{"id":"https://openalex.org/W2896904757","doi":"https://doi.org/10.1109/ijcnn.2018.8489431","title":"Using Semantic Clustering And Autoencoders For Detecting Novelty In Corpora Of Short Texts","display_name":"Using Semantic Clustering And Autoencoders For Detecting Novelty In Corpora Of Short Texts","publication_year":2018,"publication_date":"2018-07-01","ids":{"openalex":"https://openalex.org/W2896904757","doi":"https://doi.org/10.1109/ijcnn.2018.8489431","mag":"2896904757"},"language":"en","primary_location":{"id":"doi:10.1109/ijcnn.2018.8489431","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn.2018.8489431","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 International Joint Conference on Neural Networks (IJCNN)","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/A5101751494","display_name":"Mei Mei","orcid":"https://orcid.org/0000-0001-7126-3746"},"institutions":[{"id":"https://openalex.org/I63135867","display_name":"University of Cincinnati","ror":"https://ror.org/01e3m7079","country_code":"US","type":"education","lineage":["https://openalex.org/I63135867"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mei Mei","raw_affiliation_strings":["Department of Electrical Engineering and Computer Science, University of Cincinnati, OH"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering and Computer Science, University of Cincinnati, OH","institution_ids":["https://openalex.org/I63135867"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101518209","display_name":"Xinyu Guo","orcid":"https://orcid.org/0000-0003-1119-4173"},"institutions":[{"id":"https://openalex.org/I63135867","display_name":"University of Cincinnati","ror":"https://ror.org/01e3m7079","country_code":"US","type":"education","lineage":["https://openalex.org/I63135867"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xinyu Guo","raw_affiliation_strings":["Department of Electrical Engineering and Computer Science, University of Cincinnati, OH"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering and Computer Science, University of Cincinnati, OH","institution_ids":["https://openalex.org/I63135867"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036905489","display_name":"Belinda C. Williams","orcid":null},"institutions":[{"id":"https://openalex.org/I189196454","display_name":"The University of Texas at Arlington","ror":"https://ror.org/019kgqr73","country_code":"US","type":"education","lineage":["https://openalex.org/I189196454"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Belinda C. Williams","raw_affiliation_strings":["Department of Psychology, University of Texas at Arlington, TX"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Psychology, University of Texas at Arlington, TX","institution_ids":["https://openalex.org/I189196454"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005741308","display_name":"Simona Doboli","orcid":"https://orcid.org/0000-0003-0158-4725"},"institutions":[{"id":"https://openalex.org/I139290212","display_name":"Hofstra University","ror":"https://ror.org/03pm18j10","country_code":"US","type":"education","lineage":["https://openalex.org/I139290212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Simona Doboli","raw_affiliation_strings":["Department of Computer Science, Hofstra University, Hempstead, New York"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Hofstra University, Hempstead, New York","institution_ids":["https://openalex.org/I139290212"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020533881","display_name":"Jared B. Kenworthy","orcid":"https://orcid.org/0000-0003-2517-6662"},"institutions":[{"id":"https://openalex.org/I189196454","display_name":"The University of Texas at Arlington","ror":"https://ror.org/019kgqr73","country_code":"US","type":"education","lineage":["https://openalex.org/I189196454"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jared B. Kenworthy","raw_affiliation_strings":["Department of Psychology, University of Texas at Arlington, TX"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Psychology, University of Texas at Arlington, TX","institution_ids":["https://openalex.org/I189196454"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109574869","display_name":"Paul B. Paulus","orcid":null},"institutions":[{"id":"https://openalex.org/I189196454","display_name":"The University of Texas at Arlington","ror":"https://ror.org/019kgqr73","country_code":"US","type":"education","lineage":["https://openalex.org/I189196454"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Paul B. Paulus","raw_affiliation_strings":["Department of Psychology, University of Texas at Arlington, TX"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Psychology, University of Texas at Arlington, TX","institution_ids":["https://openalex.org/I189196454"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5033722814","display_name":"Ali A. Minai","orcid":"https://orcid.org/0000-0001-9727-1701"},"institutions":[{"id":"https://openalex.org/I63135867","display_name":"University of Cincinnati","ror":"https://ror.org/01e3m7079","country_code":"US","type":"education","lineage":["https://openalex.org/I63135867"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ali A. Minai","raw_affiliation_strings":["Department of Electrical Engineering and Computer Science, University of Cincinnati, OH"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering and Computer Science, University of Cincinnati, OH","institution_ids":["https://openalex.org/I63135867"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.6552,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.77321067,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":95},"biblio":{"volume":"20","issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13083","display_name":"Advanced Text Analysis Techniques","score":0.9976999759674072,"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/T13083","display_name":"Advanced Text Analysis Techniques","score":0.9976999759674072,"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":0.9943000078201294,"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":0.9926000237464905,"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/autoencoder","display_name":"Autoencoder","score":0.8422218561172485},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.798848032951355},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.6921600103378296},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.606441080570221},{"id":"https://openalex.org/keywords/novelty","display_name":"Novelty","score":0.5680760741233826},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5323790907859802},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.5283399820327759},{"id":"https://openalex.org/keywords/space","display_name":"Space (punctuation)","score":0.45016205310821533},{"id":"https://openalex.org/keywords/dimensionality-reduction","display_name":"Dimensionality reduction","score":0.43404895067214966},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.38664335012435913},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.350449800491333},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3298330008983612},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.22391670942306519}],"concepts":[{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.8422218561172485},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.798848032951355},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.6921600103378296},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.606441080570221},{"id":"https://openalex.org/C2778738651","wikidata":"https://www.wikidata.org/wiki/Q16546687","display_name":"Novelty","level":2,"score":0.5680760741233826},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5323790907859802},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.5283399820327759},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.45016205310821533},{"id":"https://openalex.org/C70518039","wikidata":"https://www.wikidata.org/wiki/Q16000077","display_name":"Dimensionality reduction","level":2,"score":0.43404895067214966},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.38664335012435913},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.350449800491333},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3298330008983612},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.22391670942306519},{"id":"https://openalex.org/C27206212","wikidata":"https://www.wikidata.org/wiki/Q34178","display_name":"Theology","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","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:10.1109/ijcnn.2018.8489431","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn.2018.8489431","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5600000023841858,"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10"},{"score":0.4000000059604645,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":38,"referenced_works":["https://openalex.org/W1490430947","https://openalex.org/W1533861849","https://openalex.org/W1536258620","https://openalex.org/W1876967670","https://openalex.org/W1972118683","https://openalex.org/W1972262362","https://openalex.org/W1979625382","https://openalex.org/W1980974094","https://openalex.org/W1987971958","https://openalex.org/W1990277796","https://openalex.org/W2027634772","https://openalex.org/W2036763306","https://openalex.org/W2053155195","https://openalex.org/W2072644219","https://openalex.org/W2086438570","https://openalex.org/W2087603196","https://openalex.org/W2095038093","https://openalex.org/W2106154564","https://openalex.org/W2122301051","https://openalex.org/W2124208340","https://openalex.org/W2125656037","https://openalex.org/W2130764762","https://openalex.org/W2144343387","https://openalex.org/W2160631673","https://openalex.org/W2168068255","https://openalex.org/W2433250023","https://openalex.org/W2482371029","https://openalex.org/W2742557696","https://openalex.org/W2913932916","https://openalex.org/W2938829626","https://openalex.org/W2964261549","https://openalex.org/W4231160248","https://openalex.org/W4244765626","https://openalex.org/W4256201318","https://openalex.org/W4285719527","https://openalex.org/W6631943919","https://openalex.org/W6647123778","https://openalex.org/W6742287796"],"related_works":["https://openalex.org/W3013693939","https://openalex.org/W2159052453","https://openalex.org/W2566616303","https://openalex.org/W2381242807","https://openalex.org/W3131327266","https://openalex.org/W2734887215","https://openalex.org/W4310873165","https://openalex.org/W2355395139","https://openalex.org/W4285596704","https://openalex.org/W2994280181"],"abstract_inverted_index":{"Semantic":[0],"analysis":[1],"of":[2,6,24,30,51,78,129,136,194,202],"text":[3],"corpora":[4],"is":[5,58,116,131,144,158,165],"broad":[7],"utility,":[8],"including":[9],"for":[10,175],"data":[11,41,164,177,186,238],"from":[12,42,89],"conversations,":[13],"on-line":[14,79],"chats,":[15],"brainstorming":[16,46],"sessions,":[17],"comments":[18],"on":[19],"blogs,":[20],"etc.":[21],"-":[22],"all":[23],"which":[25,61],"are":[26,63,102,240],"potentially":[27],"interesting":[28],"sources":[29],"information":[31],"and":[32,92,112,189,197],"ideas.":[33],"In":[34,70,211],"the":[35,67,98,139,160,163,169,191,195,198,203,206,226,229,233,237],"present":[36,99],"paper,":[37],"we":[38,93],"look":[39],"at":[40],"a":[43,105,153],"large":[44],"group":[45],"experiment":[47],"that":[48,180,190,214,239],"generated":[49],"thousands":[50],"mostly":[52],"brief":[53],"statements.":[54],"The":[55,123,172,220],"ultimate":[56],"goal":[57],"to":[59,86,118,133],"detect":[60],"statements":[62],"semantically":[64],"atypical":[65,90],"within":[66],"overall":[68],"corpus.":[69],"contexts":[71],"such":[72],"as":[73],"spam":[74],"detection":[75,77],"or":[76],"intrusions,":[80],"autoencoders":[81,213],"have":[82],"been":[83],"used":[84,117],"successfully":[85],"separate":[87],"typical":[88],"data,":[91],"consider":[94],"this":[95,157,209],"approach":[96],"in":[97,104,138,168,205,225,236],"paper.":[100],"Texts":[101],"embedded":[103,121],"semantic":[106],"space":[107],"obtained":[108],"through":[109],"topic":[110],"analysis,":[111],"an":[113,244],"autoencoder":[114,230],"network":[115],"reconstruct":[119],"each":[120,176],"text.":[122],"results":[124,221],"show":[125,223],"that,":[126,224],"while":[127],"difficulty":[128],"reconstruction":[130,173,200,227],"related":[132],"quantitative":[134],"measures":[135],"atypicality":[137],"embedding":[140,170],"vector":[141],"space,":[142],"it":[143],"not":[145,159],"well":[146],"correlated":[147],"with":[148],"novelty":[149],"assignments":[150],"made":[151],"by":[152,243],"human":[154],"rater.":[155],"However,":[156],"case":[161],"when":[162],"first":[166],"clustered":[167],"space:":[171],"error":[174,201],"cluster":[178,196,207],"indicates":[179],"some":[181],"clusters":[182,235],"represent":[183],"more":[184],"novel":[185],"than":[187],"others,":[188],"inverse":[192],"size":[193],"mean":[199],"texts":[204],"capture":[208],"well.":[210],"particular,":[212],"enforce":[215],"dimensionality":[216],"reduction":[217],"improve":[218],"discrimination.":[219],"also":[222],"process,":[228],"implicitly":[231],"discovers":[232],"same":[234],"discovered":[241],"explicitly":[242],"optimized":[245],"k-means":[246],"approach.":[247]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}