{"id":"https://openalex.org/W3211716956","doi":"https://doi.org/10.1145/3444757.3485078","title":"Unsupervised Topical Organization of Documents using Corpus-based Text Analysis","display_name":"Unsupervised Topical Organization of Documents using Corpus-based Text Analysis","publication_year":2021,"publication_date":"2021-11-01","ids":{"openalex":"https://openalex.org/W3211716956","doi":"https://doi.org/10.1145/3444757.3485078","mag":"3211716956"},"language":"en","primary_location":{"id":"doi:10.1145/3444757.3485078","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3444757.3485078","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 13th International Conference on Management of Digital EcoSystems","raw_type":"proceedings-article"},"type":"article","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/A5061050438","display_name":"Sarkis Sarkissian","orcid":null},"institutions":[{"id":"https://openalex.org/I56306041","display_name":"Lebanese American University","ror":"https://ror.org/00hqkan37","country_code":"LB","type":"education","lineage":["https://openalex.org/I56306041"]}],"countries":["LB"],"is_corresponding":true,"raw_author_name":"Sarkis Sarkissian","raw_affiliation_strings":["School of Engineering, Dept. of Elec. and Compt. Eng. Lebanese American University, Byblos, Lebanon"],"affiliations":[{"raw_affiliation_string":"School of Engineering, Dept. of Elec. and Compt. Eng. Lebanese American University, Byblos, Lebanon","institution_ids":["https://openalex.org/I56306041"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5088417940","display_name":"Joe Tekli","orcid":"https://orcid.org/0000-0003-3441-7974"},"institutions":[{"id":"https://openalex.org/I56306041","display_name":"Lebanese American University","ror":"https://ror.org/00hqkan37","country_code":"LB","type":"education","lineage":["https://openalex.org/I56306041"]}],"countries":["LB"],"is_corresponding":false,"raw_author_name":"Joe Tekli","raw_affiliation_strings":["School of Engineering, Dept. of Elec. and Compt. Eng. Lebanese American University, Byblos, Lebanon"],"affiliations":[{"raw_affiliation_string":"School of Engineering, Dept. of Elec. and Compt. Eng. Lebanese American University, Byblos, Lebanon","institution_ids":["https://openalex.org/I56306041"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5061050438"],"corresponding_institution_ids":["https://openalex.org/I56306041"],"apc_list":null,"apc_paid":null,"fwci":0.8158,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.78687587,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"87","last_page":"94"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13083","display_name":"Advanced Text Analysis Techniques","score":0.9994999766349792,"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/T13083","display_name":"Advanced Text Analysis Techniques","score":0.9994999766349792,"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/T11550","display_name":"Text and Document Classification Technologies","score":0.9988999962806702,"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":0.9968000054359436,"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/computer-science","display_name":"Computer science","score":0.8571595549583435},{"id":"https://openalex.org/keywords/keyword-extraction","display_name":"Keyword extraction","score":0.6756784915924072},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.6488127708435059},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.6426974534988403},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.6411086320877075},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.6234720349311829},{"id":"https://openalex.org/keywords/document-clustering","display_name":"Document clustering","score":0.5894736051559448},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5733189582824707},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.543570339679718},{"id":"https://openalex.org/keywords/thesaurus","display_name":"Thesaurus","score":0.527582049369812},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5150849223136902},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4957447946071625},{"id":"https://openalex.org/keywords/document-classification","display_name":"Document classification","score":0.4402986466884613},{"id":"https://openalex.org/keywords/hierarchical-clustering","display_name":"Hierarchical clustering","score":0.4374723732471466},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.4299662113189697}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8571595549583435},{"id":"https://openalex.org/C2780288562","wikidata":"https://www.wikidata.org/wiki/Q25053353","display_name":"Keyword extraction","level":2,"score":0.6756784915924072},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.6488127708435059},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.6426974534988403},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.6411086320877075},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.6234720349311829},{"id":"https://openalex.org/C177937566","wikidata":"https://www.wikidata.org/wiki/Q4223102","display_name":"Document clustering","level":3,"score":0.5894736051559448},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5733189582824707},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.543570339679718},{"id":"https://openalex.org/C2778698081","wikidata":"https://www.wikidata.org/wiki/Q179797","display_name":"Thesaurus","level":2,"score":0.527582049369812},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5150849223136902},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4957447946071625},{"id":"https://openalex.org/C2780479914","wikidata":"https://www.wikidata.org/wiki/Q302088","display_name":"Document classification","level":2,"score":0.4402986466884613},{"id":"https://openalex.org/C92835128","wikidata":"https://www.wikidata.org/wiki/Q1277447","display_name":"Hierarchical clustering","level":3,"score":0.4374723732471466},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.4299662113189697},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3444757.3485078","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3444757.3485078","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 13th International Conference on Management of Digital EcoSystems","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W73128518","https://openalex.org/W108464071","https://openalex.org/W326125486","https://openalex.org/W1963889129","https://openalex.org/W1965610470","https://openalex.org/W1965657730","https://openalex.org/W1966907789","https://openalex.org/W1978394996","https://openalex.org/W1990200782","https://openalex.org/W2033525209","https://openalex.org/W2046144220","https://openalex.org/W2063555110","https://openalex.org/W2082695069","https://openalex.org/W2085529678","https://openalex.org/W2105157020","https://openalex.org/W2136729221","https://openalex.org/W2147152072","https://openalex.org/W2150839534","https://openalex.org/W2475415301","https://openalex.org/W2808251711","https://openalex.org/W2886829956","https://openalex.org/W2900598933","https://openalex.org/W3003570628","https://openalex.org/W3018251256"],"related_works":["https://openalex.org/W4234578264","https://openalex.org/W4237492828","https://openalex.org/W2025763381","https://openalex.org/W78181647","https://openalex.org/W1487724385","https://openalex.org/W2130194910","https://openalex.org/W3046994506","https://openalex.org/W2189374779","https://openalex.org/W2538371562","https://openalex.org/W2045631426"],"abstract_inverted_index":{"This":[0],"study":[1],"aims":[2],"at":[3],"automating":[4],"the":[5,24,49,56,71,126,170,177,182],"process":[6,143],"of":[7,11,13,26,48,91,100,147,166,181],"topical":[8,155],"keyword":[9,43,158],"organization":[10,156],"set":[12,47],"documents":[14,102,167],"in":[15,23,76],"an":[16,81],"input":[17,88,107],"text":[18,93],"corpus.":[19,131],"It":[20],"is":[21],"conducted":[22],"context":[25],"a":[27,46,89,121,129,140,162],"larger":[28],"project":[29],"to":[30,36,58,63,144],"investigate":[31],"efficient":[32],"unsupervised":[33,82],"learning":[34],"techniques":[35],"automatically":[37],"extract":[38],"relevant":[39],"classes":[40,73],"and":[41,54,78,95,116,157,179],"their":[42],"descriptions":[44],"from":[45,120],"United":[50],"Nations":[51],"(UN)":[52],"documents,":[53,94,149],"use":[55],"latter":[57],"produce":[59],"reference":[60,72],"corpora":[61],"allowing":[62],"classify":[64],"future":[65],"UN":[66],"documents.":[67],"We":[68],"assume":[69],"that":[70],"are":[74,111,136],"unknown":[75],"advance,":[77],"thus":[79],"suggest":[80],"clustering":[83,142],"approach":[84],"which":[85,150],"accepts":[86],"as":[87,97,152],"bunch":[90],"unstructured":[92],"produces":[96],"output":[98],"groups":[99,146],"similar":[101,104,148],"describing":[103],"topics.":[105],"The":[106,132],"document":[108],"feature":[109,134],"vectors":[110,135],"augmented":[112,133],"with":[113],"term":[114],"co-occurrence":[115],"relatedness":[117],"scores":[118],"produced":[119],"distributional":[122],"thesaurus":[123],"built":[124],"on":[125,161],"same":[127],"(or":[128],"related)":[130],"then":[137],"run":[138],"through":[139],"hierarchical":[141],"identify":[145],"serve":[151],"candidates":[153],"for":[154],"extraction.":[159],"Experiments":[160],"manually":[163],"labelled":[164],"dataset":[165],"classified":[168],"against":[169],"UN's":[171],"Sustainable":[172],"Development":[173],"Goals":[174],"(SDGs)":[175],"confirm":[176],"quality":[178],"potential":[180],"approach.":[183]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}