{"id":"https://openalex.org/W2560835640","doi":"https://doi.org/10.3390/e19120686","title":"Do We Really Need to Catch Them All? A New User-Guided Social Media Crawling Method","display_name":"Do We Really Need to Catch Them All? A New User-Guided Social Media Crawling Method","publication_year":2017,"publication_date":"2017-12-13","ids":{"openalex":"https://openalex.org/W2560835640","doi":"https://doi.org/10.3390/e19120686","mag":"2560835640"},"language":"en","primary_location":{"id":"doi:10.3390/e19120686","is_oa":true,"landing_page_url":"https://doi.org/10.3390/e19120686","pdf_url":"https://www.mdpi.com/1099-4300/19/12/686/pdf?version=1513179859","source":{"id":"https://openalex.org/S195231649","display_name":"Entropy","issn_l":"1099-4300","issn":["1099-4300"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Entropy","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.mdpi.com/1099-4300/19/12/686/pdf?version=1513179859","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Fredrik Erlandsson","orcid":"https://orcid.org/0000-0003-3219-9598"},"institutions":[{"id":"https://openalex.org/I52719799","display_name":"Blekinge Institute of Technology","ror":"https://ror.org/0093a8w51","country_code":"SE","type":"education","lineage":["https://openalex.org/I52719799"]}],"countries":["SE"],"is_corresponding":true,"raw_author_name":"Fredrik Erlandsson","raw_affiliation_strings":["Department of Computer Science and Engineering, Blekinge Institute of Technology, 371 79 Karlskrona, Sweden"],"raw_orcid":"https://orcid.org/0000-0003-3219-9598","affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Blekinge Institute of Technology, 371 79 Karlskrona, Sweden","institution_ids":["https://openalex.org/I52719799"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Piotr Br\u00f3dka","orcid":"https://orcid.org/0000-0002-6474-0089"},"institutions":[{"id":"https://openalex.org/I11923345","display_name":"Wroc\u0142aw University of Science and Technology","ror":"https://ror.org/008fyn775","country_code":"PL","type":"education","lineage":["https://openalex.org/I11923345"]},{"id":"https://openalex.org/I686019","display_name":"AGH University of Krakow","ror":"https://ror.org/00bas1c41","country_code":"PL","type":"education","lineage":["https://openalex.org/I686019"]}],"countries":["PL"],"is_corresponding":false,"raw_author_name":"Piotr Br\u00f3dka","raw_affiliation_strings":["Department of Computational Intelligence, Wroc\u0142aw University of Science and Technology, 50-370 Wroc\u0142aw, Poland"],"raw_orcid":"https://orcid.org/0000-0002-6474-0089","affiliations":[{"raw_affiliation_string":"Department of Computational Intelligence, Wroc\u0142aw University of Science and Technology, 50-370 Wroc\u0142aw, Poland","institution_ids":["https://openalex.org/I11923345","https://openalex.org/I686019"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Martin Boldt","orcid":"https://orcid.org/0000-0002-9316-4842"},"institutions":[{"id":"https://openalex.org/I52719799","display_name":"Blekinge Institute of Technology","ror":"https://ror.org/0093a8w51","country_code":"SE","type":"education","lineage":["https://openalex.org/I52719799"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Martin Boldt","raw_affiliation_strings":["Department of Computer Science and Engineering, Blekinge Institute of Technology, 371 79 Karlskrona, Sweden"],"raw_orcid":"https://orcid.org/0000-0002-9316-4842","affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Blekinge Institute of Technology, 371 79 Karlskrona, Sweden","institution_ids":["https://openalex.org/I52719799"]}]},{"author_position":"last","author":{"id":null,"display_name":"Henric Johnson","orcid":null},"institutions":[{"id":"https://openalex.org/I52719799","display_name":"Blekinge Institute of Technology","ror":"https://ror.org/0093a8w51","country_code":"SE","type":"education","lineage":["https://openalex.org/I52719799"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Henric Johnson","raw_affiliation_strings":["Department of Computer Science and Engineering, Blekinge Institute of Technology, 371 79 Karlskrona, Sweden"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Blekinge Institute of Technology, 371 79 Karlskrona, Sweden","institution_ids":["https://openalex.org/I52719799"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I52719799"],"apc_list":{"value":2000,"currency":"CHF","value_usd":2165},"apc_paid":{"value":2000,"currency":"CHF","value_usd":2165},"fwci":2.0251,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.89281284,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":"19","issue":"12","first_page":"686","last_page":"686"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.7121000289916992,"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":0.7121000289916992,"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/T13976","display_name":"Web visibility and informetrics","score":0.019200000911951065,"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":0.013799999840557575,"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":0.9697999954223633},{"id":"https://openalex.org/keywords/social-media","display_name":"Social media","score":0.7253000140190125},{"id":"https://openalex.org/keywords/cover","display_name":"Cover (algebra)","score":0.5935999751091003},{"id":"https://openalex.org/keywords/social-network","display_name":"Social network (sociolinguistics)","score":0.5292999744415283},{"id":"https://openalex.org/keywords/order","display_name":"Order (exchange)","score":0.46959999203681946},{"id":"https://openalex.org/keywords/user-generated-content","display_name":"User-generated content","score":0.4578999876976013},{"id":"https://openalex.org/keywords/web-crawler","display_name":"Web crawler","score":0.4458000063896179}],"concepts":[{"id":"https://openalex.org/C100368936","wikidata":"https://www.wikidata.org/wiki/Q1411725","display_name":"Crawling","level":2,"score":0.9697999954223633},{"id":"https://openalex.org/C518677369","wikidata":"https://www.wikidata.org/wiki/Q202833","display_name":"Social media","level":2,"score":0.7253000140190125},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6524999737739563},{"id":"https://openalex.org/C2780428219","wikidata":"https://www.wikidata.org/wiki/Q16952335","display_name":"Cover (algebra)","level":2,"score":0.5935999751091003},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.5906999707221985},{"id":"https://openalex.org/C4727928","wikidata":"https://www.wikidata.org/wiki/Q17164759","display_name":"Social network (sociolinguistics)","level":3,"score":0.5292999744415283},{"id":"https://openalex.org/C182306322","wikidata":"https://www.wikidata.org/wiki/Q1779371","display_name":"Order (exchange)","level":2,"score":0.46959999203681946},{"id":"https://openalex.org/C108827166","wikidata":"https://www.wikidata.org/wiki/Q175975","display_name":"Internet privacy","level":1,"score":0.46129998564720154},{"id":"https://openalex.org/C101293273","wikidata":"https://www.wikidata.org/wiki/Q579716","display_name":"User-generated content","level":3,"score":0.4578999876976013},{"id":"https://openalex.org/C13743948","wikidata":"https://www.wikidata.org/wiki/Q45842","display_name":"Web crawler","level":2,"score":0.4458000063896179},{"id":"https://openalex.org/C2164484","wikidata":"https://www.wikidata.org/wiki/Q5170150","display_name":"Core (optical fiber)","level":2,"score":0.41510000824928284},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.3928999900817871},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.3321000039577484},{"id":"https://openalex.org/C18762648","wikidata":"https://www.wikidata.org/wiki/Q42213","display_name":"Work (physics)","level":2,"score":0.3314000070095062},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.3264999985694885},{"id":"https://openalex.org/C2778152352","wikidata":"https://www.wikidata.org/wiki/Q5165061","display_name":"Content (measure theory)","level":2,"score":0.30300000309944153},{"id":"https://openalex.org/C65499552","wikidata":"https://www.wikidata.org/wiki/Q5421061","display_name":"Experience sampling method","level":2,"score":0.2976999878883362},{"id":"https://openalex.org/C114713312","wikidata":"https://www.wikidata.org/wiki/Q7551269","display_name":"Social network analysis","level":3,"score":0.2809999883174896},{"id":"https://openalex.org/C60136833","wikidata":"https://www.wikidata.org/wiki/Q1071262","display_name":"Social media optimization","level":3,"score":0.26089999079704285}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.3390/e19120686","is_oa":true,"landing_page_url":"https://doi.org/10.3390/e19120686","pdf_url":"https://www.mdpi.com/1099-4300/19/12/686/pdf?version=1513179859","source":{"id":"https://openalex.org/S195231649","display_name":"Entropy","issn_l":"1099-4300","issn":["1099-4300"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Entropy","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:1612.01734","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1612.01734","pdf_url":"https://arxiv.org/pdf/1612.01734","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"pmh:oai:DiVA.org:bth-15508","is_oa":true,"landing_page_url":"http://urn.kb.se/resolve?urn=urn:nbn:se:bth-15508","pdf_url":null,"source":{"id":"https://openalex.org/S4306401559","display_name":"KTH Publication Database DiVA (KTH Royal Institute of Technology)","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":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"pmh:oai:doaj.org/article:7bb02df6ac694e67b77061418fdde322","is_oa":true,"landing_page_url":"https://doaj.org/article/7bb02df6ac694e67b77061418fdde322","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":"Entropy, Vol 19, Iss 12, p 686 (2017)","raw_type":"article"},{"id":"pmh:oai:mdpi.com:/1099-4300/19/12/686/","is_oa":true,"landing_page_url":"https://dx.doi.org/10.3390/e19120686","pdf_url":null,"source":{"id":"https://openalex.org/S4306400947","display_name":"MDPI (MDPI AG)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210097602","host_organization_name":"Multidisciplinary Digital Publishing Institute (Switzerland)","host_organization_lineage":["https://openalex.org/I4210097602"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Entropy; Volume 19; Issue 12; Pages: 686","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.3390/e19120686","is_oa":true,"landing_page_url":"https://doi.org/10.3390/e19120686","pdf_url":"https://www.mdpi.com/1099-4300/19/12/686/pdf?version=1513179859","source":{"id":"https://openalex.org/S195231649","display_name":"Entropy","issn_l":"1099-4300","issn":["1099-4300"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Entropy","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W1774848501","https://openalex.org/W1930399416","https://openalex.org/W1986435040","https://openalex.org/W1991809678","https://openalex.org/W2037858832","https://openalex.org/W2068140991","https://openalex.org/W2086886525","https://openalex.org/W2115022330","https://openalex.org/W2118129996","https://openalex.org/W2137135938","https://openalex.org/W2143286114","https://openalex.org/W2146008005","https://openalex.org/W2152046791","https://openalex.org/W2292103443","https://openalex.org/W2293214727","https://openalex.org/W2336754337","https://openalex.org/W2344482722","https://openalex.org/W2513806786","https://openalex.org/W2560835640","https://openalex.org/W2964024029","https://openalex.org/W3123679541","https://openalex.org/W6968474371"],"related_works":[],"abstract_inverted_index":{"[-15]With":[0],"the":[1,21,26,72,75,79,137,152,156,163,168,176,182],"growing":[2],"use":[3],"of":[4,46,74,136,147,175],"popular":[5],"social":[6,69,164,183],"media":[7],"services":[8],"like":[9],"Facebook":[10,104,141],"and":[11,116,150,178,189],"Twitter":[12],"it":[13,117,129,190],"is":[14,63,98,118,130],"challenging":[15],"to":[16,25,65,77,89,132,181],"collect":[17,66],"all":[18,35,187],"content":[19,36,85,107],"from":[20,68,108,167,186],"networks":[22],"without":[23],"access":[24],"core":[27],"infrastructure":[28],"or":[29],"paying":[30],"for":[31],"it.":[32],"Thus,":[33],"if":[34],"cannot":[37],"be":[38,87],"collected":[39,88],"one":[40],"must":[41],"consider":[42],"which":[43,82],"data":[44,67],"are":[45],"most":[47],"importance.":[48],"In":[49,161],"this":[50],"work":[51],"we":[52],"present":[53],"a":[54,140],"novel":[55],"User-guided":[56],"Social":[57],"Media":[58],"Crawling":[59],"method":[60],"(USMC)":[61],"that":[62,128],"able":[64],"media,":[70],"utilizing":[71],"wisdom":[73],"crowd":[76],"decide":[78],"order":[80],"in":[81],"user":[83,93],"generated":[84],"should":[86],"cover":[90,133],"as":[91,95],"many":[92],"interactions":[94,138],"possible.":[96],"USMC":[97],"validated":[99],"by":[100,143,159],"crawling":[101,123,157],"160":[102],"public":[103],"pages,":[105],"containing":[106],"368":[109],"million":[110],"users":[111,177],"including":[112],"1.3":[113],"billion":[114],"interactions,":[115],"compared":[119,180],"with":[120],"two":[121],"other":[122],"methods.":[124],"The":[125],"results":[126],"show":[127],"possible":[131],"approximately":[134],"75%":[135,174],"on":[139],"page":[142],"sampling":[144],"just":[145],"20%":[146,169],"its":[148],"posts,":[149,188],"at":[151],"same":[153],"time":[154,158],"reduce":[155],"53%.":[160],"addition,":[162],"network":[165,184],"constructed":[166],"sample":[170],"contains":[171],"more":[172],"than":[173],"edges":[179],"created":[185],"has":[191],"similar":[192],"degree":[193],"distribution.":[194]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2019,"cited_by_count":2},{"year":2017,"cited_by_count":2}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2016-12-16T00:00:00"}
