{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,8]],"date-time":"2025-09-08T06:41:23Z","timestamp":1757313683491,"version":"3.37.3"},"reference-count":57,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,1,26]],"date-time":"2022-01-26T00:00:00Z","timestamp":1643155200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,1,26]],"date-time":"2022-01-26T00:00:00Z","timestamp":1643155200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["1625677"],"award-info":[{"award-number":["1625677"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022,1,26]]},"DOI":"10.1109\/ccwc54503.2022.9720765","type":"proceedings-article","created":{"date-parts":[[2022,3,4]],"date-time":"2022-03-04T20:27:19Z","timestamp":1646425639000},"page":"0274-0280","source":"Crossref","is-referenced-by-count":21,"title":["Efficient Large Scale NLP Feature Engineering with Apache Spark"],"prefix":"10.1109","author":[{"given":"Armin","family":"Esmaeilzadeh","sequence":"first","affiliation":[{"name":"University of Nevada Las Vegas,Las Vegas,Nevada,USA"}]},{"given":"Maryam","family":"Heidari","sequence":"additional","affiliation":[{"name":"George Mason University,Virginia,USA"}]},{"given":"Reyhaneh","family":"Abdolazimi","sequence":"additional","affiliation":[{"name":"Syracuse University"}]},{"given":"Parisa","family":"Hajibabaee","sequence":"additional","affiliation":[{"name":"University of Massachusetts at Lowell,Lowell,USA"}]},{"given":"Masoud","family":"Malekzadeh","sequence":"additional","affiliation":[{"name":"University of Massachusetts at Lowell,Lowell,USA"}]}],"member":"263","reference":[{"key":"ref39","article-title":"A test driven approach to develop web-based machine learning applications","author":"esmaeilzadeh","year":"2017","journal-title":"UNLV Theses Dissertations Professional Papers and Capstones"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CCWC54503.2022.9720804"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1016\/j.cpet.2021.06.005"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/UEMCON53757.2021.9666633"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CCWC54503.2022.9720875"},{"key":"ref30","first-page":"466","article-title":"A survey of deep learning methods on semantic similar-ity and sentence modeling","author":"zad","year":"0","journal-title":"2021 IEEE 12th Annual Information Technology Electronics and Mobile Communication Conference (IEMCON)"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ISI49825.2020.9280487"},{"key":"ref36","first-page":"379","article-title":"Feature engineering for text classification","volume":"99","author":"scott","year":"1999","journal-title":"ICML"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.3390\/bios11060189"},{"key":"ref34","first-page":"1","article-title":"Ensemble of super-vised and unsupervised learning models to predict a prof-itable business decision","author":"heidari","year":"0","journal-title":"2021 IEEE International IOT Electronics and Mechatronics Conference (IEMTRONICS)"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ISI49825.2020.9280487"},{"key":"ref27","first-page":"513","article-title":"Clinical text classification of alzheimer's drugs' mechanism of action","author":"kambar","year":"0","journal-title":"Proceedings of Sixth International Congress on Information and Communication Technology"},{"key":"ref29","first-page":"175","article-title":"Text classification using neural network language model (nnlm) and bert: An empirical comparison","author":"esmaeilzadeh","year":"0","journal-title":"Proceedings of SAI Intelligent Systems Conference"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/UEMCON51285.2020.9298158"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jksuci.2017.06.001"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/IEMTRONICS52119.2021.9422605"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/AIIoT52608.2021.9454169"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/UEMCON53757.2021.9666618"},{"key":"ref24","first-page":"1","article-title":"Ontology creation model based on attention mechanism for a spe-cific business domain","author":"heidari","year":"0","journal-title":"2021 IEEE International IOT Electronics and Mechatronics Conference (IEMTRONICS)"},{"key":"ref23","first-page":"26","article-title":"Identifying and ranking critical factors that determine meritocracy using ahp technique in automotive industry in iran","volume":"24","author":"nazari","year":"0","journal-title":"International Conference on Technology and Business Management March"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/IEMCON53756.2021.9623238"},{"key":"ref25","article-title":"Pet image de-noising using unsupervised domain translation","author":"malekzadeh","year":"0","journal-title":"2021 IEEE Nuclear Science Symposium and Medical Imaging Conference Proceedings (NSS\/MIC)"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/MSST.2010.5496972"},{"key":"ref51","first-page":"1","article-title":"Apache hadoop yarn: Yet another resource nego-tiator","author":"vavilapalli","year":"0","journal-title":"Proceedings of the 4th Annual Symposium on Cloud Computing"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1145\/2723372.2742797"},{"year":"0","key":"ref56"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1108\/eb046814"},{"key":"ref54","first-page":"695","article-title":"A stochastic parts program and noun phrase parser for unrestricted text","author":"church","year":"0","journal-title":"International Conference on Acoustics Speech and Signal Processing"},{"year":"0","key":"ref53"},{"key":"ref52","first-page":"15","article-title":"Resilient distributed datasets: A fault-tolerant abstraction for in-memory cluster computing","author":"zaharia","year":"0","journal-title":"Part of the 9th USENIX Symposium on Networked Systems Design and Implementation ( NSDI 12)"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/s10586-016-0713-3"},{"key":"ref11","first-page":"472","article-title":"Noise-enhanced unsu-pervised link prediction","author":"abdolazimi","year":"0","journal-title":"Pacific-Asia Conference on Knowledge Discovery and Data Mining"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1016\/j.chb.2018.08.039"},{"journal-title":"Misinformation detection model to prevent spread of the covid-19 virus during the pandemic","year":"2022","author":"heidari","key":"ref12"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/3372923.3404788"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/SMAP49528.2020.9248443"},{"journal-title":"Transit agencies performance assessment and implications","year":"2020","author":"hajibabaee","key":"ref15"},{"journal-title":"Offensive behaviour detection on social media platforms by using natural language processing models","year":"2022","author":"heidari","key":"ref16"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICMLA52953.2021.00267"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.37193\/CMI.2015.02.05"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ISTAS50296.2020.9462170"},{"key":"ref4","first-page":"1","article-title":"Semantic convolutional neu-ral network model for safe business investment by using bert","author":"heidari","year":"0","journal-title":"2020 Seventh International Conference on Social Networks Analysis Management and Security (SNAMS)"},{"key":"ref3","first-page":"480","article-title":"Deep contextual-ized word embedding for text-based online user profiling to detect social bots on twitter","author":"heidari","year":"0","journal-title":"2020 International Conference on Data Mining Workshops (ICDMW)"},{"journal-title":"Fraud detection to increase customer trust in online shopping experience","year":"2022","author":"heidari","key":"ref6"},{"journal-title":"Nlp approach for social media bot detection(fake identity detection) to increase security and trust in online platforms","year":"2022","author":"heidari","key":"ref5"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/AIIoT52608.2021.9454192"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2021.3087730"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CCWC54503.2022.9720798"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICMLA52953.2021.00267"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1145\/1327452.1327492"},{"key":"ref45","article-title":"Improving explainability and accuracy through feature engineering: A taxonomy of features in nlp-based machine learning","author":"wambsganss","year":"0","journal-title":"Forty-Second International Conference on Information Systems"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-98192-5_9"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1145\/2934664"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/SECON.2016.7506650"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1201\/9781315181080-2"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CCWC54503.2022.9720753"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1007\/s00332-018-9465-y"}],"event":{"name":"2022 IEEE 12th Annual Computing and Communication Workshop and Conference (CCWC)","start":{"date-parts":[[2022,1,26]]},"location":"Las Vegas, NV, USA","end":{"date-parts":[[2022,1,29]]}},"container-title":["2022 IEEE 12th Annual Computing and Communication Workshop and Conference (CCWC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9720724\/9720434\/09720765.pdf?arnumber=9720765","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,6,20]],"date-time":"2022-06-20T21:34:39Z","timestamp":1655760879000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9720765\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,1,26]]},"references-count":57,"URL":"https:\/\/doi.org\/10.1109\/ccwc54503.2022.9720765","relation":{},"subject":[],"published":{"date-parts":[[2022,1,26]]}}}