{"id":"https://openalex.org/W2546429065","doi":"https://doi.org/10.1145/2908446.2908494","title":"Keyphrase-Based Hierarchical Clustering for Arabic Documents","display_name":"Keyphrase-Based Hierarchical Clustering for Arabic Documents","publication_year":2016,"publication_date":"2016-05-09","ids":{"openalex":"https://openalex.org/W2546429065","doi":"https://doi.org/10.1145/2908446.2908494","mag":"2546429065"},"language":"en","primary_location":{"id":"doi:10.1145/2908446.2908494","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2908446.2908494","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 10th International Conference on Informatics and Systems","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/A5004003646","display_name":"Moufeda Hussein","orcid":null},"institutions":[{"id":"https://openalex.org/I207547235","display_name":"Benha University","ror":"https://ror.org/03tn5ee41","country_code":"EG","type":"education","lineage":["https://openalex.org/I207547235"]}],"countries":["EG"],"is_corresponding":true,"raw_author_name":"Moufeda Hussein","raw_affiliation_strings":["Faculty of Engineering Shoubra, Benha University, Egypt"],"affiliations":[{"raw_affiliation_string":"Faculty of Engineering Shoubra, Benha University, Egypt","institution_ids":["https://openalex.org/I207547235"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028613257","display_name":"Abdelwahab Alsammak","orcid":null},"institutions":[{"id":"https://openalex.org/I207547235","display_name":"Benha University","ror":"https://ror.org/03tn5ee41","country_code":"EG","type":"education","lineage":["https://openalex.org/I207547235"]}],"countries":["EG"],"is_corresponding":false,"raw_author_name":"Abdelwahab Alsammak","raw_affiliation_strings":["Faculty of Engineering Shoubra, Benha University, Egypt"],"affiliations":[{"raw_affiliation_string":"Faculty of Engineering Shoubra, Benha University, Egypt","institution_ids":["https://openalex.org/I207547235"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5013119283","display_name":"Tarek El\u2010Shishtawy","orcid":null},"institutions":[{"id":"https://openalex.org/I207547235","display_name":"Benha University","ror":"https://ror.org/03tn5ee41","country_code":"EG","type":"education","lineage":["https://openalex.org/I207547235"]}],"countries":["EG"],"is_corresponding":false,"raw_author_name":"Tarek Elshishtawy","raw_affiliation_strings":["Faculty of Computers and Informatics, Benha University, Egypt"],"affiliations":[{"raw_affiliation_string":"Faculty of Computers and Informatics, Benha University, Egypt","institution_ids":["https://openalex.org/I207547235"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5004003646"],"corresponding_institution_ids":["https://openalex.org/I207547235"],"apc_list":null,"apc_paid":null,"fwci":0.4285,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.79409677,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"61","last_page":"67"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13083","display_name":"Advanced Text Analysis Techniques","score":0.9994000196456909,"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":0.9994000196456909,"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":0.977400004863739,"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/T13976","display_name":"Web visibility and informetrics","score":0.906000018119812,"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":0.8310343623161316},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.7294744253158569},{"id":"https://openalex.org/keywords/document-clustering","display_name":"Document clustering","score":0.5821570158004761},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.5505427122116089},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5344853401184082},{"id":"https://openalex.org/keywords/hierarchical-clustering","display_name":"Hierarchical clustering","score":0.49105405807495117},{"id":"https://openalex.org/keywords/edit-distance","display_name":"Edit distance","score":0.45521068572998047},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.44494181871414185},{"id":"https://openalex.org/keywords/fuzzy-clustering","display_name":"Fuzzy clustering","score":0.4339870810508728},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3592923879623413}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8310343623161316},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.7294744253158569},{"id":"https://openalex.org/C177937566","wikidata":"https://www.wikidata.org/wiki/Q4223102","display_name":"Document clustering","level":3,"score":0.5821570158004761},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.5505427122116089},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5344853401184082},{"id":"https://openalex.org/C92835128","wikidata":"https://www.wikidata.org/wiki/Q1277447","display_name":"Hierarchical clustering","level":3,"score":0.49105405807495117},{"id":"https://openalex.org/C44359876","wikidata":"https://www.wikidata.org/wiki/Q5338467","display_name":"Edit distance","level":2,"score":0.45521068572998047},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.44494181871414185},{"id":"https://openalex.org/C17212007","wikidata":"https://www.wikidata.org/wiki/Q5511111","display_name":"Fuzzy clustering","level":3,"score":0.4339870810508728},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3592923879623413},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2908446.2908494","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2908446.2908494","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 10th International Conference on Informatics and Systems","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.47999998927116394}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W1493454437","https://openalex.org/W1537816770","https://openalex.org/W1546602224","https://openalex.org/W1549301962","https://openalex.org/W1651093245","https://openalex.org/W1985937121","https://openalex.org/W1992419399","https://openalex.org/W2038413887","https://openalex.org/W2039346806","https://openalex.org/W2087216833","https://openalex.org/W2102381086","https://openalex.org/W2116702211","https://openalex.org/W2136480620","https://openalex.org/W2155194165","https://openalex.org/W2171313960","https://openalex.org/W2181909559","https://openalex.org/W2182446375","https://openalex.org/W2184757518","https://openalex.org/W2188347037","https://openalex.org/W2531621976","https://openalex.org/W2779285644","https://openalex.org/W2999729612","https://openalex.org/W3101604175","https://openalex.org/W4205753921","https://openalex.org/W4285719527","https://openalex.org/W6686068108","https://openalex.org/W6687181900"],"related_works":["https://openalex.org/W4237492828","https://openalex.org/W78181647","https://openalex.org/W4231226332","https://openalex.org/W2049508213","https://openalex.org/W2130194910","https://openalex.org/W3214871334","https://openalex.org/W2189374779","https://openalex.org/W2605148547","https://openalex.org/W2016788389","https://openalex.org/W2378900857"],"abstract_inverted_index":{"The":[0,61,145,164],"vast":[1],"amount":[2],"of":[3,67,70,98,104,120,132],"available":[4],"Arabic":[5,134],"web":[6],"pages":[7],"and":[8,125,136],"text":[9],"files":[10],"on":[11],"the":[12,65,90,102,105,118,175],"internet":[13],"makes":[14],"it":[15],"necessary":[16],"to":[17,116],"organize":[18],"data":[19,39],"in":[20,142],"an":[21],"easy":[22],"way":[23],"for":[24,33],"user":[25],"browsing.":[26],"Document":[27],"clustering":[28,59,106,121],"is":[29,140,169,172],"a":[30,50,56,84],"good":[31],"solution":[32],"this":[34,46],"problem,":[35],"which":[36,54,171],"groups":[37],"similar":[38],"into":[40],"clusters":[41,158],"with":[42,77,108],"meaningful":[43,58],"labels.":[44],"In":[45,80],"paper,":[47],"we":[48,82],"propose":[49],"domain":[51],"independent":[52],"approach,":[53],"builds":[55],"hierarchical":[57],"tree.":[60],"proposed":[62],"approach":[63],"overcomes":[64],"problem":[66],"high":[68],"dimensionality":[69],"feature":[71,96],"vector":[72],"by":[73,88],"representing":[74],"each":[75],"document":[76],"its":[78],"keyphrases.":[79],"addition,":[81],"introduced":[83],"new":[85],"similarity":[86,127,151,180],"measure":[87],"taking":[89],"common":[91,176],"lemma":[92,177],"form":[93,178],"keyphrases":[94,179],"among":[95],"vectors":[97],"documents.":[99],"This":[100],"improves":[101],"accuracy":[103,119],"process":[107],"reduced":[109],"complexity.":[110],"Many":[111],"experiments":[112],"are":[113],"carried":[114],"out":[115],"evaluate":[117],"using":[122,152,161,174],"String-based,":[123],"Corpus-based,":[124],"Knowledge-based":[126],"measures.":[128],"A":[129],"dataset":[130],"consists":[131],"345":[133],"documents":[135],"covering":[137],"12":[138],"domains":[139],"used":[141],"these":[143],"experiments.":[144],"results":[146],"show":[147],"that":[148],"applying":[149],"lexical":[150],"keyphrase":[153],"based":[154],"gives":[155],"more":[156],"accurate":[157],"labels":[159],"than":[160],"semantic":[162],"similarity.":[163],"best":[165],"purity":[166],"result":[167],"achieved":[168],"0.955,":[170],"obtained":[173],"method.":[181]},"counts_by_year":[{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2018,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}