{"id":"https://openalex.org/W7167439902","doi":null,"title":"Web Scraping e LLM: Confronto di metodologie per l\u2019estrazione di dati non strutturati da fonti eterogenee tramite Large Language Model","display_name":"Web Scraping e LLM: Confronto di metodologie per l\u2019estrazione di dati non strutturati da fonti eterogenee tramite Large Language Model","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7167439902"},"language":"it","primary_location":{"id":"pmh:oai:amslaurea.cib.unibo.it:39074","doi":null,"is_oa":true,"landing_page_url":"https://amslaurea.unibo.it/view/cds/CDS8009/>","pdf_url":"https://amslaurea.unibo.it/id/eprint/39074/1/tesi.pdf","source":{"id":"https://openalex.org/S4306400235","display_name":"AMS Degree Thesis (University of Bologna)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I9360294","host_organization_name":"University of Bologna","host_organization_lineage":["https://openalex.org/I9360294"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Tesi di laurea"},"volume":null,"type":"other","is_traditional":false,"indexed_in":[],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://amslaurea.unibo.it/id/eprint/39074/1/tesi.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5140083001","display_name":"Alessandro Amella","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Amella, Alessandro","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":["https://openalex.org/A5140083001"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":1.0,"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"}},"topics":[{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":1.0,"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"}},{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.0,"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/T13910","display_name":"Computational and Text Analysis Methods","score":0.0,"subfield":{"id":"https://openalex.org/subfields/3300","display_name":"General Social Sciences"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/web-scraping","display_name":"web scraping","score":0.8939999938011169},{"id":"https://openalex.org/keywords/large-language-models","display_name":"large language models","score":0.9940000176429749},{"id":"https://openalex.org/keywords/unstructured-data-extraction","display_name":"unstructured data extraction","score":0.824999988079071},{"id":"https://openalex.org/keywords/small-language-models","display_name":"small language models","score":0.796999990940094},{"id":"https://openalex.org/keywords/hallucination-mitigation","display_name":"hallucination mitigation","score":0.6499999761581421},{"id":"https://openalex.org/keywords/data-validation","display_name":"data validation","score":0.4429999887943268}],"concepts":[{"id":"https://openalex.org/C15708023","wikidata":"https://www.wikidata.org/wiki/Q80083","display_name":"Humanities","level":1,"score":0.6403999924659729},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.33809998631477356},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.3337000012397766},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.3203999996185303},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.25110000371932983},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.24130000174045563},{"id":"https://openalex.org/C58640448","wikidata":"https://www.wikidata.org/wiki/Q42515","display_name":"Cartography","level":1,"score":0.23659999668598175},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.21529999375343323},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.1915999948978424},{"id":"https://openalex.org/C3019813237","wikidata":"https://www.wikidata.org/wiki/Q65089264","display_name":"Model validation","level":2,"score":0.19050000607967377}],"mesh":[],"locations_count":1,"locations":[{"id":"pmh:oai:amslaurea.cib.unibo.it:39074","doi":null,"is_oa":true,"landing_page_url":"https://amslaurea.unibo.it/view/cds/CDS8009/>","pdf_url":"https://amslaurea.unibo.it/id/eprint/39074/1/tesi.pdf","source":{"id":"https://openalex.org/S4306400235","display_name":"AMS Degree Thesis (University of Bologna)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I9360294","host_organization_name":"University of Bologna","host_organization_lineage":["https://openalex.org/I9360294"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Tesi di laurea"}],"best_oa_location":{"id":"pmh:oai:amslaurea.cib.unibo.it:39074","doi":null,"is_oa":true,"landing_page_url":"https://amslaurea.unibo.it/view/cds/CDS8009/>","pdf_url":"https://amslaurea.unibo.it/id/eprint/39074/1/tesi.pdf","source":{"id":"https://openalex.org/S4306400235","display_name":"AMS Degree Thesis (University of Bologna)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I9360294","host_organization_name":"University of Bologna","host_organization_lineage":["https://openalex.org/I9360294"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Tesi di laurea"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7167439902.pdf","grobid_xml":"https://content.openalex.org/works/W7167439902.grobid-xml"},"referenced_works_count":10,"referenced_works":["https://openalex.org/W3030163527","https://openalex.org/W4309674289","https://openalex.org/W4386755313","https://openalex.org/W4389519585","https://openalex.org/W4399657570","https://openalex.org/W4414805766","https://openalex.org/W4415084305","https://openalex.org/W4416951121","https://openalex.org/W6891789863","https://openalex.org/W7123433410"],"related_works":["https://openalex.org/W4412603234","https://openalex.org/W7123433410","https://openalex.org/W7161114948","https://openalex.org/W7126264724","https://openalex.org/W4399657570","https://openalex.org/W4404782707","https://openalex.org/W7140977302","https://openalex.org/W7143350553","https://openalex.org/W7161110689","https://openalex.org/W7076963262"],"abstract_inverted_index":{"Il":[0],"web":[1,257],"scraping":[2,258],"tradizionale,":[3],"basato":[4],"su":[5,68],"regole":[6],"sintattiche,":[7],"\u00e8":[8],"intrinsecamente":[9],"fragile":[10,261],"alle":[11],"modifiche":[12],"strutturali":[13],"dei":[14,153],"siti":[15],"web.":[16],"I":[17,101],"Large":[18],"Language":[19,98],"Model":[20,99],"(LLM)":[21],"offrono":[22],"un":[23,59,69,130,145,161,208],"cambio":[24],"di":[25,61,73,88,118,177,220,224],"paradigma:":[26],"descrivere":[27],"alla":[28],"macchina":[29],"\"cosa\"":[30],"estrarre":[31],"anzich\u00e9":[32],"\"come\"":[33],"trovarlo.":[34],"L'IA":[35],"generativa":[36],"introduce":[37],"per\u00f2":[38],"nuove":[39],"sfide:":[40],"costi":[41,223],"operativi,":[42],"latenza":[43],"e":[44,66,90,226,244],"allucinazioni.":[45],"Questa":[46],"dissertazione":[47],"analizza":[48],"tali":[49],"trade-off":[50,210],"tramite":[51],"SWEET":[52],"(Semantic":[53],"Web":[54],"Extraction":[55],"&":[56],"Evaluation":[57],"Tool),":[58],"framework":[60],"benchmark":[62],"sviluppato":[63],"ad":[64],"hoc":[65],"testato":[67],"caso":[70],"reale":[71],"(avvisi":[72],"sciopero).":[74],"Si":[75],"valutano":[76],"accuratezza":[77],"(F1-score)":[78],"ed":[79],"efficienza":[80],"confrontando":[81],"modelli":[82,199],"(GPT,":[83],"Gemini,":[84],"Llama,":[85],"DeepSeek),":[86],"schemi":[87],"validazione":[89,152],"preprocessing,":[91],"dalle":[92],"euristiche":[93],"classiche":[94],"ai":[95],"recenti":[96],"Small":[97],"(SLM).":[100],"risultati":[102],"mostrano":[103],"che":[104,197,232],"l'uso":[105],"degli":[106,186,191,238,247],"SLM":[107],"per":[108],"il":[109,134,156,234,251,256],"preprocessing":[110],"garantisce":[111],"un'elevata":[112],"compressione":[113],"del":[114,142,179,213,227],"documento,":[115],"ma":[116,206,254],"rischia":[117],"omettere":[119],"metadati":[120],"rilevanti.":[121],"Su":[122],"fonti":[123],"semi-strutturate":[124],"a":[125,165,264],"struttura":[126],"relativamente":[127],"stabile":[128],"prevale":[129],"approccio":[131],"ibrido:":[132],"pre-filtrare":[133],"DOM":[135,180],"deterministicamente":[136],"riduce":[137,169],"i":[138,198],"token":[139],"in":[140],"input":[141],"99,5%,":[143],"mantenendo":[144],"F1-score":[146],"oltre":[147],"0,95.":[148],"Sul":[149],"fronte":[150],"della":[151],"dati,":[154],"alleggerire":[155],"carico":[157],"cognitivo":[158],"dell'IA":[159],"richiedendo":[160],"output":[162],"flessibile,":[163],"normalizzato":[164],"valle":[166],"via":[167],"codice,":[168],"le":[170],"allucinazioni":[171],"fino":[172],"al":[173,189,218],"45%.":[174],"Infine,":[175],"test":[176],"mutazione":[178],"(\"DOM":[181],"chaos\")":[182],"confermano":[183],"l'immunit\u00e0":[184],"strutturale":[185],"LLM":[187,248],"davanti":[188],"collasso":[190],"scraper":[192,239],"classici.":[193],"L'evidenza":[194],"sperimentale":[195],"dimostra":[196],"generativi":[200],"non":[201,249],"costituiscono":[202],"una":[203,260,265],"soluzione":[204],"universale,":[205],"impongono":[207],"nuovo":[209,228],"architetturale:":[211],"l'azzeramento":[212],"debito":[214],"tecnico":[215],"manutentivo":[216],"avviene":[217],"prezzo":[219],"maggiori":[221],"latenze,":[222],"inferenza":[225],"rischio":[229],"delle":[230],"allucinazioni,":[231],"sostituiscono":[233],"fallimento":[235],"esplicito":[236],"(fail-fast)":[237],"tradizionali":[240],"con":[241],"errori":[242],"subdoli":[243],"silenziosi.":[245],"L'uso":[246],"elimina":[250],"software":[252],"classico,":[253],"trasforma":[255],"da":[259],"ingegneria":[262],"sintattica":[263],"robusta":[266],"orchestrazione":[267],"semantica.":[268]},"counts_by_year":[],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2026-07-06T00:00:00"}