{"id":"https://openalex.org/W2738509022","doi":"https://doi.org/10.1145/3102254.3102266","title":"Design, implementation and test of a flexible tor-oriented web mining toolkit","display_name":"Design, implementation and test of a flexible tor-oriented web mining toolkit","publication_year":2017,"publication_date":"2017-06-19","ids":{"openalex":"https://openalex.org/W2738509022","doi":"https://doi.org/10.1145/3102254.3102266","mag":"2738509022"},"language":"en","primary_location":{"id":"doi:10.1145/3102254.3102266","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3102254.3102266","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 7th International Conference on Web Intelligence, Mining and Semantics","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/A5005168115","display_name":"Alessandro Celestini","orcid":"https://orcid.org/0000-0002-8493-4550"},"institutions":[{"id":"https://openalex.org/I3005160176","display_name":"Institute for High Performance Computing and Networking","ror":"https://ror.org/04r5fge26","country_code":"IT","type":"facility","lineage":["https://openalex.org/I3005160176","https://openalex.org/I4210155236"]}],"countries":["IT"],"is_corresponding":true,"raw_author_name":"Alessandro Celestini","raw_affiliation_strings":["Institute for Applied Computing (IAC-CNR), Rome, Italy"],"affiliations":[{"raw_affiliation_string":"Institute for Applied Computing (IAC-CNR), Rome, Italy","institution_ids":["https://openalex.org/I3005160176"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5053439134","display_name":"Stefano Guarino","orcid":"https://orcid.org/0000-0002-1545-7711"},"institutions":[{"id":"https://openalex.org/I3005160176","display_name":"Institute for High Performance Computing and Networking","ror":"https://ror.org/04r5fge26","country_code":"IT","type":"facility","lineage":["https://openalex.org/I3005160176","https://openalex.org/I4210155236"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Stefano Guarino","raw_affiliation_strings":["Institute for Applied Computing (IAC-CNR), Rome, Italy"],"affiliations":[{"raw_affiliation_string":"Institute for Applied Computing (IAC-CNR), Rome, Italy","institution_ids":["https://openalex.org/I3005160176"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5005168115"],"corresponding_institution_ids":["https://openalex.org/I3005160176"],"apc_list":null,"apc_paid":null,"fwci":1.4509,"has_fulltext":false,"cited_by_count":12,"citation_normalized_percentile":{"value":0.86755603,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"10"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9972000122070312,"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/T11241","display_name":"Advanced Malware Detection Techniques","score":0.996999979019165,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/computer-science","display_name":"Computer science","score":0.8383119702339172},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.7412807941436768},{"id":"https://openalex.org/keywords/web-modeling","display_name":"Web modeling","score":0.6391195058822632},{"id":"https://openalex.org/keywords/data-web","display_name":"Data Web","score":0.5437750220298767},{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.5221041440963745},{"id":"https://openalex.org/keywords/web-development","display_name":"Web development","score":0.5117347240447998},{"id":"https://openalex.org/keywords/static-web-page","display_name":"Static web page","score":0.5103444457054138},{"id":"https://openalex.org/keywords/web-navigation","display_name":"Web navigation","score":0.5076557397842407},{"id":"https://openalex.org/keywords/web-mining","display_name":"Web mining","score":0.5056507587432861},{"id":"https://openalex.org/keywords/web-design","display_name":"Web design","score":0.4672033190727234},{"id":"https://openalex.org/keywords/web-server","display_name":"Web server","score":0.4643924832344055},{"id":"https://openalex.org/keywords/web-application-security","display_name":"Web application security","score":0.45613035559654236},{"id":"https://openalex.org/keywords/web-standards","display_name":"Web standards","score":0.4421405792236328},{"id":"https://openalex.org/keywords/suite","display_name":"Suite","score":0.4190230667591095},{"id":"https://openalex.org/keywords/download","display_name":"Download","score":0.41313767433166504},{"id":"https://openalex.org/keywords/web-service","display_name":"Web service","score":0.41250497102737427},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.35565751791000366},{"id":"https://openalex.org/keywords/the-internet","display_name":"The Internet","score":0.2815423607826233}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8383119702339172},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.7412807941436768},{"id":"https://openalex.org/C130436687","wikidata":"https://www.wikidata.org/wiki/Q7978591","display_name":"Web modeling","level":3,"score":0.6391195058822632},{"id":"https://openalex.org/C162005631","wikidata":"https://www.wikidata.org/wiki/Q54837","display_name":"Data Web","level":3,"score":0.5437750220298767},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.5221041440963745},{"id":"https://openalex.org/C79373723","wikidata":"https://www.wikidata.org/wiki/Q386275","display_name":"Web development","level":3,"score":0.5117347240447998},{"id":"https://openalex.org/C173576120","wikidata":"https://www.wikidata.org/wiki/Q2641220","display_name":"Static web page","level":4,"score":0.5103444457054138},{"id":"https://openalex.org/C61096286","wikidata":"https://www.wikidata.org/wiki/Q7978592","display_name":"Web navigation","level":3,"score":0.5076557397842407},{"id":"https://openalex.org/C197046077","wikidata":"https://www.wikidata.org/wiki/Q785337","display_name":"Web mining","level":3,"score":0.5056507587432861},{"id":"https://openalex.org/C521306242","wikidata":"https://www.wikidata.org/wiki/Q190637","display_name":"Web design","level":3,"score":0.4672033190727234},{"id":"https://openalex.org/C11392498","wikidata":"https://www.wikidata.org/wiki/Q11288","display_name":"Web server","level":3,"score":0.4643924832344055},{"id":"https://openalex.org/C59241245","wikidata":"https://www.wikidata.org/wiki/Q4781497","display_name":"Web application security","level":4,"score":0.45613035559654236},{"id":"https://openalex.org/C182321512","wikidata":"https://www.wikidata.org/wiki/Q1153289","display_name":"Web standards","level":3,"score":0.4421405792236328},{"id":"https://openalex.org/C79581498","wikidata":"https://www.wikidata.org/wiki/Q1367530","display_name":"Suite","level":2,"score":0.4190230667591095},{"id":"https://openalex.org/C2780154274","wikidata":"https://www.wikidata.org/wiki/Q7126717","display_name":"Download","level":2,"score":0.41313767433166504},{"id":"https://openalex.org/C35578498","wikidata":"https://www.wikidata.org/wiki/Q193424","display_name":"Web service","level":2,"score":0.41250497102737427},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.35565751791000366},{"id":"https://openalex.org/C110875604","wikidata":"https://www.wikidata.org/wiki/Q75","display_name":"The Internet","level":2,"score":0.2815423607826233},{"id":"https://openalex.org/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"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":1,"locations":[{"id":"doi:10.1145/3102254.3102266","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3102254.3102266","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 7th International Conference on Web Intelligence, Mining and Semantics","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5099999904632568,"id":"https://metadata.un.org/sdg/9","display_name":"Industry, innovation and infrastructure"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W256861921","https://openalex.org/W1514527998","https://openalex.org/W1545050218","https://openalex.org/W1613836731","https://openalex.org/W1614298861","https://openalex.org/W1655958391","https://openalex.org/W1880262756","https://openalex.org/W1989993068","https://openalex.org/W1994727615","https://openalex.org/W2000273502","https://openalex.org/W2030559659","https://openalex.org/W2031211716","https://openalex.org/W2056524697","https://openalex.org/W2063943022","https://openalex.org/W2070176704","https://openalex.org/W2080429359","https://openalex.org/W2102931907","https://openalex.org/W2115579680","https://openalex.org/W2129620481","https://openalex.org/W2142955537","https://openalex.org/W2147344024","https://openalex.org/W2148317291","https://openalex.org/W2150596521","https://openalex.org/W2156072898","https://openalex.org/W2163007546","https://openalex.org/W2258998514","https://openalex.org/W2266987713","https://openalex.org/W2269520727","https://openalex.org/W2283045161","https://openalex.org/W2326804586","https://openalex.org/W2417359092","https://openalex.org/W2737644180","https://openalex.org/W2911388033","https://openalex.org/W4231510805"],"related_works":["https://openalex.org/W132269582","https://openalex.org/W2800499880","https://openalex.org/W2015727217","https://openalex.org/W163338125","https://openalex.org/W2415191659","https://openalex.org/W2744329849","https://openalex.org/W2567626003","https://openalex.org/W2563863560","https://openalex.org/W4224286275","https://openalex.org/W2520851676"],"abstract_inverted_index":{"Searching":[0],"and":[1,16,32,55,60,68,135,156],"retrieving":[2],"information":[3],"from":[4,71],"the":[5,14,43,72,81,91,96,102,108,138,142,146,153,163,173],"Web":[6,19,99,114],"is":[7,86,110],"a":[8,53,113,166],"primary":[9],"activity":[10],"needed":[11],"to":[12,64,78,89,124,127,130,136],"monitor":[13],"development":[15],"usage":[17],"of":[18,45,98,141,145,158,165,175],"resources.":[20],"Possible":[21],"benefits":[22],"include":[23],"improving":[24],"user":[25],"experience":[26],"(e.g.":[27,36],"by":[28,37,42],"optimizing":[29],"query":[30],"results)":[31],"enforcing":[33],"data/user":[34],"security":[35],"identifying":[38],"harmful":[39],"websites).":[40],"Motivated":[41],"lack":[44],"ready-to-use":[46],"solutions,":[47],"in":[48,80,151],"this":[49],"paper":[50],"we":[51,161],"present":[52],"flexible":[54],"accessible":[56],"toolkit":[57,109],"for":[58],"structure":[59,140],"content":[61,126],"mining,":[62],"able":[63,123],"crawl,":[65],"download,":[66],"extract":[67],"index":[69],"resources":[70],"Web.":[73,147],"While":[74],"being":[75],"easily":[76],"configurable":[77],"work":[79],"\"surface\"":[82],"Web,":[83,94],"our":[84,159,176],"suite":[85],"specifically":[87],"tailored":[88],"explore":[90],"Tor":[92],"dark":[93],"i.e.":[95],"ensemble":[97],"servers":[100],"composing":[101],"world's":[103],"most":[104],"famous":[105],"darknet.":[106],"Notably,":[107],"not":[111],"just":[112],"scraper,":[115],"but":[116],"it":[117],"includes":[118],"two":[119],"mining":[120],"modules,":[121],"respectively":[122],"prepare":[125],"be":[128],"fed":[129],"an":[131],"(external)":[132],"semantic":[133],"engine,":[134],"reconstruct":[137],"graph":[139],"explored":[143],"portion":[144],"Other":[148],"than":[149],"discussing":[150],"detail":[152],"design,":[154],"features":[155],"performance":[157],"toolkit,":[160],"report":[162],"findings":[164],"preliminary":[167],"run":[168],"over":[169],"Tor,":[170],"that":[171],"clarify":[172],"potential":[174],"solution.":[177]},"counts_by_year":[{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":2},{"year":2021,"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"}
