{"id":"https://openalex.org/W4399290453","doi":"https://doi.org/10.1007/s10664-024-10468-2","title":"Transformers and meta-tokenization in sentiment analysis for software engineering","display_name":"Transformers and meta-tokenization in sentiment analysis for software engineering","publication_year":2024,"publication_date":"2024-06-03","ids":{"openalex":"https://openalex.org/W4399290453","doi":"https://doi.org/10.1007/s10664-024-10468-2"},"language":"en","primary_location":{"id":"doi:10.1007/s10664-024-10468-2","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10664-024-10468-2","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10664-024-10468-2.pdf","source":{"id":"https://openalex.org/S109852484","display_name":"Empirical Software Engineering","issn_l":"1382-3256","issn":["1382-3256","1573-7616"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Empirical Software Engineering","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://link.springer.com/content/pdf/10.1007/s10664-024-10468-2.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5002876832","display_name":"Nathan Cassee","orcid":"https://orcid.org/0000-0002-6511-918X"},"institutions":[{"id":"https://openalex.org/I83019370","display_name":"Eindhoven University of Technology","ror":"https://ror.org/02c2kyt77","country_code":"NL","type":"education","lineage":["https://openalex.org/I83019370"]}],"countries":["NL"],"is_corresponding":true,"raw_author_name":"Nathan Cassee","raw_affiliation_strings":["Eindhoven University of Technology, Eindhoven, The Netherlands"],"raw_orcid":"https://orcid.org/0000-0002-6511-918X","affiliations":[{"raw_affiliation_string":"Eindhoven University of Technology, Eindhoven, The Netherlands","institution_ids":["https://openalex.org/I83019370"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5092452054","display_name":"Andrei Agaronian","orcid":null},"institutions":[{"id":"https://openalex.org/I83019370","display_name":"Eindhoven University of Technology","ror":"https://ror.org/02c2kyt77","country_code":"NL","type":"education","lineage":["https://openalex.org/I83019370"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Andrei Agaronian","raw_affiliation_strings":["Eindhoven University of Technology, Eindhoven, The Netherlands"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Eindhoven University of Technology, Eindhoven, The Netherlands","institution_ids":["https://openalex.org/I83019370"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061728632","display_name":"Eleni Constantinou","orcid":"https://orcid.org/0000-0002-4242-2581"},"institutions":[{"id":"https://openalex.org/I34771391","display_name":"University of Cyprus","ror":"https://ror.org/02qjrjx09","country_code":"CY","type":"education","lineage":["https://openalex.org/I34771391"]}],"countries":["CY"],"is_corresponding":false,"raw_author_name":"Eleni Constantinou","raw_affiliation_strings":["University of Cyprus, Nicosia, Cyprus"],"raw_orcid":"https://orcid.org/0000-0002-4242-2581","affiliations":[{"raw_affiliation_string":"University of Cyprus, Nicosia, Cyprus","institution_ids":["https://openalex.org/I34771391"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030063602","display_name":"Nicole Novielli","orcid":"https://orcid.org/0000-0003-1160-2608"},"institutions":[{"id":"https://openalex.org/I5561750","display_name":"University of Bari Aldo Moro","ror":"https://ror.org/027ynra39","country_code":"IT","type":"education","lineage":["https://openalex.org/I5561750"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Nicole Novielli","raw_affiliation_strings":["University of Bari, Bari, Italy"],"raw_orcid":"https://orcid.org/0000-0003-1160-2608","affiliations":[{"raw_affiliation_string":"University of Bari, Bari, Italy","institution_ids":["https://openalex.org/I5561750"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5054753279","display_name":"Alexander Serebrenik","orcid":"https://orcid.org/0000-0002-1418-0095"},"institutions":[{"id":"https://openalex.org/I83019370","display_name":"Eindhoven University of Technology","ror":"https://ror.org/02c2kyt77","country_code":"NL","type":"education","lineage":["https://openalex.org/I83019370"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Alexander Serebrenik","raw_affiliation_strings":["Eindhoven University of Technology, Eindhoven, The Netherlands"],"raw_orcid":"https://orcid.org/0000-0002-1418-0095","affiliations":[{"raw_affiliation_string":"Eindhoven University of Technology, Eindhoven, The Netherlands","institution_ids":["https://openalex.org/I83019370"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5002876832"],"corresponding_institution_ids":["https://openalex.org/I83019370"],"apc_list":{"value":2290,"currency":"EUR","value_usd":2890},"apc_paid":{"value":2290,"currency":"EUR","value_usd":2890},"fwci":2.4309,"has_fulltext":true,"cited_by_count":8,"citation_normalized_percentile":{"value":0.90118894,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"29","issue":"4","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10664","display_name":"Sentiment Analysis and Opinion Mining","score":0.9998000264167786,"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/T10664","display_name":"Sentiment Analysis and Opinion Mining","score":0.9998000264167786,"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/T10028","display_name":"Topic Modeling","score":0.9984999895095825,"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/T10260","display_name":"Software Engineering Research","score":0.9976999759674072,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/lexical-analysis","display_name":"Lexical analysis","score":0.7445321083068848},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5714085698127747},{"id":"https://openalex.org/keywords/software-engineering","display_name":"Software engineering","score":0.4431384205818176},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.4136066734790802},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3683699667453766},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.2954067587852478}],"concepts":[{"id":"https://openalex.org/C176982825","wikidata":"https://www.wikidata.org/wiki/Q835922","display_name":"Lexical analysis","level":2,"score":0.7445321083068848},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5714085698127747},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.4431384205818176},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.4136066734790802},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3683699667453766},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.2954067587852478}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1007/s10664-024-10468-2","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10664-024-10468-2","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10664-024-10468-2.pdf","source":{"id":"https://openalex.org/S109852484","display_name":"Empirical Software Engineering","issn_l":"1382-3256","issn":["1382-3256","1573-7616"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Empirical Software Engineering","raw_type":"journal-article"},{"id":"pmh:oai:pure.tue.nl:openaire_cris_publications/e1067615-e836-424e-9432-60780aa2e26e","is_oa":true,"landing_page_url":"https://research.tue.nl/en/publications/e1067615-e836-424e-9432-60780aa2e26e","pdf_url":"https://pure.tue.nl/ws/files/330965277/s10664-024-10468-2.pdf","source":{"id":"https://openalex.org/S4406922641","display_name":"TU/e Research Portal","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","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Cassee, N W, Agaronian, A E, Constantinou, E, Novielli, N & Serebrenik, A 2024, 'Transformers and Meta-Tokenization in Sentiment Analysis for Software Engineering', Empirical Software Engineering, vol. 29, no. 4, 77. https://doi.org/10.1007/s10664-024-10468-2","raw_type":"info:eu-repo/semantics/publishedVersion"},{"id":"pmh:oai:ricerca.uniba.it:11586/485400","is_oa":true,"landing_page_url":"https://hdl.handle.net/11586/485400","pdf_url":null,"source":{"id":"https://openalex.org/S4377196296","display_name":"CINECA IRIS Institutional Research Information System (University of Bari Aldo Moro)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I5561750","host_organization_name":"University of Bari Aldo Moro","host_organization_lineage":["https://openalex.org/I5561750"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":{"id":"doi:10.1007/s10664-024-10468-2","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10664-024-10468-2","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10664-024-10468-2.pdf","source":{"id":"https://openalex.org/S109852484","display_name":"Empirical Software Engineering","issn_l":"1382-3256","issn":["1382-3256","1573-7616"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Empirical Software Engineering","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4399290453.pdf"},"referenced_works_count":45,"referenced_works":["https://openalex.org/W401943522","https://openalex.org/W1577581905","https://openalex.org/W1872197921","https://openalex.org/W1916584426","https://openalex.org/W2013416264","https://openalex.org/W2025599150","https://openalex.org/W2037789405","https://openalex.org/W2123442489","https://openalex.org/W2162739315","https://openalex.org/W2497653487","https://openalex.org/W2571312737","https://openalex.org/W2593675739","https://openalex.org/W2766375028","https://openalex.org/W2767270401","https://openalex.org/W2767841318","https://openalex.org/W2794607770","https://openalex.org/W2884491530","https://openalex.org/W2885935106","https://openalex.org/W2886486953","https://openalex.org/W2903957153","https://openalex.org/W2915294385","https://openalex.org/W2921166721","https://openalex.org/W2949137522","https://openalex.org/W2954384356","https://openalex.org/W2963250244","https://openalex.org/W2965441567","https://openalex.org/W3014437350","https://openalex.org/W3087144884","https://openalex.org/W3096150021","https://openalex.org/W3096160408","https://openalex.org/W3100111264","https://openalex.org/W3101079689","https://openalex.org/W3124180615","https://openalex.org/W3131386055","https://openalex.org/W3155412031","https://openalex.org/W3185244049","https://openalex.org/W3207231909","https://openalex.org/W3209840080","https://openalex.org/W3211925781","https://openalex.org/W3216660278","https://openalex.org/W4239510810","https://openalex.org/W4250195981","https://openalex.org/W4299582617","https://openalex.org/W4300581206","https://openalex.org/W4312463706"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W4300598845","https://openalex.org/W2601638452","https://openalex.org/W2285263069","https://openalex.org/W4319309671","https://openalex.org/W4376107815","https://openalex.org/W4319309603","https://openalex.org/W1599985958","https://openalex.org/W1748623649"],"abstract_inverted_index":{"Abstract":[0],"Sentiment":[1],"analysis":[2,30,75,90,141,147,172,190],"has":[3],"been":[4,50],"used":[5,180],"to":[6,57,152,187,192],"study":[7],"aspects":[8],"of":[9,25,45,106,170,175],"software":[10,26,128,182,193],"engineering,":[11],"such":[12],"as":[13],"issue":[14],"resolution,":[15],"toxicity,":[16],"and":[17,60,81,110],"self-admitted":[18],"technical":[19,36],"debt.":[20],"To":[21,40],"address":[22],"the":[23,34,43,98,107,116,144,167],"peculiarities":[24],"engineering":[27,129,183,194],"texts,":[28],"sentiment":[29,46,59,74,89,140,146,171,189],"tools":[31,76,148,191],"often":[32],"consider":[33,134],"specific":[35],"lingo":[37],"practitioners":[38],"use.":[39],"further":[41],"improve":[42,166],"application":[44],"analysis,":[47],"there":[48],"have":[49],"two":[51,108],"recommendations:":[52],"Using":[53],"pre-trained":[54,78,95],"transformer":[55,79],"models":[56,80],"classify":[58],"replacing":[61],"non-natural":[62],"language":[63],"elements":[64],"with":[65],"meta-tokens.":[66],"In":[67],"this":[68],"work,":[69],"we":[70,125,160],"benchmark":[71],"five":[72],"different":[73],"(two":[77],"three":[82],"machine":[83,100],"learning":[84,101],"tools)":[85],"on":[86,103,113],"2":[87],"gold-standard":[88],"datasets.":[91],"We":[92],"find":[93,161],"that":[94,111,114,127,162],"transformers":[96],"outperform":[97],"best":[99],"tool":[102,142],"only":[104],"one":[105],"datasets,":[109],"even":[112],"dataset":[115],"performance":[117,136,169],"difference":[118],"is":[119],"a":[120,139],"few":[121],"percentage":[122,157],"points.":[123],"Therefore,":[124],"recommend":[126],"researchers":[130,184],"should":[131],"not":[132,165],"just":[133],"predictive":[135,168],"when":[137],"selecting":[138],"because":[143],"best-performing":[145],"perform":[149],"very":[150],"similarly":[151],"each":[153],"other":[154],"(within":[155],"4":[156],"points).":[158],"Meanwhile,":[159],"meta-tokenization":[163],"does":[164],"tools.":[173],"Both":[174],"our":[176],"findings":[177],"can":[178],"be":[179],"by":[181],"who":[185],"seek":[186],"apply":[188],"data.":[195]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":1}],"updated_date":"2026-06-13T06:13:01.061226","created_date":"2025-10-10T00:00:00"}