{"id":"https://openalex.org/W7224089732","doi":"https://doi.org/10.3390/sym18111799","title":"Dataset and Backbone Effects on Accuracy\u2013Efficiency Asymmetry in Hybrid Prefix\u2013Prompt Tuning for Sentiment Analysis","display_name":"Dataset and Backbone Effects on Accuracy\u2013Efficiency Asymmetry in Hybrid Prefix\u2013Prompt Tuning for Sentiment Analysis","publication_year":2026,"publication_date":"2026-10-28","ids":{"openalex":"https://openalex.org/W7224089732","doi":"https://doi.org/10.3390/sym18111799"},"language":"en","primary_location":{"id":"doi:10.3390/sym18111799","doi":"https://doi.org/10.3390/sym18111799","is_oa":true,"landing_page_url":"https://doi.org/10.3390/sym18111799","pdf_url":null,"source":{"id":"https://openalex.org/S190787756","display_name":"Symmetry","issn_l":"2073-8994","issn":["2073-8994"],"is_oa":true,"is_in_doaj":false,"is_core":true,"listed_in":["anvur-scientific","cwts-core","norway-1","poland-70","russia-white-list-1","vabb-shw"],"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Symmetry","raw_type":"journal-article"},"volume":null,"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.3390/sym18111799","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5160048721","display_name":"Yahya Al-Dhahli","orcid":"https://orcid.org/0009-0006-2272-2372","observed_orcids":["https://orcid.org/0009-0006-2272-2372"]},"institutions":[{"id":"https://openalex.org/I84524832","display_name":"Alexandria University","ror":"https://ror.org/00mzz1w90","country_code":"EG","type":"education","lineage":["https://openalex.org/I84524832"]}],"countries":["EG"],"is_corresponding":true,"raw_author_name":"Yahya Al-Dhahli","raw_affiliation_strings":["Department of Information Technology, Institute of Graduate Studies and Research, Alexandria University, Alexandria 21526, Egypt"],"raw_orcid":"https://orcid.org/0009-0006-2272-2372","affiliations":[{"raw_affiliation_string":"Department of Information Technology, Institute of Graduate Studies and Research, Alexandria University, Alexandria 21526, Egypt","institution_ids":["https://openalex.org/I84524832"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041801663","display_name":"Magda Mohamed Madbouly","orcid":"https://orcid.org/0000-0002-9854-4609","observed_orcids":["https://orcid.org/0000-0002-9854-4609"]},"institutions":[{"id":"https://openalex.org/I84524832","display_name":"Alexandria University","ror":"https://ror.org/00mzz1w90","country_code":"EG","type":"education","lineage":["https://openalex.org/I84524832"]}],"countries":["EG"],"is_corresponding":false,"raw_author_name":"Magda M. Madbouly","raw_affiliation_strings":["Faculty of Computers and Data Science, Alexandria University, Alexandria 21526, Egypt"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Faculty of Computers and Data Science, Alexandria University, Alexandria 21526, Egypt","institution_ids":["https://openalex.org/I84524832"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5010758990","display_name":"Shawkat Kamal Guirguis","orcid":"https://orcid.org/0000-0001-5718-9025","observed_orcids":["https://orcid.org/0000-0001-5718-9025"]},"institutions":[{"id":"https://openalex.org/I84524832","display_name":"Alexandria University","ror":"https://ror.org/00mzz1w90","country_code":"EG","type":"education","lineage":["https://openalex.org/I84524832"]}],"countries":["EG"],"is_corresponding":false,"raw_author_name":"Shawkat K. Guirguis","raw_affiliation_strings":["Department of Information Technology, Institute of Graduate Studies and Research, Alexandria University, Alexandria 21526, Egypt"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Information Technology, Institute of Graduate Studies and Research, Alexandria University, Alexandria 21526, Egypt","institution_ids":["https://openalex.org/I84524832"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5160048721"],"corresponding_institution_ids":["https://openalex.org/I84524832"],"apc_list":{"value":2400,"currency":"CHF","value_usd":2896},"apc_paid":{"value":2400,"currency":"CHF","value_usd":2896},"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.85389992,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"18","issue":"11","first_page":"1799","last_page":"1799"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.4779999852180481,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.4779999852180481,"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/T10664","display_name":"Sentiment Analysis and Opinion Mining","score":0.33009999990463257,"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":0.16599999368190765,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/parameter-efficient-fine-tuning","display_name":"parameter-efficient fine-tuning","score":0.9620000123977661},{"id":"https://openalex.org/keywords/sentiment-analysis","display_name":"sentiment analysis","score":0.8220000267028809},{"id":"https://openalex.org/keywords/accuracy-efficiency-trade-off","display_name":"accuracy-efficiency trade-off","score":0.9169999957084656},{"id":"https://openalex.org/keywords/lora","display_name":"LoRa","score":0.7760000228881836},{"id":"https://openalex.org/keywords/adapters","display_name":"adapters","score":0.8769999742507935},{"id":"https://openalex.org/keywords/learning-rate-sensitivity","display_name":"learning rate sensitivity","score":0.6269999742507935},{"id":"https://openalex.org/keywords/sst-2","display_name":"SST-2","score":0.7609999775886536},{"id":"https://openalex.org/keywords/imdb","display_name":"IMDB","score":0.8209999799728394},{"id":"https://openalex.org/keywords/long-context-inference","display_name":"long-context inference","score":0.37700000405311584}],"concepts":[{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.7013999819755554},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6967999935150146},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.6305999755859375},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6184999942779541},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.47519999742507935},{"id":"https://openalex.org/C66402592","wikidata":"https://www.wikidata.org/wiki/Q2271421","display_name":"Sentiment analysis","level":2,"score":0.4510999917984009},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.43130001425743103},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.3968000113964081},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.3962000012397766},{"id":"https://openalex.org/C38976095","wikidata":"https://www.wikidata.org/wiki/Q752641","display_name":"Asymmetry","level":2,"score":0.37130001187324524},{"id":"https://openalex.org/C193244246","wikidata":"https://www.wikidata.org/wiki/Q5432696","display_name":"False discovery rate","level":3,"score":0.3028999865055084},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.2833000123500824},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.26510000228881836},{"id":"https://openalex.org/C44648626","wikidata":"https://www.wikidata.org/wiki/Q1049848","display_name":"Percentage point","level":2,"score":0.26249998807907104},{"id":"https://openalex.org/C113238511","wikidata":"https://www.wikidata.org/wiki/Q1071612","display_name":"k-nearest neighbors algorithm","level":2,"score":0.25429999828338623}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.3390/sym18111799","doi":"https://doi.org/10.3390/sym18111799","is_oa":true,"landing_page_url":"https://doi.org/10.3390/sym18111799","pdf_url":null,"source":{"id":"https://openalex.org/S190787756","display_name":"Symmetry","issn_l":"2073-8994","issn":["2073-8994"],"is_oa":true,"is_in_doaj":false,"is_core":true,"listed_in":["anvur-scientific","cwts-core","norway-1","poland-70","russia-white-list-1","vabb-shw"],"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Symmetry","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.3390/sym18111799","doi":"https://doi.org/10.3390/sym18111799","is_oa":true,"landing_page_url":"https://doi.org/10.3390/sym18111799","pdf_url":null,"source":{"id":"https://openalex.org/S190787756","display_name":"Symmetry","issn_l":"2073-8994","issn":["2073-8994"],"is_oa":true,"is_in_doaj":false,"is_core":true,"listed_in":["anvur-scientific","cwts-core","norway-1","poland-70","russia-white-list-1","vabb-shw"],"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Symmetry","raw_type":"journal-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W2251939518","https://openalex.org/W2963341956","https://openalex.org/W2980708516","https://openalex.org/W3152956381","https://openalex.org/W3174770825","https://openalex.org/W3176828726","https://openalex.org/W4289861361","https://openalex.org/W4313398738","https://openalex.org/W4385570815","https://openalex.org/W4402684255","https://openalex.org/W4405821455","https://openalex.org/W4411874165","https://openalex.org/W4412631112","https://openalex.org/W4416787740","https://openalex.org/W7125799258","https://openalex.org/W7128926801","https://openalex.org/W7133183334"],"related_works":["https://openalex.org/W4404782835","https://openalex.org/W7203761582","https://openalex.org/W7214189663","https://openalex.org/W4385570973","https://openalex.org/W7214143358","https://openalex.org/W4415310991","https://openalex.org/W7118007475","https://openalex.org/W4404932120","https://openalex.org/W7160261060","https://openalex.org/W4416364542"],"abstract_inverted_index":{"Parameter-efficient":[0],"fine-tuning":[1],"(PEFT)":[2],"reduces":[3],"adaptation":[4],"costs,":[5],"but":[6,84,151],"the":[7,70,126,133,148,167],"predictive":[8],"trade-offs":[9,182],"may":[10],"vary":[11],"across":[12],"datasets":[13,115],"and":[14,31,37,50,55,58,72,96,102,179],"encoder":[15],"backbones.":[16],"This":[17],"study":[18],"evaluated":[19],"Hybrid":[20,64,90,127],"Prefix\u2013Prompt":[21],"tuning":[22],"for":[23,104],"sentiment":[24],"classification":[25],"using":[26],"BERT-base-uncased":[27],"on":[28,94,98],"3000-example":[29],"training":[30,40,75],"500-example":[32],"held-out":[33,168],"subsets":[34],"of":[35,69],"SST-2":[36,95],"IMDb.":[38],"Five":[39],"seeds":[41],"supported":[42],"comparisons":[43],"with":[44],"full":[45,82,105],"fine-tuning,":[46,83],"LoRA,":[47],"adapters,":[48],"BitFit,":[49],"IA3;":[51],"independently":[52],"tuned":[53,144],"Prefix-only":[54],"Prompt-only":[56],"variants":[57],"targeted":[59],"diagnostics":[60,130],"were":[61],"analyzed":[62],"separately.":[63],"trained":[65],"311,810":[66],"parameters":[67],"(0.284%":[68],"model)":[71],"reduced":[73],"peak":[74],"GPU":[76],"memory":[77],"by":[78,110],"46.8%":[79],"relative":[80],"to":[81,139],"inference":[85],"was":[86,92,137],"slower.":[87],"The":[88,175],"mean":[89],"accuracy":[91,123],"86.44%":[93],"80.80%":[97],"IMDb,":[99],"versus":[100],"88.48%":[101],"86.56%":[103],"fine-tuning.":[106],"Seed-level":[107],"retention":[108,135],"differed":[109],"4.36":[111],"percentage":[112],"points":[113],"between":[114],"(95%":[116],"CI:":[117],"1.34\u20137.38).":[118],"Longer-context":[119],"IMDb":[120],"tests":[121],"improved":[122],"without":[124],"eliminating":[125],"deficit.":[128],"RoBERTa":[129],"suggested":[131],"that":[132],"reversed":[134,149],"ordering":[136],"sensitive":[138],"learning":[140],"rate":[141],"selection;":[142],"a":[143,155],"single-seed":[145],"check":[146],"retained":[147],"direction":[150],"did":[152,170],"not":[153,171],"establish":[154],"causal":[156],"backbone":[157],"interaction.":[158],"A":[159],"retrospective":[160],"restricted":[161],"validation":[162],"comparison":[163],"favored":[164],"Hybrid,":[165],"whereas":[166],"ablations":[169],"show":[172],"consistent":[173],"synergy.":[174],"results":[176],"underscore":[177],"dataset-":[178],"optimization-sensitive":[180],"accuracy\u2013efficiency":[181],"rather":[183],"than":[184],"universal":[185],"PEFT":[186],"superiority.":[187]},"counts_by_year":[],"updated_date":"2026-10-30T12:39:25.321706","created_date":"2026-10-29T00:00:00"}