{"id":"https://openalex.org/W2080183019","doi":"https://doi.org/10.1145/2184512.2184568","title":"Identifying features to improve real time clustering and domain blacklisting","display_name":"Identifying features to improve real time clustering and domain blacklisting","publication_year":2012,"publication_date":"2012-03-29","ids":{"openalex":"https://openalex.org/W2080183019","doi":"https://doi.org/10.1145/2184512.2184568","mag":"2080183019"},"language":"en","primary_location":{"id":"doi:10.1145/2184512.2184568","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2184512.2184568","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 50th Annual Southeast Regional Conference","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/A5019287027","display_name":"Soma Halder","orcid":null},"institutions":[{"id":"https://openalex.org/I32389192","display_name":"University of Alabama at Birmingham","ror":"https://ror.org/008s83205","country_code":"US","type":"education","lineage":["https://openalex.org/I32389192"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Soma Halder","raw_affiliation_strings":["Univ. of Alabama at Birmingham, Birmingham, Alabama"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Univ. of Alabama at Birmingham, Birmingham, Alabama","institution_ids":["https://openalex.org/I32389192"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109408655","display_name":"Richa Tiwari","orcid":"https://orcid.org/0000-0003-3069-8510"},"institutions":[{"id":"https://openalex.org/I32389192","display_name":"University of Alabama at Birmingham","ror":"https://ror.org/008s83205","country_code":"US","type":"education","lineage":["https://openalex.org/I32389192"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Richa Tiwari","raw_affiliation_strings":["Univ. of Alabama at Birmingham, Birmingham, Alabama"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Univ. of Alabama at Birmingham, Birmingham, Alabama","institution_ids":["https://openalex.org/I32389192"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5032807283","display_name":"Alan Sprague","orcid":"https://orcid.org/0000-0002-3951-3271"},"institutions":[{"id":"https://openalex.org/I32389192","display_name":"University of Alabama at Birmingham","ror":"https://ror.org/008s83205","country_code":"US","type":"education","lineage":["https://openalex.org/I32389192"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Alan Sprague","raw_affiliation_strings":["Univ. of Alabama at Birmingham, Birmingham, Alabama"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Univ. of Alabama at Birmingham, Birmingham, Alabama","institution_ids":["https://openalex.org/I32389192"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I32389192"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.17891893,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"238","last_page":"243"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11644","display_name":"Spam and Phishing Detection","score":0.9998999834060669,"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/T11644","display_name":"Spam and Phishing Detection","score":0.9998999834060669,"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/T12016","display_name":"Web Data Mining and Analysis","score":0.9990000128746033,"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/T10400","display_name":"Network Security and Intrusion Detection","score":0.9986000061035156,"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/blacklisting","display_name":"Blacklisting","score":0.9922802448272705},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8547018766403198},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.7843436002731323},{"id":"https://openalex.org/keywords/blacklist","display_name":"Blacklist","score":0.6277843117713928},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.5752037763595581},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.5275729894638062},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5235497355461121},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.478385329246521},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.41732481122016907},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.37723076343536377},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.33966249227523804},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.19798418879508972},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.1419304609298706}],"concepts":[{"id":"https://openalex.org/C2779797433","wikidata":"https://www.wikidata.org/wiki/Q632959","display_name":"Blacklisting","level":2,"score":0.9922802448272705},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8547018766403198},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.7843436002731323},{"id":"https://openalex.org/C2781345505","wikidata":"https://www.wikidata.org/wiki/Q2535979","display_name":"Blacklist","level":2,"score":0.6277843117713928},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.5752037763595581},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5275729894638062},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5235497355461121},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.478385329246521},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.41732481122016907},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.37723076343536377},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.33966249227523804},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.19798418879508972},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.1419304609298706},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2184512.2184568","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2184512.2184568","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 50th Annual Southeast Regional Conference","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W92053470","https://openalex.org/W205142145","https://openalex.org/W1531117709","https://openalex.org/W1550514379","https://openalex.org/W1775772884","https://openalex.org/W1956559956","https://openalex.org/W2097606805","https://openalex.org/W2110548175","https://openalex.org/W2133990480","https://openalex.org/W2325227998","https://openalex.org/W2706078957","https://openalex.org/W2909435694"],"related_works":["https://openalex.org/W2181543702","https://openalex.org/W3172840274","https://openalex.org/W4241417517","https://openalex.org/W2991976289","https://openalex.org/W3037489623","https://openalex.org/W2146351192","https://openalex.org/W4379624358","https://openalex.org/W3112398763","https://openalex.org/W178883471","https://openalex.org/W2980552833"],"abstract_inverted_index":{"Feature":[0],"analysis":[1],"is":[2],"an":[3],"important":[4],"task":[5],"in":[6,70,104],"the":[7,78,99],"area":[8],"of":[9,59,77,91,101,106],"information":[10,114],"extraction.":[11],"Appropriate":[12],"features":[13,31,54,69,87,103],"give":[14],"improved":[15],"performance":[16],"for":[17],"any":[18],"classification":[19],"or":[20],"clustering":[21,90],"algorithm.":[22],"In":[23],"this":[24,71],"paper":[25,72],"we":[26],"try":[27],"to":[28,36],"analyze":[29],"different":[30],"that":[32],"can":[33],"be":[34],"used":[35,56],"cluster":[37],"spam":[38,92],"emails":[39],"at":[40],"real":[41],"time":[42],"and":[43,75,83,115],"thus":[44,116],"improve":[45,117],"IP":[46,60],"blacklisting.":[47,119],"Domain":[48],"blacklisting":[49],"becomes":[50],"easy":[51],"when":[52],"these":[53,102],"are":[55],"because":[57],"masses":[58],"address":[61],"get":[62],"grouped":[63],"easily.":[64],"We":[65,97],"have":[66],"explored":[67],"several":[68],"like":[73],"sender":[74],"subject":[76],"email;":[79],"email":[80],"attachments,":[81],"stylistic":[82],"semantic":[84],"features.":[85],"These":[86],"ensure":[88],"appropriate":[89],"originating":[93],"from":[94],"dominant":[95],"hosts.":[96],"compute":[98],"effectiveness":[100],"terms":[105],"how":[107],"well":[108],"they":[109],"group":[110],"emails,":[111],"gather":[112],"domain/IP":[113],"domain":[118]},"counts_by_year":[],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-10-10T00:00:00"}