{"id":"https://openalex.org/W4413757112","doi":"https://doi.org/10.1145/3704268.3742691","title":"SoAC and SoACer: A Sector-Based Corpus and LLM-Based Framework for Sectoral Website Classification","display_name":"SoAC and SoACer: A Sector-Based Corpus and LLM-Based Framework for Sectoral Website Classification","publication_year":2025,"publication_date":"2025-08-27","ids":{"openalex":"https://openalex.org/W4413757112","doi":"https://doi.org/10.1145/3704268.3742691"},"language":"en","primary_location":{"id":"doi:10.1145/3704268.3742691","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3704268.3742691","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3704268.3742691","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2025 ACM Symposium on Document Engineering","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3704268.3742691","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5119451222","display_name":"Shahriar Shayesteh","orcid":null},"institutions":[{"id":"https://openalex.org/I130769515","display_name":"Pennsylvania State University","ror":"https://ror.org/04p491231","country_code":"US","type":"education","lineage":["https://openalex.org/I130769515"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Shahriar Shayesteh","raw_affiliation_strings":["Pennsylvania State University"],"affiliations":[{"raw_affiliation_string":"Pennsylvania State University","institution_ids":["https://openalex.org/I130769515"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086032910","display_name":"Mukund Srinath","orcid":"https://orcid.org/0009-0007-6474-8199"},"institutions":[{"id":"https://openalex.org/I130769515","display_name":"Pennsylvania State University","ror":"https://ror.org/04p491231","country_code":"US","type":"education","lineage":["https://openalex.org/I130769515"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mukund Srinath","raw_affiliation_strings":["Pennsylvania State University"],"affiliations":[{"raw_affiliation_string":"Pennsylvania State University","institution_ids":["https://openalex.org/I130769515"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008787208","display_name":"Lee Matheson","orcid":"https://orcid.org/0009-0007-5639-8379"},"institutions":[{"id":"https://openalex.org/I2799790188","display_name":"Future of Privacy Forum","ror":"https://ror.org/03772c153","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I2799790188"]},{"id":"https://openalex.org/I4210123919","display_name":"Forum for the Future","ror":"https://ror.org/02w38qn81","country_code":"GB","type":"nonprofit","lineage":["https://openalex.org/I4210123919"]}],"countries":["GB","US"],"is_corresponding":false,"raw_author_name":"Lee Matheson","raw_affiliation_strings":["Future of Privacy Forum"],"affiliations":[{"raw_affiliation_string":"Future of Privacy Forum","institution_ids":["https://openalex.org/I4210123919","https://openalex.org/I2799790188"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071264724","display_name":"Lu Xian","orcid":"https://orcid.org/0000-0001-8120-1012"},"institutions":[{"id":"https://openalex.org/I27837315","display_name":"University of Michigan","ror":"https://ror.org/00jmfr291","country_code":"US","type":"education","lineage":["https://openalex.org/I27837315"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Lu Xian","raw_affiliation_strings":["University of Michigan"],"affiliations":[{"raw_affiliation_string":"University of Michigan","institution_ids":["https://openalex.org/I27837315"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102816449","display_name":"Sinjoy Saha","orcid":"https://orcid.org/0000-0001-5165-1602"},"institutions":[{"id":"https://openalex.org/I130769515","display_name":"Pennsylvania State University","ror":"https://ror.org/04p491231","country_code":"US","type":"education","lineage":["https://openalex.org/I130769515"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sinjoy Saha","raw_affiliation_strings":["Pennsylvania State University"],"affiliations":[{"raw_affiliation_string":"Pennsylvania State University","institution_ids":["https://openalex.org/I130769515"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001294898","display_name":"C. Lee Giles","orcid":"https://orcid.org/0000-0002-1931-585X"},"institutions":[{"id":"https://openalex.org/I130769515","display_name":"Pennsylvania State University","ror":"https://ror.org/04p491231","country_code":"US","type":"education","lineage":["https://openalex.org/I130769515"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"C. Lee Giles","raw_affiliation_strings":["Pennsylvania State University"],"affiliations":[{"raw_affiliation_string":"Pennsylvania State University","institution_ids":["https://openalex.org/I130769515"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5056978982","display_name":"Shomir Wilson","orcid":"https://orcid.org/0000-0003-1235-3754"},"institutions":[{"id":"https://openalex.org/I130769515","display_name":"Pennsylvania State University","ror":"https://ror.org/04p491231","country_code":"US","type":"education","lineage":["https://openalex.org/I130769515"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shomir Wilson","raw_affiliation_strings":["Pennsylvania State University"],"affiliations":[{"raw_affiliation_string":"Pennsylvania State University","institution_ids":["https://openalex.org/I130769515"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5119451222"],"corresponding_institution_ids":["https://openalex.org/I130769515"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.11707732,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"10"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11550","display_name":"Text and Document Classification Technologies","score":0.9976999759674072,"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/T11550","display_name":"Text and Document Classification Technologies","score":0.9976999759674072,"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/T12016","display_name":"Web Data Mining and Analysis","score":0.9976000189781189,"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/T11644","display_name":"Spam and Phishing Detection","score":0.9952999949455261,"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/computer-science","display_name":"Computer science","score":0.7020678520202637},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.4118228554725647},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.37365907430648804},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3664305508136749}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7020678520202637},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.4118228554725647},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.37365907430648804},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3664305508136749}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3704268.3742691","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3704268.3742691","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3704268.3742691","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2025 ACM Symposium on Document Engineering","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3704268.3742691","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3704268.3742691","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3704268.3742691","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2025 ACM Symposium on Document Engineering","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4413757112.pdf","grobid_xml":"https://content.openalex.org/works/W4413757112.grobid-xml"},"referenced_works_count":22,"referenced_works":["https://openalex.org/W1882783948","https://openalex.org/W1973690672","https://openalex.org/W1989338554","https://openalex.org/W2011265791","https://openalex.org/W2013316690","https://openalex.org/W2059586463","https://openalex.org/W2064675550","https://openalex.org/W2065168033","https://openalex.org/W2076568317","https://openalex.org/W2094400120","https://openalex.org/W2110693578","https://openalex.org/W2294675754","https://openalex.org/W2946007318","https://openalex.org/W2963341956","https://openalex.org/W2973291199","https://openalex.org/W3045037176","https://openalex.org/W3199704950","https://openalex.org/W4285185565","https://openalex.org/W4385625610","https://openalex.org/W4401042388","https://openalex.org/W4402671665","https://openalex.org/W4412886823"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"One":[0],"approach":[1],"to":[2,12,35,124,148],"understanding":[3],"the":[4,9,19,37,59,91,205,229],"vastness":[5],"and":[6,40,46,127,134,159,209],"complexity":[7],"of":[8,43,69,101,171,222,232],"web":[10,44,86],"is":[11,109],"categorize":[13],"websites":[14,78],"into":[15,80,130],"sectors":[16,83],"that":[17,115,165,182,203,226],"reflect":[18],"specific":[20],"industries":[21],"or":[22],"domains":[23],"in":[24],"which":[25,88],"they":[26],"operate.":[27],"However,":[28],"existing":[29],"website":[30,118,234],"classification":[31,53,97,113,146,193,211,224],"approaches":[32],"often":[33],"struggle":[34],"handle":[36],"noisy,":[38],"unstructured,":[39],"lengthy":[41,128],"nature":[42,231],"content,":[45,87],"current":[47],"datasets":[48],"lack":[49],"a":[50,72,110,131,145,216],"universal":[51],"sector":[52,201],"labeling":[54],"system":[55],"specifically":[56],"designed":[57],"for":[58,85,93,207,219],"web.":[60],"To":[61],"address":[62],"these":[63],"issues,":[64],"we":[65,163],"introduce":[66],"SoAC":[67,176],"(Sector":[68,100],"Activity":[70,102],"Corpus),":[71],"large-scale":[73],"corpus":[74],"comprising":[75],"195,":[76],"495":[77],"categorized":[79],"10":[81],"broad":[82],"tailored":[84],"serves":[89],"as":[90],"benchmark":[92],"evaluating":[94],"our":[95,174,196],"proposed":[96,175],"framework,":[98],"SoACer":[99,108,166],"Classifier).":[103],"Building":[104],"on":[105,173],"this":[106],"resource,":[107],"novel":[111],"end-to-end":[112],"framework":[114],"first":[116],"fetches":[117],"information,":[119],"then":[120],"incorporates":[121],"extractive":[122,183],"summarization":[123,184],"condense":[125],"noisy":[126],"content":[129],"concise":[132],"representation,":[133],"finally":[135],"employs":[136],"large":[137],"language":[138],"model":[139],"(LLM)":[140],"embeddings":[141],"(Llama3-8B)":[142],"combined":[143],"with":[144],"head":[147],"achieve":[149],"accurate":[150],"sectoral":[151],"prediction.":[152],"Through":[153],"extensive":[154],"experiments,":[155],"including":[156],"ablation":[157,179],"studies":[158],"detailed":[160],"error":[161,197],"analysis,":[162],"demonstrate":[164],"achieves":[167],"an":[168],"overall":[169],"accuracy":[170],"72.6%":[172],"dataset.":[177],"Our":[178],"study":[180],"confirms":[181],"not":[185],"only":[186],"reduces":[187],"computational":[188],"overhead":[189],"but":[190],"also":[191],"enhances":[192],"performance,":[194],"while":[195],"analysis":[198],"reveals":[199],"meaningful":[200],"overlaps":[202],"underscore":[204],"need":[206],"multi-label":[208],"hierarchical":[210],"frameworks.":[212],"These":[213],"findings":[214],"provide":[215],"robust":[217],"foundation":[218],"future":[220],"exploration":[221],"advanced":[223],"techniques":[225],"better":[227],"capture":[228],"complex":[230],"modern":[233],"content.1":[235]},"counts_by_year":[],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}