref12","first-page":"452","article-title":"Opinion mining and sentiment analysis","author":"bakshi","year":"2016","journal-title":"2016 3rd International Conference on Computing for Sustainable Global Development (INDIACom)"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.567"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1016\/j.future.2020.08.005"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.3316\/QRJ0902027"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/COMPSAC.2019.00064"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/BigData50022.2020.9377739"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/3465336.3475117"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1186\/s40537-021-00482-2"},{"key":"ref4","article-title":"sklearn.feature extraction.text.countvectorizer — scikit-learn 0.24.1 documentation","year":"0"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1177\/0165551520932855"},{"key":"ref6","article-title":"Efficient estimation of word representations in vector space","author":"mikolov","year":"2013"},{"key":"ref5","article-title":"sklearn.feature extraction.text.tfidfvectorizer — scikit-learn 0.24.1 documentation","year":"0"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N18-1202"},{"key":"ref7","doi-asserted-by":"crossref","first-page":"1532","DOI":"10.3115\/v1\/D14-1162","article-title":"Glove: Global vectors for word representation","author":"pennington","year":"2014","journal-title":"Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP)"},{"key":"ref49","first-page":"993","article-title":"Latent dirichlet allocation","volume":"3","author":"blei","year":"2003","journal-title":"Journal of Machine Learning Research"},{"key":"ref9","article-title":"Neural machine translation by jointly learning to align and translate","author":"bahdanau","year":"2014"},{"key":"ref46","first-page":"2579","article-title":"Visualizing data using t-sne","volume":"9","author":"maaten","year":"2008","journal-title":"Journal of Machine Learning Research"},{"key":"ref45","first-page":"281","article-title":"Some methods for classification and analysis of multivariate observations","volume":"1","author":"macqueen","year":"1967","journal-title":"Proceedings of the Fifth Berkeley Symposium on Mathematical Statistics and Probability"},{"key":"ref48","first-page":"857","article-title":"Stochastic neighbor embedding","volume":"15","author":"hinton","year":"2002","journal-title":"Advances in neural information processing systems"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.3390\/j2020016"},{"key":"ref42","article-title":"Word embeddings: A survey","author":"almeida","year":"2019"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-53817-4_4"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1016\/0306-4573(88)90021-0"},{"key":"ref43","article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","author":"devlin","year":"2018"}],"event":{"name":"2021 IEEE International Conference on Big Data (Big Data)","location":"Orlando, FL, USA","start":{"date-parts":[[2021,12,15]]},"end":{"date-parts":[[2021,12,18]]}},"container-title":["2021 IEEE International Conference on Big Data (Big Data)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9671263\/9671273\/09671598.pdf?arnumber=9671598","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,12,5]],"date-time":"2022-12-05T23:43:34Z","timestamp":1670283814000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9671598\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,12,15]]},"references-count":50,"URL":"https:\/\/doi.org\/10.1109\/bigdata52589.2021.9671598","relation":{},"subject":[],"published":{"date-parts":[[2021,12,15]]}}}