{"id":"https://openalex.org/W1987262936","doi":"https://doi.org/10.1142/s0218213007003692","title":"WORDS VERSUS CHARACTER N-GRAMS FOR ANTI-SPAM FILTERING","display_name":"WORDS VERSUS CHARACTER N-GRAMS FOR ANTI-SPAM FILTERING","publication_year":2007,"publication_date":"2007-12-01","ids":{"openalex":"https://openalex.org/W1987262936","doi":"https://doi.org/10.1142/s0218213007003692","mag":"1987262936"},"language":"en","primary_location":{"id":"doi:10.1142/s0218213007003692","is_oa":false,"landing_page_url":"https://doi.org/10.1142/s0218213007003692","pdf_url":null,"source":{"id":"https://openalex.org/S178780388","display_name":"International Journal of Artificial Intelligence Tools","issn_l":"0218-2130","issn":["0218-2130","1793-6349"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319815","host_organization_name":"World Scientific","host_organization_lineage":["https://openalex.org/P4310319815"],"host_organization_lineage_names":["World Scientific"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal on Artificial Intelligence Tools","raw_type":"journal-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/A5000360020","display_name":"Ioannis Kanaris","orcid":null},"institutions":[{"id":"https://openalex.org/I98805295","display_name":"University of the Aegean","ror":"https://ror.org/03zsp3p94","country_code":"GR","type":"education","lineage":["https://openalex.org/I98805295"]}],"countries":["GR"],"is_corresponding":false,"raw_author_name":"IOANNIS KANARIS","raw_affiliation_strings":["Department of Information and Communication Systems Eng., University of the Aegean, Karlovassi, Samos \u2013 83200, Greece","Department of Information and Communication Systems Engineering University of the Aegean Karlovassi Samos 83200 Greece"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Information and Communication Systems Eng., University of the Aegean, Karlovassi, Samos \u2013 83200, Greece","institution_ids":["https://openalex.org/I98805295"]},{"raw_affiliation_string":"Department of Information and Communication Systems Engineering University of the Aegean Karlovassi Samos 83200 Greece","institution_ids":["https://openalex.org/I98805295"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027134695","display_name":"Konstantinos Kanaris","orcid":null},"institutions":[{"id":"https://openalex.org/I98805295","display_name":"University of the Aegean","ror":"https://ror.org/03zsp3p94","country_code":"GR","type":"education","lineage":["https://openalex.org/I98805295"]}],"countries":["GR"],"is_corresponding":false,"raw_author_name":"KONSTANTINOS KANARIS","raw_affiliation_strings":["Department of Information and Communication Systems Eng., University of the Aegean, Karlovassi, Samos \u2013 83200, Greece","Department of Information and Communication Systems Engineering University of the Aegean Karlovassi Samos 83200 Greece"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Information and Communication Systems Eng., University of the Aegean, Karlovassi, Samos \u2013 83200, Greece","institution_ids":["https://openalex.org/I98805295"]},{"raw_affiliation_string":"Department of Information and Communication Systems Engineering University of the Aegean Karlovassi Samos 83200 Greece","institution_ids":["https://openalex.org/I98805295"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037618433","display_name":"IOANNIS HOUVARDAS","orcid":null},"institutions":[{"id":"https://openalex.org/I98805295","display_name":"University of the Aegean","ror":"https://ror.org/03zsp3p94","country_code":"GR","type":"education","lineage":["https://openalex.org/I98805295"]}],"countries":["GR"],"is_corresponding":false,"raw_author_name":"IOANNIS HOUVARDAS","raw_affiliation_strings":["Department of Information and Communication Systems Eng., University of the Aegean, Karlovassi, Samos \u2013 83200, Greece","Department of Information and Communication Systems Engineering University of the Aegean Karlovassi Samos 83200 Greece"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Information and Communication Systems Eng., University of the Aegean, Karlovassi, Samos \u2013 83200, Greece","institution_ids":["https://openalex.org/I98805295"]},{"raw_affiliation_string":"Department of Information and Communication Systems Engineering University of the Aegean Karlovassi Samos 83200 Greece","institution_ids":["https://openalex.org/I98805295"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5061737423","display_name":"Efstathios Stamatatos","orcid":"https://orcid.org/0000-0002-1336-9128"},"institutions":[{"id":"https://openalex.org/I98805295","display_name":"University of the Aegean","ror":"https://ror.org/03zsp3p94","country_code":"GR","type":"education","lineage":["https://openalex.org/I98805295"]}],"countries":["GR"],"is_corresponding":false,"raw_author_name":"EFSTATHIOS STAMATATOS","raw_affiliation_strings":["Department of Information and Communication Systems Eng., University of the Aegean, Karlovassi, Samos \u2013 83200, Greece","Department of Information and Communication Systems Engineering University of the Aegean Karlovassi Samos 83200 Greece"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Information and Communication Systems Eng., University of the Aegean, Karlovassi, Samos \u2013 83200, Greece","institution_ids":["https://openalex.org/I98805295"]},{"raw_affiliation_string":"Department of Information and Communication Systems Engineering University of the Aegean Karlovassi Samos 83200 Greece","institution_ids":["https://openalex.org/I98805295"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I98805295"],"apc_list":null,"apc_paid":null,"fwci":4.117,"has_fulltext":false,"cited_by_count":93,"citation_normalized_percentile":{"value":0.94055614,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":100},"biblio":{"volume":"16","issue":"06","first_page":"1047","last_page":"1067"},"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/T12380","display_name":"Authorship Attribution and Profiling","score":0.9995999932289124,"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/T11550","display_name":"Text and Document Classification Technologies","score":0.9987000226974487,"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/computer-science","display_name":"Computer science","score":0.904618501663208},{"id":"https://openalex.org/keywords/character","display_name":"Character (mathematics)","score":0.7710151672363281},{"id":"https://openalex.org/keywords/security-token","display_name":"Security token","score":0.76141756772995},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.6406604051589966},{"id":"https://openalex.org/keywords/punctuation","display_name":"Punctuation","score":0.6323280334472656},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.6212252378463745},{"id":"https://openalex.org/keywords/bag-of-words-model","display_name":"Bag-of-words model","score":0.5874910950660706},{"id":"https://openalex.org/keywords/curse-of-dimensionality","display_name":"Curse of dimensionality","score":0.5740797519683838},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5724937915802002},{"id":"https://openalex.org/keywords/variety","display_name":"Variety (cybernetics)","score":0.5480228066444397},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5461711287498474},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4982576370239258},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3270278573036194},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.06779736280441284}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.904618501663208},{"id":"https://openalex.org/C2780861071","wikidata":"https://www.wikidata.org/wiki/Q1062934","display_name":"Character (mathematics)","level":2,"score":0.7710151672363281},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.76141756772995},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.6406604051589966},{"id":"https://openalex.org/C540372491","wikidata":"https://www.wikidata.org/wiki/Q82622","display_name":"Punctuation","level":2,"score":0.6323280334472656},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6212252378463745},{"id":"https://openalex.org/C13672336","wikidata":"https://www.wikidata.org/wiki/Q3460803","display_name":"Bag-of-words model","level":2,"score":0.5874910950660706},{"id":"https://openalex.org/C111030470","wikidata":"https://www.wikidata.org/wiki/Q1430460","display_name":"Curse of dimensionality","level":2,"score":0.5740797519683838},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5724937915802002},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.5480228066444397},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5461711287498474},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4982576370239258},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3270278573036194},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.06779736280441284},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"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/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","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/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1142/s0218213007003692","is_oa":false,"landing_page_url":"https://doi.org/10.1142/s0218213007003692","pdf_url":null,"source":{"id":"https://openalex.org/S178780388","display_name":"International Journal of Artificial Intelligence Tools","issn_l":"0218-2130","issn":["0218-2130","1793-6349"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319815","host_organization_name":"World Scientific","host_organization_lineage":["https://openalex.org/P4310319815"],"host_organization_lineage_names":["World Scientific"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal on Artificial Intelligence Tools","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W740415","https://openalex.org/W39304953","https://openalex.org/W99760672","https://openalex.org/W114599062","https://openalex.org/W144665273","https://openalex.org/W164961562","https://openalex.org/W1533946607","https://openalex.org/W1536719366","https://openalex.org/W1568297139","https://openalex.org/W1593045043","https://openalex.org/W1594013288","https://openalex.org/W1601415797","https://openalex.org/W1648885110","https://openalex.org/W1912982817","https://openalex.org/W2096942889","https://openalex.org/W2099606292","https://openalex.org/W2118020653","https://openalex.org/W2120011452","https://openalex.org/W2120507151","https://openalex.org/W2149684865","https://openalex.org/W2156909104","https://openalex.org/W2160536005","https://openalex.org/W2169384781","https://openalex.org/W2171622762","https://openalex.org/W2180101149","https://openalex.org/W2435251607","https://openalex.org/W2916045930","https://openalex.org/W2966207845","https://openalex.org/W4231796555","https://openalex.org/W4285719527"],"related_works":["https://openalex.org/W2936002343","https://openalex.org/W2188883480","https://openalex.org/W1592364192","https://openalex.org/W656840002","https://openalex.org/W1605117403","https://openalex.org/W2381416480","https://openalex.org/W2380599343","https://openalex.org/W2181793145","https://openalex.org/W3200784702","https://openalex.org/W3021738440"],"abstract_inverted_index":{"The":[0,18],"increasing":[1],"number":[2],"of":[3,14,21,28,46,81,98,120],"unsolicited":[4],"e-mail":[5],"messages":[6],"(spam)":[7],"reveals":[8],"the":[9,12,37,62,79,113,118,121,137],"need":[10],"for":[11,35,128],"development":[13],"reliable":[15,33,108],"anti-spam":[16],"filters.":[17],"vast":[19],"majority":[20],"content-based":[22],"techniques":[23],"rely":[24],"on":[25,74,88,90],"word-based":[26],"representation":[27,72],"messages.":[29],"Such":[30],"approaches":[31],"require":[32],"tokenizers":[34,53,82],"detecting":[36],"token":[38],"boundaries.":[39],"As":[40],"a":[41,43,96,126],"consequence,":[42],"common":[44],"practice":[45],"spammers":[47],"is":[48],"to":[49,51],"attempt":[50],"confuse":[52],"using":[54],"unexpected":[55],"punctuation":[56],"marks":[57],"or":[58],"special":[59],"characters":[60],"within":[61],"message.":[63],"In":[64],"this":[65],"paper":[66],"we":[67,101,124],"explore":[68],"an":[69],"alternative":[70],"low-level":[71],"based":[73],"character":[75,104],"n-grams":[76,105,131],"which":[77,132],"avoids":[78],"use":[80],"and":[83,95],"other":[84],"language-dependent":[85],"tools.":[86],"Based":[87],"experiments":[89],"two":[91],"well-known":[92],"benchmark":[93],"corpora":[94],"variety":[97],"evaluation":[99],"measures,":[100],"show":[102],"that":[103,115],"are":[106],"more":[107],"features":[109],"than":[110],"word-tokens":[111],"despite":[112],"fact":[114],"they":[116],"increase":[117],"dimensionality":[119],"problem.":[122],"Moreover,":[123],"propose":[125],"method":[127],"extracting":[129],"variable-length":[130],"produces":[133],"optimal":[134],"classifiers":[135],"among":[136],"examined":[138],"models":[139],"under":[140],"cost-sensitive":[141],"evaluation.":[142]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":8},{"year":2020,"cited_by_count":6},{"year":2019,"cited_by_count":17},{"year":2018,"cited_by_count":12},{"year":2017,"cited_by_count":12},{"year":2016,"cited_by_count":4},{"year":2015,"cited_by_count":8},{"year":2014,"cited_by_count":3},{"year":2013,"cited_by_count":2},{"year":2012,"cited_by_count":4}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}