{"id":"https://openalex.org/W2268344442","doi":"https://doi.org/10.1145/2815782.2815789","title":"N-Gram Representations For Comment Filtering","display_name":"N-Gram Representations For Comment Filtering","publication_year":2015,"publication_date":"2015-09-28","ids":{"openalex":"https://openalex.org/W2268344442","doi":"https://doi.org/10.1145/2815782.2815789","mag":"2268344442"},"language":"en","primary_location":{"id":"doi:10.1145/2815782.2815789","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2815782.2815789","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2015 Annual Research Conference on South African Institute of Computer Scientists and Information Technologists","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/A5072009641","display_name":"Dirk Brand","orcid":"https://orcid.org/0000-0002-3660-5015"},"institutions":[{"id":"https://openalex.org/I26092322","display_name":"Stellenbosch University","ror":"https://ror.org/05bk57929","country_code":"ZA","type":"education","lineage":["https://openalex.org/I26092322"]}],"countries":["ZA"],"is_corresponding":true,"raw_author_name":"Dirk Brand","raw_affiliation_strings":["Computer Science Division, Stellenbosch University"],"affiliations":[{"raw_affiliation_string":"Computer Science Division, Stellenbosch University","institution_ids":["https://openalex.org/I26092322"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020437129","display_name":"Steve Kroon","orcid":null},"institutions":[{"id":"https://openalex.org/I26092322","display_name":"Stellenbosch University","ror":"https://ror.org/05bk57929","country_code":"ZA","type":"education","lineage":["https://openalex.org/I26092322"]}],"countries":["ZA"],"is_corresponding":false,"raw_author_name":"Steve Kroon","raw_affiliation_strings":["Computer Science Division, Stellenbosch University"],"affiliations":[{"raw_affiliation_string":"Computer Science Division, Stellenbosch University","institution_ids":["https://openalex.org/I26092322"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000026394","display_name":"Brink van der Merwe","orcid":"https://orcid.org/0000-0001-5010-9934"},"institutions":[{"id":"https://openalex.org/I26092322","display_name":"Stellenbosch University","ror":"https://ror.org/05bk57929","country_code":"ZA","type":"education","lineage":["https://openalex.org/I26092322"]}],"countries":["ZA"],"is_corresponding":false,"raw_author_name":"Brink van der Merwe","raw_affiliation_strings":["Computer Science Division, Stellenbosch University"],"affiliations":[{"raw_affiliation_string":"Computer Science Division, Stellenbosch University","institution_ids":["https://openalex.org/I26092322"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5043799147","display_name":"Loek Cleophas","orcid":"https://orcid.org/0000-0002-7221-3676"},"institutions":[{"id":"https://openalex.org/I26092322","display_name":"Stellenbosch University","ror":"https://ror.org/05bk57929","country_code":"ZA","type":"education","lineage":["https://openalex.org/I26092322"]},{"id":"https://openalex.org/I90267481","display_name":"Ume\u00e5 University","ror":"https://ror.org/05kb8h459","country_code":"SE","type":"education","lineage":["https://openalex.org/I90267481"]}],"countries":["SE","ZA"],"is_corresponding":false,"raw_author_name":"Loek Cleophas","raw_affiliation_strings":["Dept. of Computing Science, Ume\u00e5 University, Dept. of Information Science, Stellenbosch University"],"affiliations":[{"raw_affiliation_string":"Dept. of Computing Science, Ume\u00e5 University, Dept. of Information Science, Stellenbosch University","institution_ids":["https://openalex.org/I26092322","https://openalex.org/I90267481"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5072009641"],"corresponding_institution_ids":["https://openalex.org/I26092322"],"apc_list":null,"apc_paid":null,"fwci":0.4448,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.78340635,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"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/T10028","display_name":"Topic Modeling","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"}},"topics":[{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","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/T10181","display_name":"Natural Language Processing Techniques","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/T11550","display_name":"Text and Document Classification Technologies","score":0.9977999925613403,"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/n-gram","display_name":"n-gram","score":0.8233749866485596},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7820537090301514},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.5894936919212341},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5724128484725952},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5394118428230286},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.5128193497657776},{"id":"https://openalex.org/keywords/gram","display_name":"Gram","score":0.48461708426475525},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4625403881072998},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4135400652885437},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.32493874430656433},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3240097761154175},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.08924376964569092},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.0664379894733429},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.04998299479484558}],"concepts":[{"id":"https://openalex.org/C117884012","wikidata":"https://www.wikidata.org/wiki/Q94489","display_name":"n-gram","level":3,"score":0.8233749866485596},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7820537090301514},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.5894936919212341},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5724128484725952},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5394118428230286},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.5128193497657776},{"id":"https://openalex.org/C161369605","wikidata":"https://www.wikidata.org/wiki/Q41803","display_name":"Gram","level":3,"score":0.48461708426475525},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4625403881072998},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4135400652885437},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.32493874430656433},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3240097761154175},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.08924376964569092},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0664379894733429},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.04998299479484558},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0},{"id":"https://openalex.org/C523546767","wikidata":"https://www.wikidata.org/wiki/Q10876","display_name":"Bacteria","level":2,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"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/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":8,"locations":[{"id":"doi:10.1145/2815782.2815789","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2815782.2815789","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2015 Annual Research Conference on South African Institute of Computer Scientists and Information Technologists","raw_type":"proceedings-article"},{"id":"pmh:oai:pure.tue.nl:publications/a731a039-1edd-499d-90f2-fdd684902ab0","is_oa":false,"landing_page_url":"https://research.tue.nl/en/publications/a731a039-1edd-499d-90f2-fdd684902ab0","pdf_url":null,"source":{"id":"https://openalex.org/S4406922641","display_name":"TU/e Research Portal","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Brand, D, Kroon, S, Van Der Merwe, B & Cleophas, L 2015, N-gram representations for comment filtering. in SAICSIT '15 Proceedings of the 2015 Annual Research Conference on South African Institute of Computer Scientists and Information Technologists, 28-30 September 2015, Stellenbosch, South Africa ., 6, Association for Computing Machinery, Inc., New York, pp. 1-10, 2015 Annual Research Conference of the South African Institute of Computer Scientists and Information Technologists (SAICSIT 2015), Stellenbosch, South Africa, 28/09/15. https://doi.org/10.1145/2815782.2815789","raw_type":"info:eu-repo/semantics/publishedVersion"},{"id":"pmh:842669","is_oa":false,"landing_page_url":"http://library.tue.nl/csp/dare/LinkToRepository.csp?recordnumber=842669","pdf_url":null,"source":{"id":"https://openalex.org/S4406923046","display_name":"TU/e Research Portal (Eindhoven University of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":""},{"id":"pmh:888411","is_oa":false,"landing_page_url":"http://library.tue.nl/csp/dare/LinkToRepository.csp?recordnumber=888411","pdf_url":null,"source":{"id":"https://openalex.org/S4406923046","display_name":"TU/e Research Portal (Eindhoven University of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":""},{"id":"pmh:oai:library.tue.nl:842669","is_oa":false,"landing_page_url":"http://repository.tue.nl/842669","pdf_url":null,"source":{"id":"https://openalex.org/S4406923046","display_name":"TU/e Research Portal (Eindhoven University of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":""},{"id":"pmh:oai:library.tue.nl:888411","is_oa":false,"landing_page_url":"http://repository.tue.nl/888411","pdf_url":null,"source":{"id":"https://openalex.org/S4406923046","display_name":"TU/e Research Portal (Eindhoven University of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":""},{"id":"pmh:oai:scholar.sun.ac.za:10019.1/98228","is_oa":false,"landing_page_url":"http://hdl.handle.net/10019.1/98228","pdf_url":null,"source":{"id":"https://openalex.org/S4306400300","display_name":"SUNScholar (Stellenbosch University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I26092322","host_organization_name":"Stellenbosch University","host_organization_lineage":["https://openalex.org/I26092322"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Conference Paper"},{"id":"pmh:tue:oai:pure.tue.nl:publications/a731a039-1edd-499d-90f2-fdd684902ab0","is_oa":false,"landing_page_url":"https://research.tue.nl/nl/publications/a731a039-1edd-499d-90f2-fdd684902ab0","pdf_url":null,"source":{"id":"https://openalex.org/S4306401843","display_name":"Data Archiving and Networked Services (DANS)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1322597698","host_organization_name":"Royal Netherlands Academy of Arts and Sciences","host_organization_lineage":["https://openalex.org/I1322597698"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"SAICSIT '15 Proceedings of the 2015 Annual Research Conference on South African Institute of Computer Scientists and Information Technologists, 28-30 September 2015, Stellenbosch, South Africa, 1 - 10","raw_type":"info:eu-repo/semantics/conferencepaper"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.7200000286102295,"display_name":"Quality Education"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320322663","display_name":"Universiteit Stellenbosch","ror":"https://ror.org/05bk57929"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":77,"referenced_works":["https://openalex.org/W27263903","https://openalex.org/W1480643256","https://openalex.org/W1500117362","https://openalex.org/W1506025786","https://openalex.org/W1521626219","https://openalex.org/W1526741802","https://openalex.org/W1533946607","https://openalex.org/W1553244859","https://openalex.org/W1562615108","https://openalex.org/W1563088657","https://openalex.org/W1578692790","https://openalex.org/W1597534959","https://openalex.org/W1614298861","https://openalex.org/W1853851539","https://openalex.org/W1854214752","https://openalex.org/W1863422369","https://openalex.org/W1869391892","https://openalex.org/W1956559956","https://openalex.org/W1965061793","https://openalex.org/W1967390364","https://openalex.org/W1969100437","https://openalex.org/W1974339500","https://openalex.org/W1978394996","https://openalex.org/W1984762104","https://openalex.org/W1990950330","https://openalex.org/W1996640618","https://openalex.org/W2000631734","https://openalex.org/W2030035054","https://openalex.org/W2037858832","https://openalex.org/W2042200090","https://openalex.org/W2053522862","https://openalex.org/W2053968437","https://openalex.org/W2081580037","https://openalex.org/W2097998348","https://openalex.org/W2100329159","https://openalex.org/W2101234009","https://openalex.org/W2101746535","https://openalex.org/W2109664771","https://openalex.org/W2109943925","https://openalex.org/W2119252083","https://openalex.org/W2119671065","https://openalex.org/W2120719282","https://openalex.org/W2123622235","https://openalex.org/W2124537004","https://openalex.org/W2127384912","https://openalex.org/W2131462252","https://openalex.org/W2137570937","https://openalex.org/W2143450308","https://openalex.org/W2149684865","https://openalex.org/W2151849342","https://openalex.org/W2156909104","https://openalex.org/W2159189488","https://openalex.org/W2161084348","https://openalex.org/W2165612380","https://openalex.org/W2171836785","https://openalex.org/W2483550645","https://openalex.org/W2597289420","https://openalex.org/W2739894646","https://openalex.org/W2911681169","https://openalex.org/W2997591727","https://openalex.org/W2998216295","https://openalex.org/W2998704965","https://openalex.org/W3005347330","https://openalex.org/W4231621972","https://openalex.org/W4253684685","https://openalex.org/W4285719527","https://openalex.org/W6632118081","https://openalex.org/W6639055396","https://openalex.org/W6640862754","https://openalex.org/W6674385629","https://openalex.org/W6676373471","https://openalex.org/W6678498635","https://openalex.org/W6682316766","https://openalex.org/W6683179302","https://openalex.org/W6742065490","https://openalex.org/W6758972637","https://openalex.org/W6773842061"],"related_works":["https://openalex.org/W2906970013","https://openalex.org/W3126081632","https://openalex.org/W2625039379","https://openalex.org/W2088254117","https://openalex.org/W4254593385","https://openalex.org/W2790582133","https://openalex.org/W1901380241","https://openalex.org/W311963822","https://openalex.org/W2789473152","https://openalex.org/W3132255358"],"abstract_inverted_index":{"Accurate":[0],"classifiers":[1],"for":[2,46],"short":[3,47],"texts":[4],"are":[5],"valuable":[6],"assets":[7],"in":[8,12,20,62],"many":[9],"applications.":[10],"Especially":[11],"online":[13],"communities,":[14],"where":[15],"users":[16],"contribute":[17],"to":[18,53],"content":[19],"the":[21,40,68],"form":[22],"of":[23,30,42],"posts":[24,33],"and":[25,50],"comments,":[26],"an":[27],"effective":[28],"way":[29],"automatically":[31],"categorising":[32],"proves":[34],"highly":[35],"valuable.":[36],"This":[37],"paper":[38],"investigates":[39],"use":[41],"N-grams":[43],"as":[44],"features":[45],"text":[48],"classification,":[49],"compares":[51],"it":[52],"manual":[54,73],"feature":[55,74],"design":[56],"techniques":[57],"that":[58,67],"have":[59],"been":[60],"popular":[61],"this":[63],"domain.":[64],"We":[65],"find":[66],"N-gram":[69],"representations":[70],"greatly":[71],"outperform":[72],"extraction":[75],"techniques.":[76]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2016,"cited_by_count":1}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}