{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,20]],"date-time":"2026-07-20T22:17:20Z","timestamp":1784585840608,"version":"3.55.0"},"reference-count":44,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2021]]},"DOI":"10.1109\/access.2021.3081479","type":"journal-article","created":{"date-parts":[[2021,5,17]],"date-time":"2021-05-17T21:24:42Z","timestamp":1621286682000},"page":"80253-80263","source":"Crossref","is-referenced-by-count":107,"title":["A Spam Transformer Model for SMS Spam Detection"],"prefix":"10.1109","volume":"9","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7772-4176","authenticated-orcid":false,"given":"Xiaoxu","family":"Liu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0933-2370","authenticated-orcid":false,"given":"Haoye","family":"Lu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4605-0500","authenticated-orcid":false,"given":"Amiya","family":"Nayak","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref39","year":"0","journal-title":"UtkMl’s Twitter Spam Detection Competition | Kaggle"},{"key":"ref38","article-title":"Decoupled weight decay regularization","author":"loshchilov","year":"2017","journal-title":"arXiv 1711 05101"},{"key":"ref33","article-title":"Neural machine translation by jointly learning to align and translate","author":"bahdanau","year":"2015","journal-title":"Proc 3rd Int Conf Learn Represent (ICLR)"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.515"},{"key":"ref31","doi-asserted-by":"crossref","first-page":"939","DOI":"10.21437\/Interspeech.2017-233","article-title":"A comparison of sequence-to-sequence models for speech recognition","author":"prabhavalkar","year":"2017","journal-title":"Proc INTERSPEECH"},{"key":"ref30","first-page":"3104","article-title":"Sequence to sequence learning with neural networks","volume":"4","author":"sutskever","year":"2014","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref37","article-title":"Improving neural networks by preventing co-adaptation of feature detectors","author":"hinton","year":"2012","journal-title":"arXiv 1207 0580"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1145\/3430937"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D15-1166"},{"key":"ref34","first-page":"2048","article-title":"Show, attend and tell: Neural image caption generation with visual attention","volume":"3","author":"xu","year":"2015","journal-title":"Proc 32nd Int Conf Mach Learn"},{"key":"ref10","doi-asserted-by":"crossref","first-page":"278","DOI":"10.1109\/ICDAR.1995.598994","article-title":"Random decision forests","volume":"1","author":"ho","year":"1995","journal-title":"Proc of Int Conf Document Analysis Recognition (ICDAR)"},{"key":"ref40","article-title":"spaCy: Industrial-strength natural language processing in python","author":"honnibal","year":"2020"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/BF00994018"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/IC3.2018.8530469"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/2034691.2034742"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1016\/j.procs.2017.12.079"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1016\/B978-1-55860-377-6.50023-2"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1016\/S0020-7373(87)80003-2"},{"key":"ref17","doi-asserted-by":"crossref","first-page":"1189","DOI":"10.1214\/aos\/1013203451","article-title":"Greedy function approximation: A gradient boosting machine","volume":"29","author":"friedman","year":"2001","journal-title":"Ann Statist"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-7908-2604-3_16"},{"key":"ref19","article-title":"Efficient estimation of word representations in vector space","author":"mikolov","year":"2013","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref28","first-page":"3881","article-title":"A clockwork RNN","volume":"5","author":"koutn\u00edk","year":"2014","journal-title":"Proc 31st Int Conf Mach Learn (ICML)"},{"key":"ref4","article-title":"Language models are few-shot learners","author":"brown","year":"2020","journal-title":"arXiv 2005 14165"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1179"},{"key":"ref3","first-page":"5999","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1093\/comjnl\/bxy039"},{"key":"ref29","article-title":"A C-LSTM neural network for text classification","author":"zhou","year":"2015","journal-title":"arXiv 1511 08630"},{"key":"ref5","first-page":"4171","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","volume":"1","author":"devlin","year":"2019","journal-title":"Proc Conf North Amer Chapter Assoc Comput Linguistics Hum Lang Technol"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1016\/j.future.2020.03.021"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/s11235-016-0269-9"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/s41870-018-0157-5"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1016\/j.cmpb.2017.10.022"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.future.2019.09.001"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/219717.219748"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.3390\/fi12090156"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1023\/B:BTTJ.0000047600.45421.6d"},{"key":"ref42","first-page":"2825","article-title":"Scikit-learn: Machine learning in python","volume":"12","author":"pedregosa","year":"2011","journal-title":"J Mach Learn Res"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/72.279181"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1162"},{"key":"ref23","doi-asserted-by":"crossref","first-page":"533","DOI":"10.1038\/323533a0","article-title":"Learning representations by back-propagating errors","volume":"323","author":"rumelhart","year":"1986","journal-title":"Nature"},{"key":"ref44","article-title":"Tune: A research platform for distributed model selection and training","author":"liaw","year":"2018","journal-title":"arXiv 1807 05118"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref43","first-page":"8024","article-title":"PyTorch: An imperative style, high-performance deep learning library","author":"paszke","year":"2019","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref25","first-page":"2347","article-title":"On the difficulty of training recurrent neural networks","author":"pascanu","year":"2013","journal-title":"Proc 30th Int Conf Mach Learn (ICML)"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/9312710\/09433507.pdf?arnumber=9433507","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,12,17]],"date-time":"2021-12-17T19:57:37Z","timestamp":1639771057000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9433507\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"references-count":44,"URL":"https:\/\/doi.org\/10.1109\/access.2021.3081479","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021]]}}}