{"id":"https://openalex.org/W602665507","doi":null,"title":"Data Preparation for Social Network Mining and Analysis","display_name":"Data Preparation for Social Network Mining and Analysis","publication_year":2014,"publication_date":"2014-01-01","ids":{"openalex":"https://openalex.org/W602665507","mag":"602665507"},"language":"en","primary_location":{"id":"pmh:oai:uilis.unsyiah.ac.id:1029","doi":null,"is_oa":true,"landing_page_url":"http://uilis.unsyiah.ac.id/opentheses/items/show/1029","pdf_url":"http://uilis.unsyiah.ac.id/opentheses/items/show/1029","source":{"id":"https://openalex.org/S4377196378","display_name":"UPT. Syiah Kuala University Library (Syiah Kuala University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I187494767","host_organization_name":"Universitas Syiah Kuala","host_organization_lineage":["https://openalex.org/I187494767"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Dissertations and Theses Collection (Open Access)","raw_type":"text"},"volume":null,"type":"article","is_traditional":true,"indexed_in":[],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://uilis.unsyiah.ac.id/opentheses/items/show/1029","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Yazhe Wang","orcid":"https://orcid.org/0000-0002-1709-5283","observed_orcids":["https://orcid.org/0000-0002-1709-5283"]},"institutions":[{"id":"https://openalex.org/I79891267","display_name":"Singapore Management University","ror":"https://ror.org/050qmg959","country_code":"SG","type":"education","lineage":["https://openalex.org/I79891267"]}],"countries":["SG"],"is_corresponding":true,"raw_author_name":"Yazhe Wang","raw_affiliation_strings":["Singapore Management University"],"raw_orcid":"https://orcid.org/0000-0002-1709-5283","affiliations":[{"raw_affiliation_string":"Singapore Management University","institution_ids":["https://openalex.org/I79891267"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I79891267"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":{"value":0.0,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":88,"max":93},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10764","display_name":"Privacy-Preserving Technologies in Data","score":0.9136000275611877,"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/T10764","display_name":"Privacy-Preserving Technologies in Data","score":0.9136000275611877,"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/T14435","display_name":"Information Retrieval and Data Mining","score":0.03229999914765358,"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/T11045","display_name":"Privacy, Security, and Data Protection","score":0.01679999940097332,"subfield":{"id":"https://openalex.org/subfields/3312","display_name":"Sociology and Political Science"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/social-network-mining","display_name":"social network mining","score":0.6909999847412109},{"id":"https://openalex.org/keywords/sampling-bias","display_name":"sampling bias","score":0.6620000004768372},{"id":"https://openalex.org/keywords/data-collection","display_name":"data collection","score":0.4189999997615814},{"id":"https://openalex.org/keywords/identity-privacy","display_name":"identity privacy","score":0.6899999976158142},{"id":"https://openalex.org/keywords/k-anonymity","display_name":"k-anonymity","score":0.9010000228881836},{"id":"https://openalex.org/keywords/utility-preservation","display_name":"utility preservation","score":0.5580000281333923},{"id":"https://openalex.org/keywords/data-reduction","display_name":"data reduction","score":0.6060000061988831},{"id":"https://openalex.org/keywords/user-generated-content","display_name":"user-generated content","score":0.597000002861023},{"id":"https://openalex.org/keywords/twitter","display_name":"Twitter","score":0.3720000088214874},{"id":"https://openalex.org/keywords/facebook","display_name":"Facebook","score":0.8809999823570251},{"id":"https://openalex.org/keywords/linkedin","display_name":"LinkedIn","score":0.9629999995231628}],"concepts":[{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.7192655801773071},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7035619616508484},{"id":"https://openalex.org/C132964779","wikidata":"https://www.wikidata.org/wiki/Q2110223","display_name":"Raw data","level":2,"score":0.6694395542144775},{"id":"https://openalex.org/C4727928","wikidata":"https://www.wikidata.org/wiki/Q17164759","display_name":"Social network (sociolinguistics)","level":3,"score":0.6311683654785156},{"id":"https://openalex.org/C2780615836","wikidata":"https://www.wikidata.org/wiki/Q2471869","display_name":"USable","level":2,"score":0.5976759791374207},{"id":"https://openalex.org/C133462117","wikidata":"https://www.wikidata.org/wiki/Q4929239","display_name":"Data collection","level":2,"score":0.5899860858917236},{"id":"https://openalex.org/C24756922","wikidata":"https://www.wikidata.org/wiki/Q1757694","display_name":"Data quality","level":3,"score":0.5752767324447632},{"id":"https://openalex.org/C2780586970","wikidata":"https://www.wikidata.org/wiki/Q1357284","display_name":"Popularity","level":2,"score":0.5656788349151611},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5478255152702332},{"id":"https://openalex.org/C114713312","wikidata":"https://www.wikidata.org/wiki/Q7551269","display_name":"Social network analysis","level":3,"score":0.5456947684288025},{"id":"https://openalex.org/C10551718","wikidata":"https://www.wikidata.org/wiki/Q5227332","display_name":"Data pre-processing","level":2,"score":0.5187625885009766},{"id":"https://openalex.org/C518677369","wikidata":"https://www.wikidata.org/wiki/Q202833","display_name":"Social media","level":2,"score":0.45489946007728577},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.4524962306022644},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.2505444288253784},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.20056626200675964},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.0},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","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/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"pmh:oai:uilis.unsyiah.ac.id:1029","doi":null,"is_oa":true,"landing_page_url":"http://uilis.unsyiah.ac.id/opentheses/items/show/1029","pdf_url":"http://uilis.unsyiah.ac.id/opentheses/items/show/1029","source":{"id":"https://openalex.org/S4377196378","display_name":"UPT. Syiah Kuala University Library (Syiah Kuala University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I187494767","host_organization_name":"Universitas Syiah Kuala","host_organization_lineage":["https://openalex.org/I187494767"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Dissertations and Theses Collection (Open Access)","raw_type":"text"},{"id":"pmh:oai:ink.library.smu.edu.sg:etd_coll-1100","doi":null,"is_oa":false,"landing_page_url":"https://ink.library.smu.edu.sg/cgi/viewcontent.cgi?article=1100&context=etd_coll","pdf_url":null,"source":{"id":"https://openalex.org/S4306401925","display_name":"Singapore Management University Institutional Knowledge (InK) (Singapore Management University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I79891267","host_organization_name":"Singapore Management University","host_organization_lineage":["https://openalex.org/I79891267"],"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":"PhD Dissertation"},{"id":"mag:602665507","doi":null,"is_oa":false,"landing_page_url":"https://ink.library.smu.edu.sg/cgi/viewcontent.cgi?article=1100&context=etd_coll","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":null}],"best_oa_location":{"id":"pmh:oai:uilis.unsyiah.ac.id:1029","doi":null,"is_oa":true,"landing_page_url":"http://uilis.unsyiah.ac.id/opentheses/items/show/1029","pdf_url":"http://uilis.unsyiah.ac.id/opentheses/items/show/1029","source":{"id":"https://openalex.org/S4377196378","display_name":"UPT. Syiah Kuala University Library (Syiah Kuala University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I187494767","host_organization_name":"Universitas Syiah Kuala","host_organization_lineage":["https://openalex.org/I187494767"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Dissertations and Theses Collection (Open Access)","raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W602665507.pdf","grobid_xml":"https://content.openalex.org/works/W602665507.grobid-xml"},"referenced_works_count":94,"referenced_works":["https://openalex.org/W20667085","https://openalex.org/W153069569","https://openalex.org/W204323566","https://openalex.org/W1491317234","https://openalex.org/W1517590677","https://openalex.org/W1526460642","https://openalex.org/W1533841329","https://openalex.org/W1549390321","https://openalex.org/W1581750077","https://openalex.org/W1587629899","https://openalex.org/W1669474105","https://openalex.org/W1873763122","https://openalex.org/W1896743484","https://openalex.org/W1964878798","https://openalex.org/W1965936846","https://openalex.org/W1967579779","https://openalex.org/W1969890816","https://openalex.org/W1976320242","https://openalex.org/W1977843657","https://openalex.org/W1986678144","https://openalex.org/W1986697120","https://openalex.org/W1986828474","https://openalex.org/W1992263322","https://openalex.org/W1998091733","https://openalex.org/W1998801249","https://openalex.org/W2000200507","https://openalex.org/W2010273307","https://openalex.org/W2017509273","https://openalex.org/W2018165284","https://openalex.org/W2019331423","https://openalex.org/W2029852131","https://openalex.org/W2032186932","https://openalex.org/W2033995706","https://openalex.org/W2046804949","https://openalex.org/W2047624089","https://openalex.org/W2047940964","https://openalex.org/W2060009247","https://openalex.org/W2061901927","https://openalex.org/W2065228400","https://openalex.org/W2071776923","https://openalex.org/W2084012970","https://openalex.org/W2089077498","https://openalex.org/W2089458547","https://openalex.org/W2096296626","https://openalex.org/W2101196063","https://openalex.org/W2108614537","https://openalex.org/W2109369020","https://openalex.org/W2113401427","https://openalex.org/W2114734373","https://openalex.org/W2115022330","https://openalex.org/W2115209166","https://openalex.org/W2117410972","https://openalex.org/W2118519969","https://openalex.org/W2119404697","https://openalex.org/W2121761994","https://openalex.org/W2122710250","https://openalex.org/W2124499489","https://openalex.org/W2124849257","https://openalex.org/W2127048411","https://openalex.org/W2128248866","https://openalex.org/W2136486572","https://openalex.org/W2137135938","https://openalex.org/W2137349054","https://openalex.org/W2137845970","https://openalex.org/W2139575250","https://openalex.org/W2140096141","https://openalex.org/W2143445293","https://openalex.org/W2144143615","https://openalex.org/W2146008005","https://openalex.org/W2147734964","https://openalex.org/W2149510050","https://openalex.org/W2150611147","https://openalex.org/W2151961366","https://openalex.org/W2152284345","https://openalex.org/W2153910905","https://openalex.org/W2155058903","https://openalex.org/W2158908968","https://openalex.org/W2159024459","https://openalex.org/W2159397589","https://openalex.org/W2163263459","https://openalex.org/W2165081249","https://openalex.org/W2165515835","https://openalex.org/W2165971212","https://openalex.org/W2168332560","https://openalex.org/W2168433392","https://openalex.org/W2169861334","https://openalex.org/W2171468534","https://openalex.org/W2171935404","https://openalex.org/W2256977455","https://openalex.org/W2406036028","https://openalex.org/W2481169411","https://openalex.org/W2542727820","https://openalex.org/W2579030831","https://openalex.org/W3122139608"],"related_works":["https://openalex.org/W2894118911","https://openalex.org/W2481169411","https://openalex.org/W2942187464","https://openalex.org/W4298401195","https://openalex.org/W3165711611","https://openalex.org/W2488082082","https://openalex.org/W2780195716","https://openalex.org/W2809487870","https://openalex.org/W126603771","https://openalex.org/W6903499668"],"abstract_inverted_index":{"This":[0],"dissertation":[1,525],"studies":[2],"the":[3,106,161,174,190,222,227,233,236,241,249,253,271,274,277,295,300,316,335,352,356,360,386,395,420,465,480,512,527,542,580,589],"problem":[4,188,293,393],"of":[5,34,37,61,139,154,160,224,232,240,252,260,273,309,319,345,355,363,388,422,436,468,514,529,541,583,591],"preparing":[6],"good-quality":[7],"social":[8,18,38,65,73,112,182,194,211,218,265,331,367,379,455,533,546,560,572,584,592],"network":[9,39,74,113,183,195,219,266,332,374,483,489,534,547,561,573,585,593],"data":[10,12,40,46,75,86,114,123,131,144,146,148,151,175,178,184,196,261,280,288,301,401,530,563],"for":[11,45,130,193,226,284,532,551,564],"analysis":[13,47,89,134,242,259,535],"and":[14,24,48,54,69,80,88,108,124,133,150,177,202,229,238,281,337,369,384,414,536,587],"mining.":[15],"Modern":[16],"online":[17],"networks":[19,212,368,380,407,437,456,516],"such":[20,63],"as":[21,64,119],"Twitter,":[22],"Facebook,":[23],"LinkedIn":[25],"have":[26],"rapidly":[27],"grown":[28],"in":[29,57,82,91,181,248,286,311,329,398,464,523,545],"popularity.":[30],"The":[31,186,291,391],"consequent":[32],"availability":[33],"a":[35,58,306,320,330,473,488,495],"wealth":[36],"provides":[41,549,575],"an":[42,257],"unprecedented":[43],"opportunity":[44],"mining":[49,87,97,132,289,537],"researchers":[50],"to":[51,173,269,276,324,333,377,408,553,557,577],"determine":[52],"useful":[53],"actionable":[55],"information":[56,318],"wide":[59],"variety":[60],"fields":[62],"sciences,":[66],"marketing,":[67],"management,":[68],"security.":[70],"However,":[71],"raw":[72,122,162],"are":[76],"vast,":[77],"noisy,":[78],"distributed,":[79],"sensitive":[81],"nature,":[83],"which":[84,155,312],"challenge":[85],"tasks":[90],"storage,":[92],"efficiency,":[93],"accuracy,":[94],"etc.":[95],"Many":[96],"algorithms":[98,376,405,444],"cannot":[99,431,452],"operate":[100],"or":[101,555],"generate":[102],"accurate":[103],"results":[104],"on":[105,214,366,447,482,502,569],"vast":[107],"messy":[109],"data.":[110,163,594],"Thus":[111],"preparation":[115,137,531],"deserves":[116],"special":[117],"attention":[118],"it":[120],"processes":[121],"transforms":[125],"them":[126],"into":[127],"usable":[128],"forms":[129],"tasks.":[135,290,538],"Data":[136],"consists":[138],"four":[140],"main":[141],"steps,":[142],"namely":[143],"collection,":[145],"cleaning,":[147],"reduction,":[149],"conversion,":[152],"each":[153],"deals":[156],"with":[157,438,457,518],"different":[158],"challenges":[159],"In":[164,351],"this":[165,246,343,427,448,462,469,503,524],"dissertation,":[166,254,357,470],"we":[167,255,358,471],"consider":[168],"three":[169],"important":[170],"problems":[171],"related":[172],"collection":[176,548],"conversion":[179,302,375,490,574],"steps":[180],"preparation.":[185],"first":[187,250],"is":[189,294,394],"sampling":[191,543],"issue":[192,298,397,544],"collection.":[197],"Restricted":[198],"by":[199,418,487],"processing":[200],"power":[201],"resources,":[203],"most":[204],"research":[205],"that":[206,477],"analyzes":[207],"user-generated":[208],"content":[209,562],"from":[210,264],"relies":[213],"samples":[215,234,262,275],"obtained":[216,263],"via":[217,411],"APIs.":[220],"But":[221],"lack":[223],"consideration":[225],"quality":[228],"potential":[230,283,361],"bias":[231],"reduces":[235],"effectiveness":[237],"validity":[239],"results.":[243],"To":[244,460],"fill":[245],"gap,":[247],"work":[251,354,467,522,568],"perform":[256],"exploratory":[258],"stream":[267],"APIs":[268],"understand":[270],"representativeness":[272],"corresponding":[278],"complete":[279],"their":[282,565],"use":[285,554,558],"various":[287],"second":[292,353],"privacy":[296,399,410,570,582],"protection":[297],"at":[299],"step.":[303],"We":[304,341,425,492],"discover":[305],"new":[307,474,504],"type":[308,344],"attacks":[310,346,365,383],"malicious":[313],"adversaries":[314],"utilize":[315],"connection":[317,347],"victim":[321],"(anonymous)":[322],"user":[323,336],"some":[325],"known":[326],"public":[327],"users":[328,586],"re-identify":[334],"compromise":[338],"identity":[339,581],"privacy.":[340],"name":[342],"fingerprint":[348],"(CFP)":[349],"attacks.":[350],"investigate":[359],"risk":[362],"CFP":[364,382],"propose":[370,472],"two":[371],"efficient":[372],"k-anonymity-based":[373],"protect":[378,409,579],"against":[381],"preserve":[385,416],"utility":[387,396,417,429,434,450,475,505,513,590],"converted":[389],"networks.":[390],"third":[392,466],"preserving":[400,571],"conversion.":[402],"Existing":[403],"k-anonymization":[404,443],"convert":[406],"modifying":[412],"edges,":[413],"they":[415],"minimizing":[419],"number":[421],"edges":[423],"modified.":[424],"find":[426],"simple":[428,449],"model":[430,451],"reflect":[432],"real":[433],"changes":[435],"complex":[439],"structure.":[440],"Thus,":[441],"existing":[442,519],"designed":[445],"based":[446,501],"guarantee":[453],"generating":[454],"high":[458],"utility.":[459],"solve":[461],"problem,":[463],"benchmark":[476],"directly":[478],"measures":[479],"change":[481],"community":[484],"structure":[485],"caused":[486],"algorithm.":[491],"also":[493],"design":[494],"general":[496],"k-":[497],"anonymization":[498],"algorithm":[499,508],"framework":[500],"model.":[506],"Our":[507,521,539,567],"can":[509],"significantly":[510],"improve":[511],"generated":[515],"compared":[517],"algorithms.":[520],"emphasizes":[526],"importance":[528],"study":[540],"guidelines":[550],"people":[552],"not":[556],"sampled":[559],"research.":[566],"methods":[576],"better":[578],"maintain":[588]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2020,"cited_by_count":1}],"updated_date":"2026-10-14T16:39:01.820549","created_date":"2016-06-24T00:00:00"}