{"id":"https://openalex.org/W3217346029","doi":"https://doi.org/10.1109/access.2021.3129187","title":"Efficient Sentiment-Aware Web Crawling Methods for Constructing Sentiment Dictionary","display_name":"Efficient Sentiment-Aware Web Crawling Methods for Constructing Sentiment Dictionary","publication_year":2021,"publication_date":"2021-01-01","ids":{"openalex":"https://openalex.org/W3217346029","doi":"https://doi.org/10.1109/access.2021.3129187","mag":"3217346029"},"language":"en","primary_location":{"id":"doi:10.1109/access.2021.3129187","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2021.3129187","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/6514899/09620107.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://ieeexplore.ieee.org/ielx7/6287639/6514899/09620107.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5084878720","display_name":"Byung-Won On","orcid":"https://orcid.org/0000-0001-6929-3188"},"institutions":[{"id":"https://openalex.org/I120158604","display_name":"Kunsan National University","ror":"https://ror.org/02yj55q56","country_code":"KR","type":"education","lineage":["https://openalex.org/I120158604"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Byung-Won On","raw_affiliation_strings":["Department of Software Convergence Engineering, Kunsan National University, Gunsan-si, Jeollabuk-do 54150, Korea. (e-mail: bwon@kunsan.ac.kr)","Department of Software Convergence Engineering, Kunsan National University, Gunsan-si, Jeollabuk-do 54150, Korea"],"raw_orcid":"https://orcid.org/0000-0001-6929-3188","affiliations":[{"raw_affiliation_string":"Department of Software Convergence Engineering, Kunsan National University, Gunsan-si, Jeollabuk-do 54150, Korea. (e-mail: bwon@kunsan.ac.kr)","institution_ids":["https://openalex.org/I120158604"]},{"raw_affiliation_string":"Department of Software Convergence Engineering, Kunsan National University, Gunsan-si, Jeollabuk-do 54150, Korea","institution_ids":["https://openalex.org/I120158604"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069860835","display_name":"Junyoung Jo","orcid":"https://orcid.org/0000-0001-9721-7641"},"institutions":[{"id":"https://openalex.org/I120158604","display_name":"Kunsan National University","ror":"https://ror.org/02yj55q56","country_code":"KR","type":"education","lineage":["https://openalex.org/I120158604"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Jun-Young Jo","raw_affiliation_strings":["Department of Software Convergence Engineering, Kunsan National University, Gunsan-si, Jeollabuk-do 54150, Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Software Convergence Engineering, Kunsan National University, Gunsan-si, Jeollabuk-do 54150, Korea","institution_ids":["https://openalex.org/I120158604"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024967023","display_name":"Hyunkwang Shin","orcid":"https://orcid.org/0000-0002-9148-1131"},"institutions":[{"id":"https://openalex.org/I55240360","display_name":"Yeungnam University","ror":"https://ror.org/05yc6p159","country_code":"KR","type":"education","lineage":["https://openalex.org/I55240360"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Hyunkwang Shin","raw_affiliation_strings":["Department of Information and Communication Engineering, Yeungnam University, Gyeongsan-si, Gyeongsangbuk-do 38541, Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Information and Communication Engineering, Yeungnam University, Gyeongsan-si, Gyeongsangbuk-do 38541, Korea","institution_ids":["https://openalex.org/I55240360"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042427900","display_name":"Jangwon Gim","orcid":"https://orcid.org/0000-0002-4480-7944"},"institutions":[{"id":"https://openalex.org/I120158604","display_name":"Kunsan National University","ror":"https://ror.org/02yj55q56","country_code":"KR","type":"education","lineage":["https://openalex.org/I120158604"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Jangwon Gim","raw_affiliation_strings":["Department of Software Convergence Engineering, Kunsan National University, Gunsan-si, Jeollabuk-do 54150, Korea"],"raw_orcid":"https://orcid.org/0000-0002-4480-7944","affiliations":[{"raw_affiliation_string":"Department of Software Convergence Engineering, Kunsan National University, Gunsan-si, Jeollabuk-do 54150, Korea","institution_ids":["https://openalex.org/I120158604"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044080887","display_name":"Gyu Sang Choi","orcid":"https://orcid.org/0000-0002-0854-768X"},"institutions":[{"id":"https://openalex.org/I55240360","display_name":"Yeungnam University","ror":"https://ror.org/05yc6p159","country_code":"KR","type":"education","lineage":["https://openalex.org/I55240360"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Gyu Sang Choi","raw_affiliation_strings":["Department of Information and Communication Engineering, Yeungnam University, Gyeongsan-si, Gyeongsangbuk-do 38541, Korea"],"raw_orcid":"https://orcid.org/0000-0002-0854-768X","affiliations":[{"raw_affiliation_string":"Department of Information and Communication Engineering, Yeungnam University, Gyeongsan-si, Gyeongsangbuk-do 38541, Korea","institution_ids":["https://openalex.org/I55240360"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5109955956","display_name":"Soo-Mok Jung","orcid":null},"institutions":[{"id":"https://openalex.org/I27941296","display_name":"Sahmyook University","ror":"https://ror.org/04vxr4k74","country_code":"KR","type":"education","lineage":["https://openalex.org/I27941296"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Soo-Mok Jung","raw_affiliation_strings":["Division of Computer Science and Engineering, Sahmyook University, Seoul 01795, Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Division of Computer Science and Engineering, Sahmyook University, Seoul 01795, Korea","institution_ids":["https://openalex.org/I27941296"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":2075,"currency":"USD","value_usd":2075},"apc_paid":{"value":2075,"currency":"USD","value_usd":2075},"fwci":1.15,"has_fulltext":true,"cited_by_count":5,"citation_normalized_percentile":{"value":0.84413154,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":"9","issue":null,"first_page":"161208","last_page":"161223"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9991999864578247,"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"}},"topics":[{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9991999864578247,"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/T11644","display_name":"Spam and Phishing Detection","score":0.9947999715805054,"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/T11478","display_name":"Caching and Content Delivery","score":0.9939000010490417,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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":0.8811867237091064},{"id":"https://openalex.org/keywords/crawling","display_name":"Crawling","score":0.8174238204956055},{"id":"https://openalex.org/keywords/web-crawler","display_name":"Web crawler","score":0.6649619340896606},{"id":"https://openalex.org/keywords/hash-function","display_name":"Hash function","score":0.6197099685668945},{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.610278844833374},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5131266713142395},{"id":"https://openalex.org/keywords/join","display_name":"Join (topology)","score":0.4642632007598877},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.44257086515426636},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.3846662938594818},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.05753394961357117}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8811867237091064},{"id":"https://openalex.org/C100368936","wikidata":"https://www.wikidata.org/wiki/Q1411725","display_name":"Crawling","level":2,"score":0.8174238204956055},{"id":"https://openalex.org/C13743948","wikidata":"https://www.wikidata.org/wiki/Q45842","display_name":"Web crawler","level":2,"score":0.6649619340896606},{"id":"https://openalex.org/C99138194","wikidata":"https://www.wikidata.org/wiki/Q183427","display_name":"Hash function","level":2,"score":0.6197099685668945},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.610278844833374},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5131266713142395},{"id":"https://openalex.org/C2776124973","wikidata":"https://www.wikidata.org/wiki/Q3183033","display_name":"Join (topology)","level":2,"score":0.4642632007598877},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.44257086515426636},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.3846662938594818},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.05753394961357117},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"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/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.0},{"id":"https://openalex.org/C105702510","wikidata":"https://www.wikidata.org/wiki/Q514","display_name":"Anatomy","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/access.2021.3129187","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2021.3129187","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/6514899/09620107.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:90e4d5c593df490bb6fb3fc709afa24a","is_oa":true,"landing_page_url":"https://doaj.org/article/90e4d5c593df490bb6fb3fc709afa24a","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Access, Vol 9, Pp 161208-161223 (2021)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1109/access.2021.3129187","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2021.3129187","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/6514899/09620107.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2420811182","display_name":null,"funder_award_id":"2019R1F1A1060752","funder_id":"https://openalex.org/F4320322120","funder_display_name":"National Research Foundation of Korea"},{"id":"https://openalex.org/G284234960","display_name":null,"funder_award_id":"NRF-2021R1A6A1A03039493","funder_id":"https://openalex.org/F4320322120","funder_display_name":"National Research Foundation of Korea"},{"id":"https://openalex.org/G3639147631","display_name":null,"funder_award_id":"NRF-2019R1F1A1060752","funder_id":"https://openalex.org/F4320322120","funder_display_name":"National Research Foundation of Korea"},{"id":"https://openalex.org/G8626891402","display_name":null,"funder_award_id":"NRF-2021R1A6A1A03039493","funder_id":"https://openalex.org/F4320328359","funder_display_name":"Ministry of Science and ICT, South Korea"},{"id":"https://openalex.org/G960464093","display_name":null,"funder_award_id":"2021R1A6A1A03039493.","funder_id":"https://openalex.org/F4320322120","funder_display_name":"National Research Foundation of Korea"}],"funders":[{"id":"https://openalex.org/F4320320671","display_name":"National Research Foundation","ror":"https://ror.org/05s0g1g46"},{"id":"https://openalex.org/F4320322120","display_name":"National Research Foundation of Korea","ror":"https://ror.org/013aysd81"},{"id":"https://openalex.org/F4320328359","display_name":"Ministry of Science and ICT, South Korea","ror":"https://ror.org/01wpjm123"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3217346029.pdf","grobid_xml":"https://content.openalex.org/works/W3217346029.grobid-xml"},"referenced_works_count":29,"referenced_works":["https://openalex.org/W1490731164","https://openalex.org/W1515038756","https://openalex.org/W1991873845","https://openalex.org/W2007030756","https://openalex.org/W2016300339","https://openalex.org/W2043934800","https://openalex.org/W2130221750","https://openalex.org/W2169486917","https://openalex.org/W2515777276","https://openalex.org/W2548298479","https://openalex.org/W2765200277","https://openalex.org/W2778981424","https://openalex.org/W2779183570","https://openalex.org/W2810966518","https://openalex.org/W2923280274","https://openalex.org/W2953804754","https://openalex.org/W2966959960","https://openalex.org/W2997097677","https://openalex.org/W3003279033","https://openalex.org/W3006145085","https://openalex.org/W3010285765","https://openalex.org/W3142751212","https://openalex.org/W4211186029","https://openalex.org/W4243739522","https://openalex.org/W6629161310","https://openalex.org/W6630842491","https://openalex.org/W6747178056","https://openalex.org/W6766683234","https://openalex.org/W6773391132"],"related_works":["https://openalex.org/W2566658409","https://openalex.org/W3119324922","https://openalex.org/W2352686120","https://openalex.org/W2372594123","https://openalex.org/W2358310581","https://openalex.org/W2026132847","https://openalex.org/W4385695127","https://openalex.org/W2137810919","https://openalex.org/W2964752624","https://openalex.org/W4255854114"],"abstract_inverted_index":{"In":[0,87,131],"traditional":[1],"web":[2,5,21,48,62,100,110,119,144,162],"crawling,":[3],"all":[4,47],"pages":[6,22,49],"crawled":[7],"are":[8],"first":[9,58],"stored":[10],"to":[11,138,159],"databases.":[12],"As":[13],"a":[14,32,36,91],"result,":[15],"this":[16],"approach":[17],"can":[18,153],"store":[19],"unnecessary":[20],"and":[23,65,80,128,149],"requires":[24],"additional":[25],"running":[26,126],"time":[27,127,136],"for":[28,71,96],"the":[29,51,60,72,81,97,108,125,132,135,140,150,160],"construction":[30],"of":[31],"sentiment":[33,40],"dictionary":[34],"in":[35,50],"particular":[37],"domain":[38],"because":[39],"words":[41],"should":[42],"be":[43,154],"identified":[44],"by":[45,122,156],"scanning":[46],"database.":[52],"To":[53],"address":[54],"these":[55],"problems,":[56],"we":[57,89],"define":[59],"sentiment-aware":[61,99,141],"crawling":[63,101,111,120,163],"problem":[64],"then":[66],"propose":[67,90],"two":[68],"hash-based":[69],"methods":[70,121],"implementation.":[73],"One":[74],"is":[75,83,146],"based":[76],"on":[77],"hash":[78,85,94,115],"join":[79,95,116],"other":[82],"bucket-sorted":[84,93,114],"join.":[86],"particular,":[88],"novel":[92],"efficient":[98],"method.":[102],"Our":[103],"experimental":[104],"results":[105],"show":[106],"that":[107],"proposed":[109,133],"method":[112],"using":[113],"outperforms":[117],"existing":[118,161],"significantly":[123],"reducing":[124],"storage":[129],"space.":[130],"method,":[134],"taken":[137],"execute":[139],"task":[142],"per":[143],"page":[145],"0.016":[147],"seconds":[148],"database":[151],"space":[152],"saved":[155],"59%":[157],"compared":[158],"methods.":[164]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":2}],"updated_date":"2026-08-21T09:56:20.448147","created_date":"2025-10-10T00:00:00"}
