{"id":"https://openalex.org/W2902396799","doi":"https://doi.org/10.1145/3278293.3278301","title":"A Novel Feature Hashing With Efficient Collision Resolution for Bag-of-Words Representation of Text Data","display_name":"A Novel Feature Hashing With Efficient Collision Resolution for Bag-of-Words Representation of Text Data","publication_year":2018,"publication_date":"2018-09-07","ids":{"openalex":"https://openalex.org/W2902396799","doi":"https://doi.org/10.1145/3278293.3278301","mag":"2902396799"},"language":"en","primary_location":{"id":"doi:10.1145/3278293.3278301","doi":"https://doi.org/10.1145/3278293.3278301","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3278293.3278301","pdf_url":null,"source":{"id":"https://openalex.org/S7407087597","display_name":"International Conference on Natural Language Processing and Information Retrieval (NLPIR)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2nd International Conference on Natural Language Processing and Information Retrieval","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","is_traditional":true,"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/A5015291210","display_name":"Bobby A. Eclarin","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4405278569","display_name":"Technological Institute of the Philippines-Quezon City","ror":"https://ror.org/007ehk224","country_code":"PH","type":"education","lineage":["https://openalex.org/I4405278569","https://openalex.org/I95350115"]}],"countries":["PH"],"is_corresponding":false,"raw_author_name":"Bobby A. Eclarin","raw_affiliation_strings":["Technological Institute of the Philippines, Quezon City, Philippines"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Technological Institute of the Philippines, Quezon City, Philippines","institution_ids":["https://openalex.org/I4405278569"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024811786","display_name":"Arnel C. Fajardo","orcid":"https://orcid.org/0000-0002-1231-6382","observed_orcids":["https://orcid.org/0000-0002-1231-6382"]},"institutions":[{"id":"https://openalex.org/I4405278623","display_name":"La Consolacion College Manila","ror":"https://ror.org/00a1xcb06","country_code":"PH","type":"education","lineage":["https://openalex.org/I4405278623"]}],"countries":["PH"],"is_corresponding":false,"raw_author_name":"Arnel C. Fajardo","raw_affiliation_strings":["La Consolacion College Manila, Mendiola St, San Miguel Manila, Philippines"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"La Consolacion College Manila, Mendiola St, San Miguel Manila, Philippines","institution_ids":["https://openalex.org/I4405278623"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5032332379","display_name":"Ruji P. Medina","orcid":"https://orcid.org/0000-0003-1649-4634","observed_orcids":["https://orcid.org/0000-0003-1649-4634"]},"institutions":[{"id":"https://openalex.org/I4405278569","display_name":"Technological Institute of the Philippines-Quezon City","ror":"https://ror.org/007ehk224","country_code":"PH","type":"education","lineage":["https://openalex.org/I4405278569","https://openalex.org/I95350115"]}],"countries":["PH"],"is_corresponding":false,"raw_author_name":"Ruji P. Medina","raw_affiliation_strings":["Technological Institute of the Philippines, Quezon City, Philippines"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Technological Institute of the Philippines, Quezon City, Philippines","institution_ids":["https://openalex.org/I4405278569"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0885,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.26778629,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":87,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"12","last_page":"16"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11550","display_name":"Text and Document Classification Technologies","score":0.9390000104904175,"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":0.9390000104904175,"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/T11269","display_name":"Algorithms and Data Compression","score":0.02539999969303608,"subfield":{"id":"https://openalex.org/subfields/2614","display_name":"Theoretical Computer Science"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.013100000098347664,"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/feature-hashing","display_name":"feature hashing","score":0.9829999804496765},{"id":"https://openalex.org/keywords/collision-resolution","display_name":"collision resolution","score":0.9210000038146973},{"id":"https://openalex.org/keywords/bag-of-words","display_name":"bag-of-words","score":0.925000011920929},{"id":"https://openalex.org/keywords/text-mining","display_name":"text mining","score":0.7540000081062317},{"id":"https://openalex.org/keywords/text-classification","display_name":"text classification","score":0.9829999804496765},{"id":"https://openalex.org/keywords/feature-selection","display_name":"feature selection","score":0.5509999990463257},{"id":"https://openalex.org/keywords/text-feature-extraction","display_name":"text feature extraction","score":0.578000009059906},{"id":"https://openalex.org/keywords/vector-data-structures","display_name":"vector data structures","score":0.48899999260902405},{"id":"https://openalex.org/keywords/memory-efficiency","display_name":"memory efficiency","score":0.8320000171661377}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8003703951835632},{"id":"https://openalex.org/C99138194","wikidata":"https://www.wikidata.org/wiki/Q183427","display_name":"Hash function","level":2,"score":0.6662177443504333},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.616202175617218},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5980790853500366},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5137889981269836},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.5021929740905762},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4931299388408661},{"id":"https://openalex.org/C13672336","wikidata":"https://www.wikidata.org/wiki/Q3460803","display_name":"Bag-of-words model","level":2,"score":0.488872230052948},{"id":"https://openalex.org/C74270461","wikidata":"https://www.wikidata.org/wiki/Q1625299","display_name":"Locality-sensitive hashing","level":4,"score":0.47949057817459106},{"id":"https://openalex.org/C67388219","wikidata":"https://www.wikidata.org/wiki/Q207440","display_name":"Hash table","level":3,"score":0.4694015085697174},{"id":"https://openalex.org/C121704057","wikidata":"https://www.wikidata.org/wiki/Q352070","display_name":"Collision","level":2,"score":0.45816972851753235},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4261455237865448},{"id":"https://openalex.org/C162319229","wikidata":"https://www.wikidata.org/wiki/Q175263","display_name":"Data structure","level":2,"score":0.41833972930908203},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.4162151515483856},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3754003047943115},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.37424740195274353},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","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/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"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/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","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/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3278293.3278301","doi":"https://doi.org/10.1145/3278293.3278301","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3278293.3278301","pdf_url":null,"source":{"id":"https://openalex.org/S7407087597","display_name":"International Conference on Natural Language Processing and Information Retrieval (NLPIR)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2nd International Conference on Natural Language Processing and Information Retrieval","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320324072","display_name":"Commission on Higher Education","ror":"https://ror.org/04s346m05"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W1576138761","https://openalex.org/W1978397141","https://openalex.org/W2024078544","https://openalex.org/W2044784665","https://openalex.org/W2090645789","https://openalex.org/W2093709025","https://openalex.org/W2094937180","https://openalex.org/W2268177516","https://openalex.org/W2334175399","https://openalex.org/W2472731163","https://openalex.org/W2561635958","https://openalex.org/W2597027883","https://openalex.org/W2613366409","https://openalex.org/W2617640238","https://openalex.org/W2735364069","https://openalex.org/W2798375247","https://openalex.org/W2807076668","https://openalex.org/W4285719527"],"related_works":["https://openalex.org/W7098993160","https://openalex.org/W3183436810","https://openalex.org/W4413418720","https://openalex.org/W2087787226","https://openalex.org/W4281703876","https://openalex.org/W2528236455","https://openalex.org/W2514020411","https://openalex.org/W2607731345","https://openalex.org/W122956856","https://openalex.org/W2396991783"],"abstract_inverted_index":{"Text":[0],"Mining":[1],"is":[2,40,61,92,104,128,137],"widely":[3],"used":[4],"in":[5,51,58],"many":[6],"areas":[7],"transforming":[8],"unstructured":[9],"text":[10,47,54],"data":[11,48,91,123],"from":[12,46],"all":[13],"sources":[14],"such":[15],"as":[16],"patients'":[17],"record,":[18],"social":[19],"media":[20],"network,":[21],"insurance":[22],"data,":[23],"and":[24,69,106,118,133],"news,":[25],"among":[26],"others":[27],"into":[28],"an":[29],"invaluable":[30],"source":[31],"of":[32,43,89,111,115],"information.":[33],"The":[34],"Bag":[35],"Of":[36],"Words":[37],"(BoW)":[38],"representation":[39],"a":[41,56,59,63],"means":[42],"extracting":[44],"features":[45],"for":[49],"use":[50,94],"modeling.":[52],"In":[53],"classification,":[55],"word":[57],"document":[60],"assigned":[62],"weight":[64],"according":[65],"to":[66,85,93],"its":[67],"frequency":[68,70],"between":[71],"different":[72],"documents;":[73],"therefore,":[74],"words":[75],"together":[76],"with":[77],"their":[78],"weights":[79],"form":[80],"the":[81,87,95,109,112,121,125,134],"BoW.":[82],"One":[83],"way":[84],"solve":[86],"issue":[88],"voluminous":[90],"feature":[96,116],"hashing":[97,100],"method":[98],"or":[99],"trick.":[101],"However,":[102],"collision":[103,132],"inevitable":[105],"might":[107],"change":[108],"result":[110],"whole":[113],"process":[114],"generation":[117],"selection.":[119],"Using":[120],"vector":[122],"structure,":[124],"lookup":[126],"performance":[127],"improved":[129],"while":[130],"resolving":[131],"memory":[135],"usage":[136],"also":[138],"efficient.":[139]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2021,"cited_by_count":1}],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2018-12-11T00:00:00"}