{"id":"https://openalex.org/W2123449924","doi":"https://doi.org/10.1145/2381896.2381907","title":"Robust detection of comment spam using entropy rate","display_name":"Robust detection of comment spam using entropy rate","publication_year":2012,"publication_date":"2012-10-19","ids":{"openalex":"https://openalex.org/W2123449924","doi":"https://doi.org/10.1145/2381896.2381907","mag":"2123449924"},"language":"en","primary_location":{"id":"doi:10.1145/2381896.2381907","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2381896.2381907","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 5th ACM workshop on Security and artificial intelligence","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/A5033041590","display_name":"Alex Kantchelian","orcid":null},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Alex Kantchelian","raw_affiliation_strings":["University of California, Berkeley, Berkeley, CA, USA","University of California, Berkeley, Berkeley, CA USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California, Berkeley, Berkeley, CA, USA","institution_ids":["https://openalex.org/I95457486"]},{"raw_affiliation_string":"University of California, Berkeley, Berkeley, CA USA","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101589605","display_name":"Justin Ma","orcid":"https://orcid.org/0000-0001-9050-3493"},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Justin Ma","raw_affiliation_strings":["University of California, Berkeley, Berkeley, CA, USA","University of California, Berkeley, Berkeley, CA USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California, Berkeley, Berkeley, CA, USA","institution_ids":["https://openalex.org/I95457486"]},{"raw_affiliation_string":"University of California, Berkeley, Berkeley, CA USA","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082878554","display_name":"Ling Huang","orcid":"https://orcid.org/0000-0001-5089-4637"},"institutions":[{"id":"https://openalex.org/I1343180700","display_name":"Intel (United States)","ror":"https://ror.org/01ek73717","country_code":"US","type":"company","lineage":["https://openalex.org/I1343180700"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ling Huang","raw_affiliation_strings":["Intel Labs, Berkeley, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Intel Labs, Berkeley, CA, USA","institution_ids":["https://openalex.org/I1343180700"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101418350","display_name":"Sadia Afroz","orcid":"https://orcid.org/0000-0002-8427-0635"},"institutions":[{"id":"https://openalex.org/I72816309","display_name":"Drexel University","ror":"https://ror.org/04bdffz58","country_code":"US","type":"education","lineage":["https://openalex.org/I72816309"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sadia Afroz","raw_affiliation_strings":["Drexel University, Philadelphia, PA, USA","Drexel University, Philadelphia, PA, USA;"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Drexel University, Philadelphia, PA, USA","institution_ids":["https://openalex.org/I72816309"]},{"raw_affiliation_string":"Drexel University, Philadelphia, PA, USA;","institution_ids":["https://openalex.org/I72816309"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017381278","display_name":"Anthony D. Joseph","orcid":"https://orcid.org/0000-0002-6798-9664"},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Anthony Joseph","raw_affiliation_strings":["University of California, Berkeley, Berkeley, CA, USA","University of California, Berkeley, Berkeley, CA USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California, Berkeley, Berkeley, CA, USA","institution_ids":["https://openalex.org/I95457486"]},{"raw_affiliation_string":"University of California, Berkeley, Berkeley, CA USA","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5113907559","display_name":"J. D. Tygar","orcid":null},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"J. D. Tygar","raw_affiliation_strings":["University of California, Berkeley, Berkeley, CA, USA","University of California, Berkeley, Berkeley, CA USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California, Berkeley, Berkeley, CA, USA","institution_ids":["https://openalex.org/I95457486"]},{"raw_affiliation_string":"University of California, Berkeley, Berkeley, CA USA","institution_ids":["https://openalex.org/I95457486"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":9.554,"has_fulltext":false,"cited_by_count":58,"citation_normalized_percentile":{"value":0.97655115,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"59","last_page":"70"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11644","display_name":"Spam and Phishing Detection","score":1.0,"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":1.0,"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/T11550","display_name":"Text and Document Classification Technologies","score":0.9986000061035156,"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/T10064","display_name":"Complex Network Analysis Techniques","score":0.9973999857902527,"subfield":{"id":"https://openalex.org/subfields/3109","display_name":"Statistical and Nonlinear Physics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7809515595436096},{"id":"https://openalex.org/keywords/communication-source","display_name":"Communication source","score":0.7263829708099365},{"id":"https://openalex.org/keywords/lexical-analysis","display_name":"Lexical analysis","score":0.6836853623390198},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.5868976712226868},{"id":"https://openalex.org/keywords/entropy","display_name":"Entropy (arrow of time)","score":0.524281919002533},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.49345722794532776},{"id":"https://openalex.org/keywords/spambot","display_name":"Spambot","score":0.4775184690952301},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4631921648979187},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.45367830991744995},{"id":"https://openalex.org/keywords/spamming","display_name":"Spamming","score":0.45205825567245483},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.4299701750278473},{"id":"https://openalex.org/keywords/entropy-estimation","display_name":"Entropy estimation","score":0.4118579924106598},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.34348493814468384},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.32001620531082153},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.23351413011550903},{"id":"https://openalex.org/keywords/the-internet","display_name":"The Internet","score":0.15774396061897278},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.11681464314460754},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.08053523302078247},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.07934942841529846}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7809515595436096},{"id":"https://openalex.org/C198104137","wikidata":"https://www.wikidata.org/wiki/Q974688","display_name":"Communication source","level":2,"score":0.7263829708099365},{"id":"https://openalex.org/C176982825","wikidata":"https://www.wikidata.org/wiki/Q835922","display_name":"Lexical analysis","level":2,"score":0.6836853623390198},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.5868976712226868},{"id":"https://openalex.org/C106301342","wikidata":"https://www.wikidata.org/wiki/Q4117933","display_name":"Entropy (arrow of time)","level":2,"score":0.524281919002533},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.49345722794532776},{"id":"https://openalex.org/C127735637","wikidata":"https://www.wikidata.org/wiki/Q2306702","display_name":"Spambot","level":4,"score":0.4775184690952301},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4631921648979187},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.45367830991744995},{"id":"https://openalex.org/C158955206","wikidata":"https://www.wikidata.org/wiki/Q83058","display_name":"Spamming","level":3,"score":0.45205825567245483},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.4299701750278473},{"id":"https://openalex.org/C95546049","wikidata":"https://www.wikidata.org/wiki/Q1345207","display_name":"Entropy estimation","level":3,"score":0.4118579924106598},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.34348493814468384},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.32001620531082153},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.23351413011550903},{"id":"https://openalex.org/C110875604","wikidata":"https://www.wikidata.org/wiki/Q75","display_name":"The Internet","level":2,"score":0.15774396061897278},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.11681464314460754},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.08053523302078247},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.07934942841529846},{"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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C185429906","wikidata":"https://www.wikidata.org/wiki/Q1130160","display_name":"Estimator","level":2,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/2381896.2381907","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2381896.2381907","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 5th ACM workshop on Security and artificial intelligence","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.310.3544","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.310.3544","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cs.berkeley.edu/~tygar/papers/SML2/Comment_spam.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.352.3044","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.352.3044","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www2.berkeley.intel-research.net/~hling/research/aisec12.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320306113","display_name":"U.S. Department of State","ror":"https://ror.org/03vvynj75"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W1593657937","https://openalex.org/W1965586806","https://openalex.org/W1996802155","https://openalex.org/W2000359198","https://openalex.org/W2000631734","https://openalex.org/W2018891628","https://openalex.org/W2041597619","https://openalex.org/W2079145130","https://openalex.org/W2081988714","https://openalex.org/W2087070363","https://openalex.org/W2096977913","https://openalex.org/W2102098892","https://openalex.org/W2104290684","https://openalex.org/W2108214308","https://openalex.org/W2112063328","https://openalex.org/W2113344319","https://openalex.org/W2119252083","https://openalex.org/W2121871834","https://openalex.org/W2132178626","https://openalex.org/W2134305421","https://openalex.org/W2256578114","https://openalex.org/W2401383085","https://openalex.org/W2405550436","https://openalex.org/W4213173876","https://openalex.org/W4233802931","https://openalex.org/W4237690029","https://openalex.org/W6635272604","https://openalex.org/W6677885705","https://openalex.org/W6712844215"],"related_works":["https://openalex.org/W2018000323","https://openalex.org/W2054635172","https://openalex.org/W2403960249","https://openalex.org/W2095720311","https://openalex.org/W2006090454","https://openalex.org/W1636188228","https://openalex.org/W2030018935","https://openalex.org/W384368127","https://openalex.org/W4239718349","https://openalex.org/W2154166086"],"abstract_inverted_index":{"In":[0],"this":[1,58,63],"work,":[2],"we":[3,33,42],"design":[4],"a":[5,28,35,47,67],"method":[6],"for":[7],"blog":[8,31],"comment":[9,74],"spam":[10,16,75],"detection":[11,76],"using":[12],"the":[13,25,51,79,87,90,94],"assumption":[14],"that":[15],"is":[17],"any":[18],"kind":[19],"of":[20,27,30,70,84],"uninformative":[21],"content.":[22],"To":[23],"measure":[24],"\"informativeness\"":[26],"set":[29,69],"comments,":[32],"construct":[34],"language":[36],"and":[37],"tokenization":[38],"independent":[39],"metric":[40,64],"which":[41],"call":[43],"content":[44,80],"complexity,":[45],"providing":[46],"normalized":[48],"answer":[49],"to":[50,65,73],"informal":[52],"question":[53],"\"how":[54],"much":[55],"information":[56],"does":[57],"text":[59],"contain?\"":[60],"We":[61],"leverage":[62],"create":[66],"small":[68],"features":[71],"well-adjusted":[72],"by":[77],"computing":[78],"complexity":[81],"over":[82],"groupings":[83],"messages":[85],"sharing":[86],"same":[88,91,95],"author,":[89],"sender":[92],"IP,":[93],"included":[96],"links,":[97],"etc.":[98]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":6},{"year":2019,"cited_by_count":18},{"year":2018,"cited_by_count":3},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":5},{"year":2015,"cited_by_count":4},{"year":2014,"cited_by_count":4},{"year":2013,"cited_by_count":5}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}