{"id":"https://openalex.org/W2972968934","doi":"https://doi.org/10.1109/access.2019.2939872","title":"SInFo \u2013 Structure-Driven Incremental Forum Crawler That Optimizes User-Generated Content Retrieval","display_name":"SInFo \u2013 Structure-Driven Incremental Forum Crawler That Optimizes User-Generated Content Retrieval","publication_year":2019,"publication_date":"2019-01-01","ids":{"openalex":"https://openalex.org/W2972968934","doi":"https://doi.org/10.1109/access.2019.2939872","mag":"2972968934"},"language":"en","primary_location":{"id":"doi:10.1109/access.2019.2939872","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2019.2939872","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/8600701/08832156.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/ielx7/6287639/8600701/08832156.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5069947278","display_name":"Milo\u0161 Pavkovi\u0107","orcid":"https://orcid.org/0000-0001-7776-6045"},"institutions":[{"id":"https://openalex.org/I4068193","display_name":"University of Belgrade","ror":"https://ror.org/02qsmb048","country_code":"RS","type":"education","lineage":["https://openalex.org/I4068193"]}],"countries":["RS"],"is_corresponding":false,"raw_author_name":"Milos Pavkovic","raw_affiliation_strings":["School of Electrical Engineering, University of Belgrade, Belgrade, Serbia"],"raw_orcid":"https://orcid.org/0000-0001-7776-6045","affiliations":[{"raw_affiliation_string":"School of Electrical Engineering, University of Belgrade, Belgrade, Serbia","institution_ids":["https://openalex.org/I4068193"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5030643641","display_name":"Jelica Proti\u0107","orcid":"https://orcid.org/0000-0002-2171-477X"},"institutions":[{"id":"https://openalex.org/I4068193","display_name":"University of Belgrade","ror":"https://ror.org/02qsmb048","country_code":"RS","type":"education","lineage":["https://openalex.org/I4068193"]}],"countries":["RS"],"is_corresponding":false,"raw_author_name":"Jelica Protic","raw_affiliation_strings":["School of Electrical Engineering, University of Belgrade, Belgrade, Serbia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Electrical Engineering, University of Belgrade, Belgrade, Serbia","institution_ids":["https://openalex.org/I4068193"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4068193"],"apc_list":{"value":1850,"currency":"USD","value_usd":1850},"apc_paid":{"value":1850,"currency":"USD","value_usd":1850},"fwci":0.3444,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":{"value":0.68916547,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":"7","issue":null,"first_page":"126941","last_page":"126961"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":1.0,"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":1.0,"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":0.9975000023841858,"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"}},{"id":"https://openalex.org/T10742","display_name":"Peer-to-Peer Network Technologies","score":0.9902999997138977,"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/crawling","display_name":"Crawling","score":0.8097981214523315},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8007300496101379},{"id":"https://openalex.org/keywords/web-crawler","display_name":"Web crawler","score":0.7472401857376099},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.6185169219970703},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.5509259104728699},{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.537721574306488},{"id":"https://openalex.org/keywords/upload","display_name":"Upload","score":0.5330368876457214},{"id":"https://openalex.org/keywords/sort","display_name":"sort","score":0.5135838985443115},{"id":"https://openalex.org/keywords/focused-crawler","display_name":"Focused crawler","score":0.4387246072292328},{"id":"https://openalex.org/keywords/static-web-page","display_name":"Static web page","score":0.22779342532157898},{"id":"https://openalex.org/keywords/web-development","display_name":"Web development","score":0.16926166415214539}],"concepts":[{"id":"https://openalex.org/C100368936","wikidata":"https://www.wikidata.org/wiki/Q1411725","display_name":"Crawling","level":2,"score":0.8097981214523315},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8007300496101379},{"id":"https://openalex.org/C13743948","wikidata":"https://www.wikidata.org/wiki/Q45842","display_name":"Web crawler","level":2,"score":0.7472401857376099},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.6185169219970703},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.5509259104728699},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.537721574306488},{"id":"https://openalex.org/C71901391","wikidata":"https://www.wikidata.org/wiki/Q7126699","display_name":"Upload","level":2,"score":0.5330368876457214},{"id":"https://openalex.org/C88548561","wikidata":"https://www.wikidata.org/wiki/Q347599","display_name":"sort","level":2,"score":0.5135838985443115},{"id":"https://openalex.org/C73340581","wikidata":"https://www.wikidata.org/wiki/Q5463958","display_name":"Focused crawler","level":5,"score":0.4387246072292328},{"id":"https://openalex.org/C173576120","wikidata":"https://www.wikidata.org/wiki/Q2641220","display_name":"Static web page","level":4,"score":0.22779342532157898},{"id":"https://openalex.org/C79373723","wikidata":"https://www.wikidata.org/wiki/Q386275","display_name":"Web development","level":3,"score":0.16926166415214539},{"id":"https://openalex.org/C105702510","wikidata":"https://www.wikidata.org/wiki/Q514","display_name":"Anatomy","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}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/access.2019.2939872","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2019.2939872","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/8600701/08832156.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:7232bdd21a57482aad23c8c8583f18ba","is_oa":true,"landing_page_url":"https://doaj.org/article/7232bdd21a57482aad23c8c8583f18ba","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 7, Pp 126941-126961 (2019)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1109/access.2019.2939872","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2019.2939872","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/8600701/08832156.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":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2972968934.pdf","grobid_xml":"https://content.openalex.org/works/W2972968934.grobid-xml"},"referenced_works_count":34,"referenced_works":["https://openalex.org/W140013298","https://openalex.org/W270849871","https://openalex.org/W1507589574","https://openalex.org/W1566984846","https://openalex.org/W1976216148","https://openalex.org/W2049318906","https://openalex.org/W2059713800","https://openalex.org/W2066636486","https://openalex.org/W2083563309","https://openalex.org/W2085922539","https://openalex.org/W2086613190","https://openalex.org/W2099126271","https://openalex.org/W2100464657","https://openalex.org/W2100779529","https://openalex.org/W2105803339","https://openalex.org/W2109803107","https://openalex.org/W2110270499","https://openalex.org/W2113184419","https://openalex.org/W2134491992","https://openalex.org/W2145349611","https://openalex.org/W2152565070","https://openalex.org/W2156909104","https://openalex.org/W2168358004","https://openalex.org/W2250463012","https://openalex.org/W2495792383","https://openalex.org/W2501750902","https://openalex.org/W2551528114","https://openalex.org/W2551928050","https://openalex.org/W2581267621","https://openalex.org/W2789893667","https://openalex.org/W2798110387","https://openalex.org/W2907165009","https://openalex.org/W4246219036","https://openalex.org/W6634031162"],"related_works":["https://openalex.org/W2375180657","https://openalex.org/W2042034567","https://openalex.org/W2026132847","https://openalex.org/W1506122440","https://openalex.org/W2137810919","https://openalex.org/W2358310581","https://openalex.org/W2274831913","https://openalex.org/W2352686120","https://openalex.org/W2019080882","https://openalex.org/W4385695127"],"abstract_inverted_index":{"In":[0],"this":[1],"paper":[2],"we":[3,176],"present":[4],"a":[5,20,39,66,75,215],"Structure-driven":[6],"Incremental":[7],"Forum":[8],"crawler":[9],"(SInFo)":[10],"that":[11,45],"targets":[12],"the":[13,54,57,61,81,87,101,104,130,135,146,171,181,186,192,199,202,244,249],"latest":[14,58,62,203],"content":[15,25,63,73,83,90,124,157,251],"in":[16,79,125,252],"crawling":[17],"cycles.":[18],"On":[19],"Web":[21],"forum,":[22],"user":[23,55],"generated":[24],"is":[26,34,38,64,91,118,140],"almost":[27],"never":[28],"changed":[29],"or":[30],"deleted,":[31],"but":[32],"it":[33],"constantly":[35],"added.":[36],"There":[37],"wide":[40,216],"spectrum":[41],"of":[42,116,122,134,194,218,226,239,246],"forum":[43,76,89,126,136,148,152,164,220],"technologies":[44,211],"have":[46],"different":[47],"representations":[48],"and":[49,93,144,154,158,174,190,212,236],"navigational":[50,166],"paths":[51],"to":[52,56,74,97,100,119,142,179,197],"lead":[53,96],"content.":[59,204],"Targeting":[60],"not":[65],"trivial":[67],"task,":[68],"since":[69],"adding":[70],"some":[71],"new":[72,250],"often":[77],"results":[78],"shifting":[80],"old":[82],"between":[84,168],"pages.":[85,169],"Ignoring":[86],"way":[88],"distributed":[92],"sorted":[94],"can":[95],"repetitive":[98],"visits":[99],"pages":[102],"with":[103],"same":[105],"data":[106],"from":[107],"previous":[108],"crawls":[109],"while":[110],"incrementally":[111],"crawling.":[112],"The":[113,138,205],"main":[114],"goal":[115],"SInFo":[117,232],"avoid":[120],"transfer":[121],"duplicate":[123],"incremental":[127],"crawling,":[128],"using":[129],"generic":[131],"approach":[132],"regardless":[133],"technology.":[137],"problem":[139],"reduced":[141],"discovering":[143],"utilizing":[145],"following":[147],"technology":[149,165],"features:":[150],"(1)":[151],"index":[153],"thread":[155],"page":[156,183,200],"sort":[159],"representation":[160],"and,":[161],"(2)":[162],"available":[163],"options":[167],"With":[170],"proposed":[172],"methods":[173],"techniques,":[175],"show":[177],"how":[178],"locate":[180],"target":[182],"by":[184,242],"observing":[185],"URL":[187],"signature":[188],"format":[189],"minimize":[191],"number":[193],"required":[195],"downloads":[196],"fetch":[198],"containing":[201],"experiments":[206],"were":[207],"conducted":[208],"on":[209,214],"custom":[210],"also":[213],"range":[217],"pre-built":[219],"packages":[221],"covering":[222],"more":[223],"than":[224],"80%":[225],"representative":[227],"widely":[228],"used":[229],"software":[230],"packages.":[231],"showed":[233],"high":[234],"accuracy":[235],"low":[237],"level":[238],"duplicates":[240],"transmission":[241],"reaching":[243],"average":[245],"92.6%":[247],"for":[248],"each":[253],"recrawl":[254],"cycle.":[255]},"counts_by_year":[{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}