{"id":"https://openalex.org/W2000908731","doi":"https://doi.org/10.1145/2766462.2767701","title":"HSpam14","display_name":"HSpam14","publication_year":2015,"publication_date":"2015-08-04","ids":{"openalex":"https://openalex.org/W2000908731","doi":"https://doi.org/10.1145/2766462.2767701","mag":"2000908731"},"language":"en","primary_location":{"id":"doi:10.1145/2766462.2767701","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2766462.2767701","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 38th International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"},"type":"conference-paper","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/A5027829088","display_name":"Surendra Sedhai","orcid":null},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Surendra Sedhai","raw_affiliation_strings":["Nanyang Technological University, Singapore , Singapore","Nanyang Technological University, Singapore, SINGAPORE#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanyang Technological University, Singapore , Singapore","institution_ids":["https://openalex.org/I172675005"]},{"raw_affiliation_string":"Nanyang Technological University, Singapore, SINGAPORE#TAB#","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100618738","display_name":"Aixin Sun","orcid":"https://orcid.org/0000-0003-0764-4258"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Aixin Sun","raw_affiliation_strings":["Nanyang Technological University, Singapore , Singapore","Nanyang Technological University, Singapore, SINGAPORE#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanyang Technological University, Singapore , Singapore","institution_ids":["https://openalex.org/I172675005"]},{"raw_affiliation_string":"Nanyang Technological University, Singapore, SINGAPORE#TAB#","institution_ids":["https://openalex.org/I172675005"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I172675005"],"apc_list":null,"apc_paid":null,"fwci":8.1091,"has_fulltext":false,"cited_by_count":82,"citation_normalized_percentile":{"value":0.98355194,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"223","last_page":"232"},"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/T10664","display_name":"Sentiment Analysis and Opinion Mining","score":0.9993000030517578,"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/T11147","display_name":"Misinformation and Its Impacts","score":0.9979000091552734,"subfield":{"id":"https://openalex.org/subfields/3312","display_name":"Sociology and Political Science"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/spamming","display_name":"Spamming","score":0.8368382453918457},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8319171667098999},{"id":"https://openalex.org/keywords/annotation","display_name":"Annotation","score":0.6726452708244324},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5920687913894653},{"id":"https://openalex.org/keywords/sentiment-analysis","display_name":"Sentiment analysis","score":0.47662270069122314},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.44134262204170227},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.38032349944114685},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.274219810962677},{"id":"https://openalex.org/keywords/the-internet","display_name":"The Internet","score":0.22061750292778015}],"concepts":[{"id":"https://openalex.org/C158955206","wikidata":"https://www.wikidata.org/wiki/Q83058","display_name":"Spamming","level":3,"score":0.8368382453918457},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8319171667098999},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.6726452708244324},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5920687913894653},{"id":"https://openalex.org/C66402592","wikidata":"https://www.wikidata.org/wiki/Q2271421","display_name":"Sentiment analysis","level":2,"score":0.47662270069122314},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.44134262204170227},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.38032349944114685},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.274219810962677},{"id":"https://openalex.org/C110875604","wikidata":"https://www.wikidata.org/wiki/Q75","display_name":"The Internet","level":2,"score":0.22061750292778015},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2766462.2767701","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2766462.2767701","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 38th International ACM SIGIR Conference on Research and Development in Information Retrieval","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":41,"referenced_works":["https://openalex.org/W9223698","https://openalex.org/W83087001","https://openalex.org/W113059239","https://openalex.org/W168249728","https://openalex.org/W176212337","https://openalex.org/W1532325895","https://openalex.org/W1775665607","https://openalex.org/W1969568357","https://openalex.org/W2005556331","https://openalex.org/W2007972815","https://openalex.org/W2017270267","https://openalex.org/W2039190653","https://openalex.org/W2047756776","https://openalex.org/W2061989622","https://openalex.org/W2064237629","https://openalex.org/W2067432306","https://openalex.org/W2076149295","https://openalex.org/W2076219102","https://openalex.org/W2084591134","https://openalex.org/W2097089247","https://openalex.org/W2097436041","https://openalex.org/W2098395374","https://openalex.org/W2100738695","https://openalex.org/W2103976304","https://openalex.org/W2105689297","https://openalex.org/W2106476394","https://openalex.org/W2127124926","https://openalex.org/W2127935984","https://openalex.org/W2132069633","https://openalex.org/W2134510195","https://openalex.org/W2143996849","https://openalex.org/W2144415203","https://openalex.org/W2159359879","https://openalex.org/W2160702998","https://openalex.org/W2161283199","https://openalex.org/W2165701072","https://openalex.org/W2290561533","https://openalex.org/W2401383085","https://openalex.org/W2962991180","https://openalex.org/W3125182500","https://openalex.org/W4297970707"],"related_works":["https://openalex.org/W1987732684","https://openalex.org/W2286465138","https://openalex.org/W637393809","https://openalex.org/W2808742736","https://openalex.org/W1526983901","https://openalex.org/W3126526144","https://openalex.org/W3021299372","https://openalex.org/W2184211279","https://openalex.org/W2346278349","https://openalex.org/W3139094847"],"abstract_inverted_index":{"Hashtag":[0],"facilitates":[1],"information":[2,13],"diffusion":[3],"in":[4,71,86,193],"Twitter":[5,17],"by":[6,32],"creating":[7],"dynamic":[8],"and":[9,51,90,100,143,159],"virtual":[10],"communities":[11],"for":[12,25,42,122,189],"aggregation":[14],"from":[15,201],"all":[16],"users.":[18],"Because":[19],"hashtags":[20,39,85],"serve":[21],"as":[22],"additional":[23],"channels":[24],"one's":[26],"tweets":[27,80,97,123,140,151,155],"to":[28,60,120,128,136,153,165],"be":[29,129,187],"potentially":[30],"accessed":[31],"other":[33],"users":[34],"than":[35],"her":[36],"own":[37],"followers,":[38],"are":[40,67,125,157],"targeted":[41],"spamming":[43],"purposes":[44],"(e.g.,":[45],"hashtag":[46],"hijacking),":[47],"particularly":[48],"the":[49,96,106,146,167,180,198,202,206],"popular":[50],"trending":[52,84],"hashtags.":[53],"Although":[54],"much":[55],"effort":[56],"has":[57],"been":[58],"devoted":[59],"fighting":[61],"against":[62],"email/web":[63],"spam,":[64,130],"limited":[65],"studies":[66],"on":[68],"hashtag-oriented":[69,190],"spam":[70,99,191],"tweets.":[72,172,194],"In":[73],"this":[74,177],"paper,":[75],"we":[76],"collected":[77],"14":[78],"million":[79],"that":[81,124,156],"matched":[82],"some":[83],"two":[87],"months'":[88],"time":[89],"then":[91,144],"conducted":[92],"systematic":[93],"annotation":[94,111,135],"of":[95,169,176,182,205],"being":[98],"ham":[101,150],"(i.e.,":[102],"non-spam).":[103],"We":[104],"name":[105],"annotated":[107],"dataset":[108],"HSpam14.":[109],"Our":[110],"process":[112],"includes":[113],"four":[114],"major":[115,174],"steps:":[116],"(i)":[117],"heuristic-based":[118],"selection":[119],"search":[121],"more":[126],"likely":[127],"(ii)":[131],"near-duplicate":[132],"cluster":[133],"based":[134],"firstly":[137],"group":[138],"similar":[139],"into":[141],"clusters":[142],"label":[145,154,163],"clusters,":[147],"(iii)":[148],"reliable":[149],"detection":[152],"non-spam,":[158],"(iv)":[160],"Expectation-Maximization":[161],"(EM)-based":[162],"prediction":[164],"predict":[166],"labels":[168],"remaining":[170],"unlabeled":[171],"One":[173],"contribution":[175,196],"work":[178],"is":[179,197],"creation":[181],"HSpam14":[183,207],"dataset,":[184],"which":[185],"can":[186],"used":[188],"research":[192],"Another":[195],"observations":[199],"made":[200],"preliminary":[203],"analysis":[204],"dataset.":[208]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":9},{"year":2021,"cited_by_count":7},{"year":2020,"cited_by_count":12},{"year":2019,"cited_by_count":15},{"year":2018,"cited_by_count":12},{"year":2017,"cited_by_count":8},{"year":2016,"cited_by_count":8}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2016-06-24T00:00:00"}