{"id":"https://openalex.org/W2954580219","doi":"https://doi.org/10.1145/3331184.3331239","title":"Similarity-Based Synthetic Document Representations for Meta-Feature Generation in Text Classification","display_name":"Similarity-Based Synthetic Document Representations for Meta-Feature Generation in Text Classification","publication_year":2019,"publication_date":"2019-07-18","ids":{"openalex":"https://openalex.org/W2954580219","doi":"https://doi.org/10.1145/3331184.3331239","mag":"2954580219"},"language":"en","primary_location":{"id":"doi:10.1145/3331184.3331239","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3331184.3331239","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3331184.3331239","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 42nd International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3331184.3331239","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5046683090","display_name":"S\u00e9rgio Canuto","orcid":"https://orcid.org/0000-0003-2973-4158"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Sergio Canuto","raw_affiliation_strings":["DCC - UFMG, Belo Horizonte, Brazil"],"affiliations":[{"raw_affiliation_string":"DCC - UFMG, Belo Horizonte, Brazil","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001156386","display_name":"Thiago Salles","orcid":"https://orcid.org/0000-0003-2165-1999"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Thiago Salles","raw_affiliation_strings":["DCC - UFMG, Belo Horizonte, Brazil"],"affiliations":[{"raw_affiliation_string":"DCC - UFMG, Belo Horizonte, Brazil","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024659734","display_name":"Thierson Couto Rosa","orcid":"https://orcid.org/0000-0001-7117-3994"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Thierson C. Rosa","raw_affiliation_strings":["INF - UFG, Goi\u00e2nia, Brazil"],"affiliations":[{"raw_affiliation_string":"INF - UFG, Goi\u00e2nia, Brazil","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5046370637","display_name":"Marcos Andr\u00e9 Gon\u00e7alves","orcid":"https://orcid.org/0000-0002-2075-3363"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Marcos A. Gon\u00e7alves","raw_affiliation_strings":["DCC - UFMG, Belo Horizonte, Brazil"],"affiliations":[{"raw_affiliation_string":"DCC - UFMG, Belo Horizonte, Brazil","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5046683090"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.4002,"has_fulltext":false,"cited_by_count":16,"citation_normalized_percentile":{"value":0.86203861,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"355","last_page":"364"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11550","display_name":"Text and Document Classification Technologies","score":0.9998000264167786,"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/T11550","display_name":"Text and Document Classification Technologies","score":0.9998000264167786,"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/T10028","display_name":"Topic Modeling","score":0.9932000041007996,"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/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.991599977016449,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.7147433757781982},{"id":"https://openalex.org/keywords/hyperplane","display_name":"Hyperplane","score":0.6977790594100952},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.6759501099586487},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.6705195903778076},{"id":"https://openalex.org/keywords/document-classification","display_name":"Document classification","score":0.5197938680648804},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5123773813247681},{"id":"https://openalex.org/keywords/feature-vector","display_name":"Feature vector","score":0.4829372763633728},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4716978073120117},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4467594027519226},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.43102535605430603},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.15642604231834412},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.06486326456069946}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7147433757781982},{"id":"https://openalex.org/C68693459","wikidata":"https://www.wikidata.org/wiki/Q657586","display_name":"Hyperplane","level":2,"score":0.6977790594100952},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.6759501099586487},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.6705195903778076},{"id":"https://openalex.org/C2780479914","wikidata":"https://www.wikidata.org/wiki/Q302088","display_name":"Document classification","level":2,"score":0.5197938680648804},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5123773813247681},{"id":"https://openalex.org/C83665646","wikidata":"https://www.wikidata.org/wiki/Q42139305","display_name":"Feature vector","level":2,"score":0.4829372763633728},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4716978073120117},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4467594027519226},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.43102535605430603},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.15642604231834412},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.06486326456069946},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3331184.3331239","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3331184.3331239","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3331184.3331239","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 42nd International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3331184.3331239","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3331184.3331239","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3331184.3331239","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 42nd International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.6299999952316284,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320322025","display_name":"Conselho Nacional de Desenvolvimento Cient\u00edfico e Tecnol\u00f3gico","ror":"https://ror.org/03swz6y49"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2954580219.pdf","grobid_xml":"https://content.openalex.org/works/W2954580219.grobid-xml"},"referenced_works_count":19,"referenced_works":["https://openalex.org/W159719520","https://openalex.org/W1230873221","https://openalex.org/W1618905105","https://openalex.org/W1965350272","https://openalex.org/W2050338028","https://openalex.org/W2057194219","https://openalex.org/W2114535528","https://openalex.org/W2118585731","https://openalex.org/W2131744502","https://openalex.org/W2145241906","https://openalex.org/W2145658888","https://openalex.org/W2150102617","https://openalex.org/W2153758664","https://openalex.org/W2157874634","https://openalex.org/W2165828254","https://openalex.org/W2170096781","https://openalex.org/W2295077356","https://openalex.org/W2795240784","https://openalex.org/W3104717349"],"related_works":["https://openalex.org/W2369655046","https://openalex.org/W2019467317","https://openalex.org/W1585519779","https://openalex.org/W1965515989","https://openalex.org/W4376167435","https://openalex.org/W2088737283","https://openalex.org/W1999587863","https://openalex.org/W1929902734","https://openalex.org/W2042783797","https://openalex.org/W1543940884"],"abstract_inverted_index":{"We":[0],"propose":[1],"new":[2,91],"solutions":[3,92],"that":[4,89],"enhance":[5],"and":[6,46,48,52,64,83],"extend":[7],"the":[8,27,55,65,69,76,94,108,113],"already":[9],"very":[10],"successful":[11],"application":[12],"of":[13,29,32,42,57,75,86,103,112],"meta-features":[14,21,67],"to":[15,105],"text":[16],"classification.":[17],"Our":[18,79],"newly":[19,62],"proposed":[20,63],"are":[22],"capable":[23],"of:":[24],"(1)":[25],"improving":[26],"correlation":[28],"small":[30],"pieces":[31],"evidence":[33],"shared":[34],"by":[35,40,60],"neighbors":[36],"with":[37,81],"labeled":[38],"categories":[39],"means":[41],"synthetic":[43],"document":[44],"representations":[45],"(local":[47],"global)":[49],"hyperplane":[50],"distances;":[51],"(2)":[53],"estimating":[54],"level":[56],"error":[58],"introduced":[59],"these":[61],"existing":[66],"in":[68,97],"literature,":[70],"specially":[71],"for":[72],"hard-to-classify":[73],"regions":[74],"feature":[77],"space.":[78],"experiments":[80],"large":[82],"representative":[84],"number":[85],"datasets":[87],"show":[88],"our":[90],"produce":[93],"best":[95],"results":[96],"all":[98],"tested":[99],"scenarios,":[100],"achieving":[101],"gains":[102],"up":[104],"12%":[106],"over":[107],"strongest":[109],"meta-feature":[110],"proposal":[111],"literature.":[114]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":5},{"year":2020,"cited_by_count":4}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}