{"id":"https://openalex.org/W4408402807","doi":"https://doi.org/10.1145/3677389.3702591","title":"Can LLMs categorize the specialized documents from web archives in a better way?","display_name":"Can LLMs categorize the specialized documents from web archives in a better way?","publication_year":2024,"publication_date":"2024-12-16","ids":{"openalex":"https://openalex.org/W4408402807","doi":"https://doi.org/10.1145/3677389.3702591"},"language":"en","primary_location":{"id":"doi:10.1145/3677389.3702591","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3677389.3702591","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 24th ACM/IEEE Joint Conference on Digital Libraries","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5116608960","display_name":"Saran Pandian Pandi","orcid":"https://orcid.org/0000-0001-7110-8551"},"institutions":[{"id":"https://openalex.org/I39422238","display_name":"University of Illinois Chicago","ror":"https://ror.org/02mpq6x41","country_code":"US","type":"education","lineage":["https://openalex.org/I39422238"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Saran Pandian Pandi","raw_affiliation_strings":["Computer Science, University of Illinois at Chicago, Chicago, USA"],"raw_orcid":"https://orcid.org/0000-0001-7110-8551","affiliations":[{"raw_affiliation_string":"Computer Science, University of Illinois at Chicago, Chicago, USA","institution_ids":["https://openalex.org/I39422238"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113733457","display_name":"Seoyeon Park","orcid":"https://orcid.org/0009-0002-3611-3018"},"institutions":[{"id":"https://openalex.org/I4575257","display_name":"Hanyang University","ror":"https://ror.org/046865y68","country_code":"KR","type":"education","lineage":["https://openalex.org/I4575257"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Seoyeon Park","raw_affiliation_strings":["Hanyang University ERICA, Ansan, Republic of Korea"],"raw_orcid":"https://orcid.org/0009-0002-3611-3018","affiliations":[{"raw_affiliation_string":"Hanyang University ERICA, Ansan, Republic of Korea","institution_ids":["https://openalex.org/I4575257"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5116608961","display_name":"Praneeth Rikka","orcid":null},"institutions":[{"id":"https://openalex.org/I123534392","display_name":"University of North Texas","ror":"https://ror.org/00v97ad02","country_code":"US","type":"education","lineage":["https://openalex.org/I123534392"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Praneeth Rikka","raw_affiliation_strings":["University of North Texas, Denton, TX, USA"],"raw_orcid":"https://orcid.org/0009-0003-5079-4347","affiliations":[{"raw_affiliation_string":"University of North Texas, Denton, TX, USA","institution_ids":["https://openalex.org/I123534392"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064990515","display_name":"Mark Edward Phillips","orcid":"https://orcid.org/0000-0002-9679-6730"},"institutions":[{"id":"https://openalex.org/I123534392","display_name":"University of North Texas","ror":"https://ror.org/00v97ad02","country_code":"US","type":"education","lineage":["https://openalex.org/I123534392"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mark Edward Phillips","raw_affiliation_strings":["University Libraries, University of North Texas, Denton, TX, USA"],"raw_orcid":"https://orcid.org/0000-0002-9679-6730","affiliations":[{"raw_affiliation_string":"University Libraries, University of North Texas, Denton, TX, USA","institution_ids":["https://openalex.org/I123534392"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5089085275","display_name":"Cornelia Caragea","orcid":"https://orcid.org/0000-0002-5664-2163"},"institutions":[{"id":"https://openalex.org/I39422238","display_name":"University of Illinois Chicago","ror":"https://ror.org/02mpq6x41","country_code":"US","type":"education","lineage":["https://openalex.org/I39422238"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Cornelia Caragea","raw_affiliation_strings":["University of Illinois, Chicago, Chicago, IL, USA"],"raw_orcid":"https://orcid.org/0000-0002-5664-2163","affiliations":[{"raw_affiliation_string":"University of Illinois, Chicago, Chicago, IL, USA","institution_ids":["https://openalex.org/I39422238"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"11"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9972000122070312,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9972000122070312,"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/T14330","display_name":"Library Science and Information Systems","score":0.9868999719619751,"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/T12016","display_name":"Web Data Mining and Analysis","score":0.9804999828338623,"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/categorization","display_name":"Categorization","score":0.7933256030082703},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6870893239974976},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.5581842660903931},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4864756762981415},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.3904901444911957},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.1284201443195343}],"concepts":[{"id":"https://openalex.org/C94124525","wikidata":"https://www.wikidata.org/wiki/Q912550","display_name":"Categorization","level":2,"score":0.7933256030082703},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6870893239974976},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.5581842660903931},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4864756762981415},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.3904901444911957},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.1284201443195343}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3677389.3702591","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3677389.3702591","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 24th ACM/IEEE Joint Conference on Digital Libraries","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W1990321981","https://openalex.org/W2071085279","https://openalex.org/W2136348312","https://openalex.org/W2149684865","https://openalex.org/W2157748587","https://openalex.org/W2562691023","https://openalex.org/W2963042536","https://openalex.org/W2981852735","https://openalex.org/W3006210356","https://openalex.org/W3046234757","https://openalex.org/W4224308101","https://openalex.org/W4233402780","https://openalex.org/W4240777659","https://openalex.org/W4288089799","https://openalex.org/W6810081322"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2165912799","https://openalex.org/W2735662278","https://openalex.org/W2382615723","https://openalex.org/W4405331580","https://openalex.org/W4311804456","https://openalex.org/W1987484445","https://openalex.org/W2623658258"],"abstract_inverted_index":{"The":[0],"explosive":[1],"growth":[2],"of":[3,59,91,103,135],"web":[4,79],"archives":[5,80],"presents":[6],"a":[7],"significant":[8,101],"challenge:":[9],"manually":[10],"curating":[11],"specialized":[12,76,138,153],"document":[13,112],"collections":[14],"from":[15,78],"this":[16],"vast":[17],"data.":[18],"Existing":[19],"approaches":[20],"rely":[21],"on":[22,48,143],"supervised":[23],"techniques,":[24],"but":[25],"recent":[26],"advancements":[27],"in":[28,62],"Large":[29,40],"Language":[30,41],"Models":[31,42],"(LLMs)":[32,43],"offer":[33],"new":[34],"possibilities":[35],"for":[36,74,116,137,151],"automating":[37,152],"collection":[38,154],"creation.":[39],"are":[44],"demonstrating":[45],"impressive":[46],"performance":[47,90],"various":[49,94],"tasks":[50],"even":[51],"without":[52],"fine-tuning.":[53,145],"This":[54,125,146],"paper":[55],"investigates":[56],"the":[57,89,100,111,117,133,149],"effectiveness":[58],"prompt":[60,95,159],"design":[61],"achieving":[63],"results":[64],"comparable":[65],"to":[66,121],"fine-tuned":[67],"models.":[68],"We":[69,86],"explore":[70],"different":[71],"prompting":[72],"techniques":[73],"collecting":[75],"documents":[77],"like":[81],"UNT.edu,":[82],"Michigan.gov,":[83],"and":[84,158],"Texas.gov.":[85],"then":[87],"analyze":[88],"LLMs":[92,136,157],"under":[93],"configurations.":[96],"Our":[97],"findings":[98],"highlight":[99],"impact":[102],"incorporating":[104],"task":[105],"descriptions":[106],"within":[107],"prompts.":[108],"Additionally,":[109],"including":[110],"type":[113],"as":[114],"justification":[115],"search":[118],"scope":[119],"leads":[120],"demonstrably":[122],"better":[123],"results.":[124],"research":[126,147],"suggests":[127],"that":[128],"well-crafted":[129],"prompts":[130],"can":[131],"unlock":[132],"potential":[134],"tasks,":[139],"potentially":[140],"reducing":[141],"reliance":[142],"resource-intensive":[144],"paves":[148],"way":[150],"creation":[155],"using":[156],"engineering.":[160]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}