{"id":"https://openalex.org/W2913894097","doi":"https://doi.org/10.1145/3308558.3313397","title":"Classifying Extremely Short Texts by Exploiting Semantic Centroids in Word Mover's Distance Space","display_name":"Classifying Extremely Short Texts by Exploiting Semantic Centroids in Word Mover's Distance Space","publication_year":2019,"publication_date":"2019-05-13","ids":{"openalex":"https://openalex.org/W2913894097","doi":"https://doi.org/10.1145/3308558.3313397","mag":"2913894097"},"language":"en","primary_location":{"id":"doi:10.1145/3308558.3313397","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3308558.3313397","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The World Wide Web Conference","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3308558.3313397","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101700398","display_name":"Changchun Li","orcid":"https://orcid.org/0000-0002-4699-8609"},"institutions":[{"id":"https://openalex.org/I194450716","display_name":"Jilin University","ror":"https://ror.org/00js3aw79","country_code":"CN","type":"education","lineage":["https://openalex.org/I194450716"]},{"id":"https://openalex.org/I4210136497","display_name":"Jilin Medical University","ror":"https://ror.org/03mzw7781","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210136497"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Changchun Li","raw_affiliation_strings":["Jilin University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Jilin University, China","institution_ids":["https://openalex.org/I4210136497","https://openalex.org/I194450716"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103822192","display_name":"Jihong Ouyang","orcid":"https://orcid.org/0000-0001-6151-365X"},"institutions":[{"id":"https://openalex.org/I194450716","display_name":"Jilin University","ror":"https://ror.org/00js3aw79","country_code":"CN","type":"education","lineage":["https://openalex.org/I194450716"]},{"id":"https://openalex.org/I4210136497","display_name":"Jilin Medical University","ror":"https://ror.org/03mzw7781","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210136497"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jihong Ouyang","raw_affiliation_strings":["Jilin University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Jilin University, China","institution_ids":["https://openalex.org/I4210136497","https://openalex.org/I194450716"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100751173","display_name":"Ximing Li","orcid":"https://orcid.org/0000-0001-8190-5087"},"institutions":[{"id":"https://openalex.org/I194450716","display_name":"Jilin University","ror":"https://ror.org/00js3aw79","country_code":"CN","type":"education","lineage":["https://openalex.org/I194450716"]},{"id":"https://openalex.org/I4210136497","display_name":"Jilin Medical University","ror":"https://ror.org/03mzw7781","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210136497"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ximing Li","raw_affiliation_strings":["Jilin University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Jilin University, China","institution_ids":["https://openalex.org/I4210136497","https://openalex.org/I194450716"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.1691,"has_fulltext":false,"cited_by_count":21,"citation_normalized_percentile":{"value":0.90425361,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"939","last_page":"949"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","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/T10028","display_name":"Topic Modeling","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/T11550","display_name":"Text and Document Classification Technologies","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/T13083","display_name":"Advanced Text Analysis Techniques","score":0.9990000128746033,"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":0.7559269070625305},{"id":"https://openalex.org/keywords/generality","display_name":"Generality","score":0.7154292464256287},{"id":"https://openalex.org/keywords/semantic-similarity","display_name":"Semantic similarity","score":0.6670712232589722},{"id":"https://openalex.org/keywords/centroid","display_name":"Centroid","score":0.6649608612060547},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.6114626526832581},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6051942110061646},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5725493431091309},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.4605070948600769},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.42691439390182495},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.42502808570861816},{"id":"https://openalex.org/keywords/k-nearest-neighbors-algorithm","display_name":"k-nearest neighbors algorithm","score":0.4214571714401245},{"id":"https://openalex.org/keywords/latent-semantic-analysis","display_name":"Latent semantic analysis","score":0.4132082164287567},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.35341882705688477},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.14280131459236145},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.08364838361740112}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7559269070625305},{"id":"https://openalex.org/C2780767217","wikidata":"https://www.wikidata.org/wiki/Q5532421","display_name":"Generality","level":2,"score":0.7154292464256287},{"id":"https://openalex.org/C130318100","wikidata":"https://www.wikidata.org/wiki/Q2268914","display_name":"Semantic similarity","level":2,"score":0.6670712232589722},{"id":"https://openalex.org/C146599234","wikidata":"https://www.wikidata.org/wiki/Q511093","display_name":"Centroid","level":2,"score":0.6649608612060547},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.6114626526832581},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6051942110061646},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5725493431091309},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.4605070948600769},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.42691439390182495},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.42502808570861816},{"id":"https://openalex.org/C113238511","wikidata":"https://www.wikidata.org/wiki/Q1071612","display_name":"k-nearest neighbors algorithm","level":2,"score":0.4214571714401245},{"id":"https://openalex.org/C170133592","wikidata":"https://www.wikidata.org/wiki/Q1806883","display_name":"Latent semantic analysis","level":2,"score":0.4132082164287567},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.35341882705688477},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.14280131459236145},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.08364838361740112},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C542102704","wikidata":"https://www.wikidata.org/wiki/Q183257","display_name":"Psychotherapist","level":1,"score":0.0},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3308558.3313397","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3308558.3313397","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The World Wide Web Conference","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3308558.3313397","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3308558.3313397","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The World Wide Web Conference","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.5400000214576721}],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":50,"referenced_works":["https://openalex.org/W385466589","https://openalex.org/W562660536","https://openalex.org/W658020064","https://openalex.org/W1572158434","https://openalex.org/W1762430620","https://openalex.org/W1880262756","https://openalex.org/W1960685374","https://openalex.org/W2039434802","https://openalex.org/W2048195127","https://openalex.org/W2052274922","https://openalex.org/W2055400882","https://openalex.org/W2076219102","https://openalex.org/W2098759550","https://openalex.org/W2108828123","https://openalex.org/W2113455164","https://openalex.org/W2121184547","https://openalex.org/W2125101937","https://openalex.org/W2127416213","https://openalex.org/W2130284530","https://openalex.org/W2141599568","https://openalex.org/W2143668817","https://openalex.org/W2151703435","https://openalex.org/W2158131535","https://openalex.org/W2162993204","https://openalex.org/W2164385956","https://openalex.org/W2170240176","https://openalex.org/W2171836785","https://openalex.org/W2248116437","https://openalex.org/W2252215182","https://openalex.org/W2312355711","https://openalex.org/W2321588627","https://openalex.org/W2516780539","https://openalex.org/W2539033431","https://openalex.org/W2556873163","https://openalex.org/W2577037304","https://openalex.org/W2579923771","https://openalex.org/W2752197020","https://openalex.org/W2755330151","https://openalex.org/W2788402790","https://openalex.org/W2799605284","https://openalex.org/W2854210280","https://openalex.org/W2897454190","https://openalex.org/W2949129950","https://openalex.org/W2951798229","https://openalex.org/W2962708723","https://openalex.org/W4241307704","https://openalex.org/W4256361765","https://openalex.org/W4366084930","https://openalex.org/W6615672858","https://openalex.org/W6729835178"],"related_works":["https://openalex.org/W2045049461","https://openalex.org/W1978893398","https://openalex.org/W2201908702","https://openalex.org/W4381094582","https://openalex.org/W2499112530","https://openalex.org/W2362413895","https://openalex.org/W3152143533","https://openalex.org/W4283655540","https://openalex.org/W2626769217","https://openalex.org/W4385572821"],"abstract_inverted_index":{"Automatically":[0],"classifying":[1],"extremely":[2,166],"short":[3,61,73,93,107,167],"texts,":[4,108],"such":[5],"as":[6],"social":[7],"media":[8],"posts":[9],"and":[10,125],"web":[11],"page":[12],"titles,":[13],"plays":[14],"an":[15],"important":[16],"role":[17],"in":[18,36,65],"a":[19,81,102,114],"wide":[20],"range":[21],"of":[22,60,72,145],"content":[23],"analysis":[24],"applications.":[25],"However,":[26],"traditional":[27],"classifiers":[28],"based":[29,150],"on":[30,151,165],"bag-of-words":[31],"(BoW)":[32],"representations":[33,54],"often":[34],"fail":[35],"this":[37,77],"task.":[38],"The":[39,135],"underlying":[40],"reason":[41],"is":[42,137],"that":[43,156],"the":[44,57,70,96,122,131,142],"document":[45],"similarity":[46],"can":[47,89,159],"not":[48],"be":[49],"accurately":[50],"measured":[51],"under":[52,121],"BoW":[53],"due":[55],"to":[56,68],"extreme":[58],"sparseness":[59],"texts.":[62,74,168],"This":[63],"results":[64,154],"significant":[66],"difficulty":[67],"capture":[69],"generality":[71],"To":[75],"address":[76],"problem,":[78],"we":[79],"use":[80],"better":[82],"regularized":[83],"word":[84],"mover's":[85],"distance":[86],"(RWMD),":[87],"which":[88],"measure":[90],"distances":[91],"among":[92],"texts":[94],"at":[95],"semantic":[97,116,133],"level.":[98],"We":[99],"then":[100],"propose":[101],"RWMD-based":[103],"centroid":[104,117],"classifier":[105,149],"for":[106,118],"named":[109],"RWMD-CC.":[110],"Basically,":[111],"RWMD-CC":[112,158],"computes":[113],"representative":[115],"each":[119],"category":[120],"RWMD":[123],"measure,":[124],"predicts":[126],"test":[127],"documents":[128],"by":[129],"finding":[130],"closest":[132],"centroid.":[134],"testing":[136],"much":[138],"more":[139],"efficient":[140],"than":[141],"prior":[143],"art":[144],"K":[146],"nearest":[147],"neighbor":[148],"WMD.":[152],"Experimental":[153],"indicate":[155],"our":[157],"achieve":[160],"very":[161],"competitive":[162],"classification":[163],"performance":[164]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":7},{"year":2019,"cited_by_count":2}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}