{"id":"https://openalex.org/W2975262101","doi":"https://doi.org/10.1109/icdim.2018.8847156","title":"Improved TFIDF weighting techniques in document Retrieval","display_name":"Improved TFIDF weighting techniques in document Retrieval","publication_year":2018,"publication_date":"2018-09-01","ids":{"openalex":"https://openalex.org/W2975262101","doi":"https://doi.org/10.1109/icdim.2018.8847156","mag":"2975262101"},"language":"en","primary_location":{"id":"doi:10.1109/icdim.2018.8847156","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icdim.2018.8847156","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 Thirteenth International Conference on Digital Information Management (ICDIM)","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/A5022547940","display_name":"Fadi Yamout","orcid":null},"institutions":[{"id":"https://openalex.org/I911468752","display_name":"Lebanese International University","ror":"https://ror.org/034agrd14","country_code":"LB","type":"education","lineage":["https://openalex.org/I911468752"]}],"countries":["LB"],"is_corresponding":true,"raw_author_name":"Fadi Yamout","raw_affiliation_strings":["Computer Science, Lebanese International University, Beirut, Lebanon"],"affiliations":[{"raw_affiliation_string":"Computer Science, Lebanese International University, Beirut, Lebanon","institution_ids":["https://openalex.org/I911468752"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5090856922","display_name":"Rachad Lakkis","orcid":null},"institutions":[{"id":"https://openalex.org/I911468752","display_name":"Lebanese International University","ror":"https://ror.org/034agrd14","country_code":"LB","type":"education","lineage":["https://openalex.org/I911468752"]}],"countries":["LB"],"is_corresponding":false,"raw_author_name":"Rachad Lakkis","raw_affiliation_strings":["Computer Science, Lebanese International University, Beirut, Lebanon"],"affiliations":[{"raw_affiliation_string":"Computer Science, Lebanese International University, Beirut, Lebanon","institution_ids":["https://openalex.org/I911468752"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5022547940"],"corresponding_institution_ids":["https://openalex.org/I911468752"],"apc_list":null,"apc_paid":null,"fwci":1.1846,"has_fulltext":false,"cited_by_count":13,"citation_normalized_percentile":{"value":0.85170695,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"69","last_page":"73"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13083","display_name":"Advanced Text Analysis Techniques","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/T13083","display_name":"Advanced Text Analysis Techniques","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/T10286","display_name":"Information Retrieval and Search Behavior","score":0.9973000288009644,"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/T11550","display_name":"Text and Document Classification Technologies","score":0.9965000152587891,"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/tf\u2013idf","display_name":"tf\u2013idf","score":0.9704338312149048},{"id":"https://openalex.org/keywords/weighting","display_name":"Weighting","score":0.8519635200500488},{"id":"https://openalex.org/keywords/vector-space-model","display_name":"Vector space model","score":0.783325731754303},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7130318880081177},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.6877487897872925},{"id":"https://openalex.org/keywords/document-retrieval","display_name":"Document retrieval","score":0.6096625924110413},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5565565824508667},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.5129765868186951},{"id":"https://openalex.org/keywords/term","display_name":"Term (time)","score":0.4693725109100342},{"id":"https://openalex.org/keywords/document-classification","display_name":"Document classification","score":0.42796677350997925},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4150884747505188},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.38744497299194336},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1792377233505249},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.15378770232200623}],"concepts":[{"id":"https://openalex.org/C81758059","wikidata":"https://www.wikidata.org/wiki/Q796584","display_name":"tf\u2013idf","level":3,"score":0.9704338312149048},{"id":"https://openalex.org/C183115368","wikidata":"https://www.wikidata.org/wiki/Q856577","display_name":"Weighting","level":2,"score":0.8519635200500488},{"id":"https://openalex.org/C89686163","wikidata":"https://www.wikidata.org/wiki/Q1187982","display_name":"Vector space model","level":2,"score":0.783325731754303},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7130318880081177},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.6877487897872925},{"id":"https://openalex.org/C161156560","wikidata":"https://www.wikidata.org/wiki/Q1638872","display_name":"Document retrieval","level":2,"score":0.6096625924110413},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5565565824508667},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.5129765868186951},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.4693725109100342},{"id":"https://openalex.org/C2780479914","wikidata":"https://www.wikidata.org/wiki/Q302088","display_name":"Document classification","level":2,"score":0.42796677350997925},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4150884747505188},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.38744497299194336},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1792377233505249},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.15378770232200623},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C126838900","wikidata":"https://www.wikidata.org/wiki/Q77604","display_name":"Radiology","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icdim.2018.8847156","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icdim.2018.8847156","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 Thirteenth International Conference on Digital Information Management (ICDIM)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.5400000214576721,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":9,"referenced_works":["https://openalex.org/W1560138630","https://openalex.org/W1584533718","https://openalex.org/W1602667807","https://openalex.org/W1660390307","https://openalex.org/W2031302834","https://openalex.org/W2095683564","https://openalex.org/W2510561604","https://openalex.org/W2605889996","https://openalex.org/W6634872676"],"related_works":["https://openalex.org/W2549551998","https://openalex.org/W3036265557","https://openalex.org/W2900987978","https://openalex.org/W4281569536","https://openalex.org/W2349205074","https://openalex.org/W2171473894","https://openalex.org/W2975262101","https://openalex.org/W3028990185","https://openalex.org/W2154282042","https://openalex.org/W2035503345"],"abstract_inverted_index":{"In":[0,64],"information":[1,31],"retrieval,":[2],"documents":[3,175],"are":[4,41,49,108],"usually":[5],"retrieved":[6,177],"using":[7,52],"lexical":[8],"matching":[9],"which":[10,89,126,152],"matches":[11],"where":[12,38],"words":[13,19,40,95,107,112,132,161],"in":[14,21,30,46,97,114,134,162,178],"a":[15,22,44,53,163],"user's":[16],"query":[17],"with":[18],"found":[20,113,133,172],"set":[23],"of":[24,99,157],"documents.":[25],"A":[26],"significant":[27,110],"model":[28,37],"used":[29],"retrieval":[32],"is":[33,83,120,144],"the":[34,76,94,100,131,135,155,158,167],"vector":[35,45],"space":[36,47],"these":[39],"represented":[42],"as":[43],"and":[48,138,170],"assigned":[50],"weights":[51],"favorite":[54],"weighting":[55,72,78],"technique":[56,82,119,143],"called":[57,121,145],"TFIDF":[58,77],"(Term":[59],"Frequency":[60],"Inverse":[61],"Document":[62],"Frequency).":[63],"this":[65],"thesis,":[66],"we":[67,103,171],"have":[68],"devised":[69],"three":[70,168],"new":[71],"techniques":[73],"to":[74,93,130],"improve":[75],"technique.":[79],"The":[80,117,141],"first":[81,139],"Dispersed":[84],"Words":[85,148],"Weight":[86,123,149],"Augmentation":[87,124,150],"(DWWA)":[88],"gives":[90,127],"more":[91,109,128,173],"weight":[92,129,156],"distributed":[96],"most":[98,159],"document's":[101,136],"paragraphs;":[102],"consider":[104],"that":[105],"those":[106],"than":[111],"few":[115],"paragraphs.":[116,140],"second":[118],"Title":[122],"(TWA)":[125],"title":[137],"third":[142],"First":[146],"Ranked":[147],"(FRWWA)":[151],"increments":[153],"further":[154],"frequent":[160],"document.":[164],"We":[165],"tested":[166],"techniques,":[169],"relevant":[174],"were":[176],"our":[179],"system.":[180]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":3}],"updated_date":"2026-03-27T14:29:43.386196","created_date":"2025-10-10T00:00:00"}