{"id":"https://openalex.org/W4400579109","doi":"https://doi.org/10.1109/tetci.2024.3423444","title":"From Bag-of-Words to Transformers: A Comparative Study for Text Classification in Healthcare Discussions in Social Media","display_name":"From Bag-of-Words to Transformers: A Comparative Study for Text Classification in Healthcare Discussions in Social Media","publication_year":2024,"publication_date":"2024-07-12","ids":{"openalex":"https://openalex.org/W4400579109","doi":"https://doi.org/10.1109/tetci.2024.3423444"},"language":"en","primary_location":{"id":"doi:10.1109/tetci.2024.3423444","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tetci.2024.3423444","pdf_url":null,"source":{"id":"https://openalex.org/S4210210251","display_name":"IEEE Transactions on Emerging Topics in Computational Intelligence","issn_l":"2471-285X","issn":["2471-285X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Emerging Topics in Computational Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://iris.luiss.it/bitstream/11385/239878/3/From_Bag-of-Words_to_Transformers_A_Comparative_Study_for_Text_Classification_in_Healthcare_Discussions_in_Social_Media.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5020616232","display_name":"Enrico De Santis","orcid":"https://orcid.org/0000-0003-4915-0723"},"institutions":[{"id":"https://openalex.org/I861853513","display_name":"Sapienza University of Rome","ror":"https://ror.org/02be6w209","country_code":"IT","type":"education","lineage":["https://openalex.org/I861853513"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Enrico De Santis","raw_affiliation_strings":["Department of Information Engineering, Electronics and Telecommunications, University of Rome “La Sapienza”, Rome, Italy"],"raw_orcid":"https://orcid.org/0000-0003-4915-0723","affiliations":[{"raw_affiliation_string":"Department of Information Engineering, Electronics and Telecommunications, University of Rome “La Sapienza”, Rome, Italy","institution_ids":["https://openalex.org/I861853513"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102864628","display_name":"Alessio Martino","orcid":"https://orcid.org/0000-0003-1730-5436"},"institutions":[{"id":"https://openalex.org/I56441308","display_name":"Libera Universit\u00e0 Internazionale degli Studi Sociali Guido Carli","ror":"https://ror.org/01q8b6q23","country_code":"IT","type":"education","lineage":["https://openalex.org/I56441308"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Alessio Martino","raw_affiliation_strings":["Department of Business and Management, LUISS University, Rome, Italy"],"raw_orcid":"https://orcid.org/0000-0003-1730-5436","affiliations":[{"raw_affiliation_string":"Department of Business and Management, LUISS University, Rome, Italy","institution_ids":["https://openalex.org/I56441308"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109614120","display_name":"Francesca Ronci","orcid":null},"institutions":[{"id":"https://openalex.org/I861853513","display_name":"Sapienza University of Rome","ror":"https://ror.org/02be6w209","country_code":"IT","type":"education","lineage":["https://openalex.org/I861853513"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Francesca Ronci","raw_affiliation_strings":["Department of Information Engineering, Electronics and Telecommunications, University of Rome “La Sapienza”, Rome, Italy"],"raw_orcid":"https://orcid.org/0009-0001-3920-6044","affiliations":[{"raw_affiliation_string":"Department of Information Engineering, Electronics and Telecommunications, University of Rome “La Sapienza”, Rome, Italy","institution_ids":["https://openalex.org/I861853513"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5025282612","display_name":"Antonello Rizzi","orcid":null},"institutions":[{"id":"https://openalex.org/I861853513","display_name":"Sapienza University of Rome","ror":"https://ror.org/02be6w209","country_code":"IT","type":"education","lineage":["https://openalex.org/I861853513"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Antonello Rizzi","raw_affiliation_strings":["Department of Information Engineering, Electronics and Telecommunications, University of Rome “La Sapienza”, Rome, Italy"],"raw_orcid":"https://orcid.org/0000-0001-8244-0015","affiliations":[{"raw_affiliation_string":"Department of Information Engineering, Electronics and Telecommunications, University of Rome “La Sapienza”, Rome, Italy","institution_ids":["https://openalex.org/I861853513"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":6.6402,"has_fulltext":true,"cited_by_count":27,"citation_normalized_percentile":{"value":0.97178668,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":100},"biblio":{"volume":"9","issue":"1","first_page":"1063","last_page":"1077"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9663000106811523,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9663000106811523,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11147","display_name":"Misinformation and Its Impacts","score":0.9628999829292297,"subfield":{"id":"https://openalex.org/subfields/3312","display_name":"Sociology and Political Science"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.9562000036239624,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/word-embedding","display_name":"Word embedding","score":0.738714873790741},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7357136011123657},{"id":"https://openalex.org/keywords/categorization","display_name":"Categorization","score":0.647304356098175},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.593165397644043},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.5511196255683899},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5308172702789307},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.5144679546356201},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5066710114479065},{"id":"https://openalex.org/keywords/social-media","display_name":"Social media","score":0.49085599184036255},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.45550110936164856},{"id":"https://openalex.org/keywords/sentiment-analysis","display_name":"Sentiment analysis","score":0.4539759159088135},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.43155449628829956},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3494451642036438},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.2370418906211853}],"concepts":[{"id":"https://openalex.org/C2777462759","wikidata":"https://www.wikidata.org/wiki/Q18395344","display_name":"Word embedding","level":3,"score":0.738714873790741},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7357136011123657},{"id":"https://openalex.org/C94124525","wikidata":"https://www.wikidata.org/wiki/Q912550","display_name":"Categorization","level":2,"score":0.647304356098175},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.593165397644043},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.5511196255683899},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5308172702789307},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.5144679546356201},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5066710114479065},{"id":"https://openalex.org/C518677369","wikidata":"https://www.wikidata.org/wiki/Q202833","display_name":"Social media","level":2,"score":0.49085599184036255},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.45550110936164856},{"id":"https://openalex.org/C66402592","wikidata":"https://www.wikidata.org/wiki/Q2271421","display_name":"Sentiment analysis","level":2,"score":0.4539759159088135},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.43155449628829956},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3494451642036438},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.2370418906211853},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/tetci.2024.3423444","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tetci.2024.3423444","pdf_url":null,"source":{"id":"https://openalex.org/S4210210251","display_name":"IEEE Transactions on Emerging Topics in Computational Intelligence","issn_l":"2471-285X","issn":["2471-285X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Emerging Topics in Computational Intelligence","raw_type":"journal-article"},{"id":"pmh:oai:iris.luiss.it:11385/239878","is_oa":true,"landing_page_url":"https://hdl.handle.net/11385/239878","pdf_url":"https://iris.luiss.it/bitstream/11385/239878/3/From_Bag-of-Words_to_Transformers_A_Comparative_Study_for_Text_Classification_in_Healthcare_Discussions_in_Social_Media.pdf","source":{"id":"https://openalex.org/S4377196446","display_name":"IRIS - Institutional Research Information System (Libera Universit\u00e0 Internazionale degli Studi Sociali Guido Carli)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I56441308","host_organization_name":"Libera Universit\u00e0 Internazionale degli Studi Sociali Guido Carli","host_organization_lineage":["https://openalex.org/I56441308"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/article"},{"id":"pmh:oai:iris.uniroma1.it:11573/1718338","is_oa":true,"landing_page_url":"https://hdl.handle.net/11573/1718338","pdf_url":"https://iris.uniroma1.it/bitstream/11573/1718338/1/De%20Santis_From_Bag-of-Words_2024.pdf","source":{"id":"https://openalex.org/S4377196107","display_name":"IRIS Research product catalog (Sapienza University of Rome)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":{"id":"pmh:oai:iris.luiss.it:11385/239878","is_oa":true,"landing_page_url":"https://hdl.handle.net/11385/239878","pdf_url":"https://iris.luiss.it/bitstream/11385/239878/3/From_Bag-of-Words_to_Transformers_A_Comparative_Study_for_Text_Classification_in_Healthcare_Discussions_in_Social_Media.pdf","source":{"id":"https://openalex.org/S4377196446","display_name":"IRIS - Institutional Research Information System (Libera Universit\u00e0 Internazionale degli Studi Sociali Guido Carli)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I56441308","host_organization_name":"Libera Universit\u00e0 Internazionale degli Studi Sociali Guido Carli","host_organization_lineage":["https://openalex.org/I56441308"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.44999998807907104,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4400579109.pdf","grobid_xml":"https://content.openalex.org/works/W4400579109.grobid-xml"},"referenced_works_count":71,"referenced_works":["https://openalex.org/W168564468","https://openalex.org/W825525975","https://openalex.org/W1981617416","https://openalex.org/W2002514548","https://openalex.org/W2066918800","https://openalex.org/W2101234009","https://openalex.org/W2105482032","https://openalex.org/W2125031621","https://openalex.org/W2131567188","https://openalex.org/W2133564696","https://openalex.org/W2140679639","https://openalex.org/W2141599568","https://openalex.org/W2144902422","https://openalex.org/W2147152072","https://openalex.org/W2165612380","https://openalex.org/W2171056096","https://openalex.org/W2187089797","https://openalex.org/W2250539671","https://openalex.org/W2330858170","https://openalex.org/W2493916176","https://openalex.org/W2515248967","https://openalex.org/W2749701213","https://openalex.org/W2779179495","https://openalex.org/W2896457183","https://openalex.org/W2951934944","https://openalex.org/W2963923670","https://openalex.org/W2965373594","https://openalex.org/W2997591727","https://openalex.org/W3017280632","https://openalex.org/W3041311242","https://openalex.org/W3042262243","https://openalex.org/W3045669112","https://openalex.org/W3091571146","https://openalex.org/W3114035546","https://openalex.org/W3150635270","https://openalex.org/W3154477404","https://openalex.org/W3213505436","https://openalex.org/W4205138587","https://openalex.org/W4205767597","https://openalex.org/W4210586753","https://openalex.org/W4211116998","https://openalex.org/W4239510810","https://openalex.org/W4251179700","https://openalex.org/W4292779060","https://openalex.org/W4307976116","https://openalex.org/W4313483544","https://openalex.org/W4321021524","https://openalex.org/W4324130227","https://openalex.org/W4327810158","https://openalex.org/W4360618568","https://openalex.org/W4380629188","https://openalex.org/W4385245566","https://openalex.org/W4385482653","https://openalex.org/W4385571552","https://openalex.org/W4387561528","https://openalex.org/W4390102235","https://openalex.org/W4391164144","https://openalex.org/W4391900009","https://openalex.org/W4404782964","https://openalex.org/W6623178044","https://openalex.org/W6678885109","https://openalex.org/W6680532216","https://openalex.org/W6680890276","https://openalex.org/W6681302627","https://openalex.org/W6685314792","https://openalex.org/W6766673545","https://openalex.org/W6778883912","https://openalex.org/W6786951257","https://openalex.org/W6794193156","https://openalex.org/W6803865828","https://openalex.org/W6861601097"],"related_works":["https://openalex.org/W2165912799","https://openalex.org/W2735662278","https://openalex.org/W2382615723","https://openalex.org/W4311804456","https://openalex.org/W1987484445","https://openalex.org/W2623658258","https://openalex.org/W3186997021","https://openalex.org/W4200618314","https://openalex.org/W4308088897","https://openalex.org/W4286432911"],"abstract_inverted_index":{"One":[0],"notable":[1],"paradigm":[2],"shift":[3],"in":[4,37,49,86,149,222,239,250,254],"Natural":[5],"Language":[6],"Processing":[7],"has":[8,135],"been":[9],"the":[10,38,62,160,177,189,195,205,223,236,247,255],"introduction":[11],"of":[12,27,40,64,163,235,257],"Transformers,":[13,28],"revolutionizing":[14],"language":[15,251],"modeling":[16],"as":[17],"Convolutional":[18],"Neural":[19],"Networks":[20],"did":[21],"for":[22,68,90,99,264],"Computer":[23],"Vision.":[24],"The":[25,93,110,133,172],"power":[26],"along":[29],"with":[30,192],"many":[31],"other":[32],"innovative":[33],"features,":[34],"also":[35,159],"lies":[36],"integration":[39],"word":[41,100],"embedding":[42,101,123,232],"techniques,":[43,124],"traditionally":[44],"used":[45,186],"to":[46,53,114,140,157,187,194],"represent":[47],"words":[48],"a":[50,136],"text":[51,65,240,258],"and":[52,81,104,122,152,156,170,208,217,228,260],"build":[54,141],"classification":[55,202,224,266],"systems":[56],"directly.":[57],"This":[58,198,242],"study":[59,94],"delves":[60],"into":[61,246],"comparison":[63],"representation":[66,259],"techniques":[67],"classifying":[69],"users":[70],"who":[71],"generate":[72],"medical":[73,150,268],"topic":[74],"posts":[75],"on":[76,201],"Facebook":[77],"discussion":[78],"groups.":[79],"Short":[80],"noisy":[82],"social":[83],"media":[84],"texts":[85],"Italian":[87],"pose":[88],"challenges":[89],"user":[91,117,265],"categorization.":[92],"employs":[95],"two":[96],"datasets,":[97],"one":[98,234],"model":[102],"estimation":[103],"another":[105],"comprising":[106],"discussions":[107,151],"from":[108],"users.":[109],"main":[111],"objective":[112],"is":[113,174],"achieve":[115],"optimal":[116],"categorization":[118],"through":[119],"different":[120,214],"pre-processing":[121],"aiming":[125],"at":[126],"high":[127],"generalization":[128],"performance":[129],"despite":[130],"class":[131],"imbalance.":[132],"paper":[134],"dual":[137],"purpose,":[138],"i.e.,":[139],"an":[142],"effective":[143],"classifier,":[144],"ensuring":[145],"accurate":[146],"information":[147],"dissemination":[148],"combating":[153],"fake":[154],"news,":[155],"explore":[158],"representational":[161],"capabilities":[162],"various":[164],"LLMs,":[165],"especially":[166],"concerning":[167],"BERT,":[168],"Mistral":[169],"GPT-4.":[171],"latter":[173],"investigated":[175],"using":[176],"in-context":[178],"learning":[179],"approach.":[180],"Finally,":[181],"data":[182],"visualization":[183],"tools":[184],"are":[185],"evaluate":[188],"semantic":[190],"embeddings":[191],"respect":[193],"achieved":[196],"performance.":[197],"investigation,":[199],"focusing":[200],"performance,":[203],"compares":[204],"classic":[206],"BERT":[207],"several":[209,229],"hybrid":[210],"versions":[211],"(i.e.,":[212],"employing":[213],"training":[215],"strategies":[216],"approximate":[218],"Support":[219],"Vector":[220],"Machines":[221],"layer)":[225],"against":[226],"LLMs":[227],"Bag-of-Words":[230],"based":[231],"(notably,":[233],"earliest":[237],"approaches":[238],"classification).":[241],"research":[243],"offers":[244],"insights":[245],"latest":[248],"developments":[249],"modeling,":[252],"advancing":[253],"field":[256],"its":[261],"practical":[262],"application":[263],"within":[267],"discussions.":[269]},"counts_by_year":[{"year":2026,"cited_by_count":7},{"year":2025,"cited_by_count":17},{"year":2024,"cited_by_count":3}],"updated_date":"2026-07-15T18:14:33.161393","created_date":"2025-10-10T00:00:00"}