{"id":"https://openalex.org/W2923438682","doi":null,"title":"Detection of Web API Content Scraping : An Empirical Study of Machine Learning Algorithms","display_name":"Detection of Web API Content Scraping : An Empirical Study of Machine Learning Algorithms","publication_year":2017,"publication_date":"2017-01-01","ids":{"openalex":"https://openalex.org/W2923438682","mag":"2923438682"},"language":"en","primary_location":{"id":"pmh:oai:DiVA.org:kth-210235","doi":null,"is_oa":true,"landing_page_url":"http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-210235","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,"listed_in":[],"host_organization":"https://openalex.org/I86987016","host_organization_name":"KTH Royal Institute of Technology","host_organization_lineage":["https://openalex.org/I86987016"],"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":"","raw_type":"info:eu-repo/semantics/bachelorThesis"},"volume":null,"type":"dissertation","is_traditional":true,"indexed_in":[],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-210235","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5027731495","display_name":"Dina Jawad","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Dina Jawad","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":["https://openalex.org/A5027731495"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"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/T12016","display_name":"Web Data Mining and Analysis","score":0.47269999980926514,"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":0.47269999980926514,"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":0.4480000138282776,"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/T11598","display_name":"Internet Traffic Analysis and Secure E-voting","score":0.020099999383091927,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/spotify-api","display_name":"Spotify API","score":0.8029999732971191},{"id":"https://openalex.org/keywords/random-forest","display_name":"random forest","score":0.8259999752044678},{"id":"https://openalex.org/keywords/classifier-comparison","display_name":"classifier comparison","score":0.609000027179718},{"id":"https://openalex.org/keywords/false-positive-rate","display_name":"false positive rate","score":0.7170000076293945},{"id":"https://openalex.org/keywords/minority-class-oversampling","display_name":"minority class oversampling","score":0.6439999938011169},{"id":"https://openalex.org/keywords/smote","display_name":"SMOTE","score":0.8790000081062317},{"id":"https://openalex.org/keywords/synthetic-data","display_name":"synthetic data","score":0.7919999957084656}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6500247716903687},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.6164577007293701},{"id":"https://openalex.org/C2776324614","wikidata":"https://www.wikidata.org/wiki/Q3948731","display_name":"Web content","level":3,"score":0.518997073173523},{"id":"https://openalex.org/C2778152352","wikidata":"https://www.wikidata.org/wiki/Q5165061","display_name":"Content (measure theory)","level":2,"score":0.4722178280353546},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3988458514213562},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.39300936460494995},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3755040764808655},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.37214550375938416},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.34856414794921875},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.32640939950942993},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1304911971092224},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.06233254075050354},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:DiVA.org:kth-210235","doi":null,"is_oa":true,"landing_page_url":"http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-210235","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,"listed_in":[],"host_organization":"https://openalex.org/I86987016","host_organization_name":"KTH Royal Institute of Technology","host_organization_lineage":["https://openalex.org/I86987016"],"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":"","raw_type":"info:eu-repo/semantics/bachelorThesis"},{"id":"mag:2923438682","doi":null,"is_oa":false,"landing_page_url":"http://www.diva-portal.org/smash/record.jsf?pid=diva2:1117695","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:DiVA.org:kth-210235","doi":null,"is_oa":true,"landing_page_url":"http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-210235","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,"listed_in":[],"host_organization":"https://openalex.org/I86987016","host_organization_name":"KTH Royal Institute of Technology","host_organization_lineage":["https://openalex.org/I86987016"],"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":"","raw_type":"info:eu-repo/semantics/bachelorThesis"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W51582649","https://openalex.org/W126199333","https://openalex.org/W1551909886","https://openalex.org/W1558402437","https://openalex.org/W1680392829","https://openalex.org/W1966493433","https://openalex.org/W1988790447","https://openalex.org/W2007085915","https://openalex.org/W2015928143","https://openalex.org/W2041185491","https://openalex.org/W2045049630","https://openalex.org/W2060472984","https://openalex.org/W2076723282","https://openalex.org/W2101234009","https://openalex.org/W2107589078","https://openalex.org/W2112995928","https://openalex.org/W2118978333","https://openalex.org/W2144182447","https://openalex.org/W2146841526","https://openalex.org/W2150093300","https://openalex.org/W2161742217","https://openalex.org/W2165669526","https://openalex.org/W2167710876","https://openalex.org/W2296719434","https://openalex.org/W2525985711","https://openalex.org/W2545049201","https://openalex.org/W2561784576","https://openalex.org/W2911964244"],"related_works":["https://openalex.org/W2900422759","https://openalex.org/W2803638390","https://openalex.org/W3136660186","https://openalex.org/W4375853925","https://openalex.org/W7030396115","https://openalex.org/W7222891710","https://openalex.org/W7151249859","https://openalex.org/W4296915926","https://openalex.org/W4392132671","https://openalex.org/W4412603234"],"abstract_inverted_index":{"Scraping":[0],"is":[1,18,55,171,206],"known":[2],"to":[3,6,36,64,78,96,129,138],"be":[4,193],"difficult":[5],"detect":[7],"and":[8,205,210],"prevent,":[9],"especially":[10],"in":[11,19,127,141],"the":[12,20,28,80,97,115,130,135,151,161,174,188,212,217],"context":[13],"of":[14,22,83,103,119,158,163,187,216],"web":[15,34,51,74,98,189],"APIs.":[16],"It":[17],"interest":[21],"organisations":[23],"that":[24,88,147,173],"rely":[25],"heavily":[26],"on":[27,70],"content":[29,39,53],"they":[30],"provide":[31],"through":[32],"their":[33,38],"APIs":[35],"protect":[37],"from":[40,72],"scrapers.":[41],"In":[42],"this":[43,167],"thesis,":[44],"a":[45,101,179,200],"machine":[46,59],"learning":[47,60],"approach":[48],"towards":[49],"detecting":[50],"API":[52,99,190],"scrapers":[54,123],"proposed.":[56],"Three":[57],"supervised":[58],"algorithms":[61],"were":[62,109],"evaluated":[63],"see":[65],"which":[66],"would":[67],"perform":[68,139],"better":[69,152],"data":[71,87,121],"Spotify's":[73],"API.":[75],"Data":[76],"used":[77,137],"evaluate":[79],"classifiers":[81],"consisted":[82,118],"aggregated":[84],"HTTP":[85,94],"request":[86],"describes":[89],"each":[90,112],"application":[91],"having":[92],"sent":[93],"requests":[95],"over":[100],"span":[102],"two":[104],"weeks.":[105],"Two":[106],"separate":[107],"experiments":[108],"performed":[110],"for":[111,122],"classifier,":[113,153],"where":[114],"second":[116],"experiment":[117,142],"synthetic":[120,164],"(the":[124],"minority":[125],"class)":[126],"addition":[128],"original":[131],"dataset.":[132],"SMOTE":[133],"was":[134,150],"algorithm":[136],"oversampling":[140],"two.":[143],"The":[144,195],"results":[145],"show":[146],"Random":[148,196],"Forest":[149,197],"with":[154],"an":[155],"MCC":[156],"value":[157],"0.692,":[159],"without":[160],"use":[162],"data.":[165],"For":[166],"particular":[168],"problem,":[169],"it":[170],"crucial":[172],"classifier":[175,198,214],"does":[176],"not":[177,192],"have":[178],"high":[180],"false":[181,202],"positive":[182,203],"rate":[183,204],"as":[184],"legitimate":[185],"usage":[186],"should":[191],"blocked.":[194],"has":[199],"low":[201],"therefore":[207],"more":[208],"favourable,":[209],"considered":[211],"strongest":[213],"out":[215],"three":[218],"examined.":[219]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2019,"cited_by_count":1}],"updated_date":"2026-10-16T09:59:22.235173","created_date":"2019-04-01T00:00:00"}