{"id":"https://openalex.org/W2803720263","doi":"https://doi.org/10.1145/3201064.3201066","title":"Guidelines for Online Network Crawling","display_name":"Guidelines for Online Network Crawling","publication_year":2018,"publication_date":"2018-05-15","ids":{"openalex":"https://openalex.org/W2803720263","doi":"https://doi.org/10.1145/3201064.3201066","mag":"2803720263"},"language":"en","primary_location":{"id":"doi:10.1145/3201064.3201066","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3201064.3201066","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 10th ACM Conference on Web Science","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/A5050296572","display_name":"Katchaguy Areekijseree","orcid":null},"institutions":[{"id":"https://openalex.org/I70983195","display_name":"Syracuse University","ror":"https://ror.org/025r5qe02","country_code":"US","type":"education","lineage":["https://openalex.org/I70983195"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Katchaguy Areekijseree","raw_affiliation_strings":["Syracuse University, Syracuse, NY, USA"],"affiliations":[{"raw_affiliation_string":"Syracuse University, Syracuse, NY, USA","institution_ids":["https://openalex.org/I70983195"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074046047","display_name":"Ricky Laishram","orcid":null},"institutions":[{"id":"https://openalex.org/I70983195","display_name":"Syracuse University","ror":"https://ror.org/025r5qe02","country_code":"US","type":"education","lineage":["https://openalex.org/I70983195"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ricky Laishram","raw_affiliation_strings":["Syracuse University, Syracuse, NY, USA"],"affiliations":[{"raw_affiliation_string":"Syracuse University, Syracuse, NY, USA","institution_ids":["https://openalex.org/I70983195"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5062221607","display_name":"Sucheta Soundarajan","orcid":"https://orcid.org/0000-0003-1166-4067"},"institutions":[{"id":"https://openalex.org/I70983195","display_name":"Syracuse University","ror":"https://ror.org/025r5qe02","country_code":"US","type":"education","lineage":["https://openalex.org/I70983195"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sucheta Soundarajan","raw_affiliation_strings":["Syracuse University, Syracuse, NY, USA"],"affiliations":[{"raw_affiliation_string":"Syracuse University, Syracuse, NY, USA","institution_ids":["https://openalex.org/I70983195"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5050296572"],"corresponding_institution_ids":["https://openalex.org/I70983195"],"apc_list":null,"apc_paid":null,"fwci":1.0557,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":{"value":0.76394032,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"57","last_page":"66"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10064","display_name":"Complex Network Analysis Techniques","score":0.9995999932289124,"subfield":{"id":"https://openalex.org/subfields/3109","display_name":"Statistical and Nonlinear Physics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10064","display_name":"Complex Network Analysis Techniques","score":0.9995999932289124,"subfield":{"id":"https://openalex.org/subfields/3109","display_name":"Statistical and Nonlinear Physics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10742","display_name":"Peer-to-Peer Network Technologies","score":0.9991999864578247,"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/T11478","display_name":"Caching and Content Delivery","score":0.9991999864578247,"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":0.9661543369293213},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8458443880081177},{"id":"https://openalex.org/keywords/node","display_name":"Node (physics)","score":0.5346070528030396},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.49994707107543945},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.49479812383651733},{"id":"https://openalex.org/keywords/community-structure","display_name":"Community structure","score":0.48999109864234924},{"id":"https://openalex.org/keywords/sampling","display_name":"Sampling (signal processing)","score":0.4472987949848175},{"id":"https://openalex.org/keywords/bandwidth","display_name":"Bandwidth (computing)","score":0.4385560154914856},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.43722549080848694},{"id":"https://openalex.org/keywords/social-network","display_name":"Social network (sociolinguistics)","score":0.43524104356765747},{"id":"https://openalex.org/keywords/web-crawler","display_name":"Web crawler","score":0.42523902654647827},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.25231945514678955},{"id":"https://openalex.org/keywords/social-media","display_name":"Social media","score":0.19821980595588684},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.17439985275268555}],"concepts":[{"id":"https://openalex.org/C100368936","wikidata":"https://www.wikidata.org/wiki/Q1411725","display_name":"Crawling","level":2,"score":0.9661543369293213},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8458443880081177},{"id":"https://openalex.org/C62611344","wikidata":"https://www.wikidata.org/wiki/Q1062658","display_name":"Node (physics)","level":2,"score":0.5346070528030396},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.49994707107543945},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.49479812383651733},{"id":"https://openalex.org/C133079900","wikidata":"https://www.wikidata.org/wiki/Q5155065","display_name":"Community structure","level":2,"score":0.48999109864234924},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.4472987949848175},{"id":"https://openalex.org/C2776257435","wikidata":"https://www.wikidata.org/wiki/Q1576430","display_name":"Bandwidth (computing)","level":2,"score":0.4385560154914856},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.43722549080848694},{"id":"https://openalex.org/C4727928","wikidata":"https://www.wikidata.org/wiki/Q17164759","display_name":"Social network (sociolinguistics)","level":3,"score":0.43524104356765747},{"id":"https://openalex.org/C13743948","wikidata":"https://www.wikidata.org/wiki/Q45842","display_name":"Web crawler","level":2,"score":0.42523902654647827},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.25231945514678955},{"id":"https://openalex.org/C518677369","wikidata":"https://www.wikidata.org/wiki/Q202833","display_name":"Social media","level":2,"score":0.19821980595588684},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.17439985275268555},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.0},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.0},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","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},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3201064.3201066","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3201064.3201066","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 10th ACM Conference on Web Science","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320338291","display_name":"Sandia National Laboratories","ror":"https://ror.org/01apwpt12"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W1556756413","https://openalex.org/W1973846084","https://openalex.org/W2023655578","https://openalex.org/W2026840599","https://openalex.org/W2042359627","https://openalex.org/W2064831732","https://openalex.org/W2087812679","https://openalex.org/W2089458547","https://openalex.org/W2101196063","https://openalex.org/W2106315062","https://openalex.org/W2115022330","https://openalex.org/W2121761994","https://openalex.org/W2131681506","https://openalex.org/W2146008005","https://openalex.org/W2146591355","https://openalex.org/W2158601853","https://openalex.org/W2171935404","https://openalex.org/W2302677616","https://openalex.org/W2963316155","https://openalex.org/W3099768174"],"related_works":["https://openalex.org/W2084213350","https://openalex.org/W2566658409","https://openalex.org/W3119324922","https://openalex.org/W2352686120","https://openalex.org/W2372594123","https://openalex.org/W2358310581","https://openalex.org/W2964752624","https://openalex.org/W2026132847","https://openalex.org/W4385695127","https://openalex.org/W2766789703"],"abstract_inverted_index":{"Over":[0],"the":[1,24,50,109,129,137],"past":[2],"two":[3],"decades,":[4],"online":[5,61,94],"social":[6],"networks":[7],"have":[8,65],"attracted":[9],"a":[10,29,80,88,122],"great":[11],"deal":[12],"of":[13,28,92,111,131,171],"attention":[14],"from":[15,98],"researchers.":[16],"However,":[17],"before":[18],"one":[19,31],"can":[20],"gain":[21],"insight":[22],"into":[23],"properties":[25],"or":[26,45,117],"structure":[27],"network,":[30],"must":[32],"first":[33],"collect":[34],"appropriate":[35,173],"data.":[36],"Data":[37],"collection":[38],"poses":[39],"several":[40,93],"challenges,":[41],"such":[42],"as":[43,113,119],"API":[44],"bandwidth":[46],"limits,":[47],"which":[48,56,74],"require":[49],"data":[51,115],"collector":[52],"to":[53,58,102,108,167],"carefully":[54],"consider":[55],"queries":[57],"make.":[59],"Many":[60],"network":[62,138,144],"crawling":[63,95,100],"methods":[64,101,133],"been":[66],"proposed,":[67],"but":[68],"it":[69],"is":[70],"not":[71],"always":[72],"clear":[73],"method":[75],"should":[76],"be":[77],"used":[78],"for":[79],"given":[81,121],"network.":[82],"In":[83],"this":[84],"paper,":[85],"we":[86],"perform":[87],"detailed,":[89],"hypothesis-driven":[90],"analysis":[91],"algorithms,":[96,105],"ranging":[97],"classical":[99],"modern,":[103],"state-of-the-art":[104],"with":[106],"respect":[107],"task":[110],"collecting":[112],"much":[114],"(nodes":[116],"edges)":[118],"possible":[120],"fixed":[123],"query":[124],"budget.":[125],"We":[126,140,155],"show":[127],"that":[128],"performance":[130],"these":[132],"depends":[134],"strongly":[135],"on":[136,158],"structure.":[139],"identify":[141],"three":[142],"relevant":[143],"characteristics:":[145],"community":[146,149],"separation,":[147],"average":[148,152],"size,":[150],"and":[151,161,164],"node":[153],"degree.":[154],"present":[156],"experiments":[157],"both":[159],"real":[160],"synthetic":[162],"networks,":[163],"provide":[165],"guidelines":[166],"researchers":[168],"regarding":[169],"selection":[170],"an":[172],"sampling":[174],"method.":[175]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
