{"id":"https://openalex.org/W2991402558","doi":"https://doi.org/10.26615/978-954-452-056-4_062","title":"Classification of Micro-Texts Using Sub-Word Embeddings","display_name":"Classification of Micro-Texts Using Sub-Word Embeddings","publication_year":2019,"publication_date":"2019-10-22","ids":{"openalex":"https://openalex.org/W2991402558","doi":"https://doi.org/10.26615/978-954-452-056-4_062","mag":"2991402558"},"language":"en","primary_location":{"id":"doi:10.26615/978-954-452-056-4_062","is_oa":true,"landing_page_url":"http://doi.org/10.26615/978-954-452-056-4_062","pdf_url":"https://doi.org/10.26615/978-954-452-056-4_062","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings - Natural Language Processing in a Deep Learning World","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.26615/978-954-452-056-4_062","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5040268488","display_name":"Mihir Joshi","orcid":null},"institutions":[{"id":"https://openalex.org/I129902397","display_name":"Dalhousie University","ror":"https://ror.org/01e6qks80","country_code":"CA","type":"education","lineage":["https://openalex.org/I129902397"]}],"countries":["CA"],"is_corresponding":true,"raw_author_name":"Mihir Joshi","raw_affiliation_strings":["Faculty of Computer Science Dalhousie University Halifax, Nova Scotia, Canada"],"affiliations":[{"raw_affiliation_string":"Faculty of Computer Science Dalhousie University Halifax, Nova Scotia, Canada","institution_ids":["https://openalex.org/I129902397"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5008462534","display_name":"A. Nur Zincir\u2010Heywood","orcid":"https://orcid.org/0000-0003-2796-7265"},"institutions":[{"id":"https://openalex.org/I129902397","display_name":"Dalhousie University","ror":"https://ror.org/01e6qks80","country_code":"CA","type":"education","lineage":["https://openalex.org/I129902397"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Nur Zincir-Heywood","raw_affiliation_strings":["Faculty of Computer Science Dalhousie University Halifax, Nova Scotia, Canada"],"affiliations":[{"raw_affiliation_string":"Faculty of Computer Science Dalhousie University Halifax, Nova Scotia, Canada","institution_ids":["https://openalex.org/I129902397"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5040268488"],"corresponding_institution_ids":["https://openalex.org/I129902397"],"apc_list":null,"apc_paid":null,"fwci":0.42,"has_fulltext":true,"cited_by_count":6,"citation_normalized_percentile":{"value":0.721148,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"526","last_page":"533"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12380","display_name":"Authorship Attribution and Profiling","score":0.9998999834060669,"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/T12380","display_name":"Authorship Attribution and Profiling","score":0.9998999834060669,"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":0.9973999857902527,"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/T11644","display_name":"Spam and Phishing Detection","score":0.9968000054359436,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8281416893005371},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.7339782118797302},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6696617007255554},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6673429012298584},{"id":"https://openalex.org/keywords/character","display_name":"Character (mathematics)","score":0.5919374823570251},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.5682632923126221},{"id":"https://openalex.org/keywords/word-embedding","display_name":"Word embedding","score":0.5370631814002991},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5222780704498291},{"id":"https://openalex.org/keywords/perceptron","display_name":"Perceptron","score":0.4777364134788513},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.4588715136051178},{"id":"https://openalex.org/keywords/layer","display_name":"Layer (electronics)","score":0.4545400142669678},{"id":"https://openalex.org/keywords/n-gram","display_name":"n-gram","score":0.41946983337402344},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3661564886569977},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.32879310846328735},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.28021514415740967},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.2450716197490692},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.10997626185417175}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8281416893005371},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.7339782118797302},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6696617007255554},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6673429012298584},{"id":"https://openalex.org/C2780861071","wikidata":"https://www.wikidata.org/wiki/Q1062934","display_name":"Character (mathematics)","level":2,"score":0.5919374823570251},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.5682632923126221},{"id":"https://openalex.org/C2777462759","wikidata":"https://www.wikidata.org/wiki/Q18395344","display_name":"Word embedding","level":3,"score":0.5370631814002991},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5222780704498291},{"id":"https://openalex.org/C60908668","wikidata":"https://www.wikidata.org/wiki/Q690207","display_name":"Perceptron","level":3,"score":0.4777364134788513},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.4588715136051178},{"id":"https://openalex.org/C2779227376","wikidata":"https://www.wikidata.org/wiki/Q6505497","display_name":"Layer (electronics)","level":2,"score":0.4545400142669678},{"id":"https://openalex.org/C117884012","wikidata":"https://www.wikidata.org/wiki/Q94489","display_name":"n-gram","level":3,"score":0.41946983337402344},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3661564886569977},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.32879310846328735},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.28021514415740967},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.2450716197490692},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.10997626185417175},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.26615/978-954-452-056-4_062","is_oa":true,"landing_page_url":"http://doi.org/10.26615/978-954-452-056-4_062","pdf_url":"https://doi.org/10.26615/978-954-452-056-4_062","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings - Natural Language Processing in a Deep Learning World","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.26615/978-954-452-056-4_062","is_oa":true,"landing_page_url":"http://doi.org/10.26615/978-954-452-056-4_062","pdf_url":"https://doi.org/10.26615/978-954-452-056-4_062","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings - Natural Language Processing in a Deep Learning World","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.8700000047683716,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320321629","display_name":"Dalhousie University","ror":"https://ror.org/01e6qks80"},{"id":"https://openalex.org/F4320334593","display_name":"Natural Sciences and Engineering Research Council of Canada","ror":"https://ror.org/01h531d29"},{"id":"https://openalex.org/F4320334904","display_name":"National Institute for Materials Science","ror":"https://ror.org/026v1ze26"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2991402558.pdf","grobid_xml":"https://content.openalex.org/works/W2991402558.grobid-xml"},"referenced_works_count":27,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1532325895","https://openalex.org/W1603920809","https://openalex.org/W1614298861","https://openalex.org/W1964455472","https://openalex.org/W1980867644","https://openalex.org/W2068737686","https://openalex.org/W2071629922","https://openalex.org/W2101234009","https://openalex.org/W2150102617","https://openalex.org/W2158899491","https://openalex.org/W2187089797","https://openalex.org/W2250966211","https://openalex.org/W2493916176","https://openalex.org/W2742157926","https://openalex.org/W2896457183","https://openalex.org/W2899374547","https://openalex.org/W2899675781","https://openalex.org/W2950577311","https://openalex.org/W2952230511","https://openalex.org/W2962739339","https://openalex.org/W2963026768","https://openalex.org/W2963341956","https://openalex.org/W2963355447","https://openalex.org/W2964121744","https://openalex.org/W4231934124","https://openalex.org/W4244053005"],"related_works":["https://openalex.org/W2081900870","https://openalex.org/W2906970013","https://openalex.org/W2037549926","https://openalex.org/W3126081632","https://openalex.org/W2345479200","https://openalex.org/W2349784553","https://openalex.org/W2183306018","https://openalex.org/W4286432911","https://openalex.org/W3043635985","https://openalex.org/W2899277986"],"abstract_inverted_index":{"Extracting":[0],"features":[1,75],"and":[2,57],"writing":[3],"styles":[4],"from":[5,76],"short":[6,80],"text":[7,81],"messages":[8],"is":[9,34,90],"always":[10],"a":[11,58,69,91],"challenge.":[12],"Short":[13],"messages,":[14],"like":[15],"tweets,":[16],"do":[17],"not":[18],"have":[19],"enough":[20],"data":[21],"to":[22,72,78],"perform":[23],"statistical":[24],"authorship":[25],"attribution.":[26],"Besides,":[27],"the":[28,63],"vocabulary":[29],"used":[30],"in":[31,40],"these":[32,74],"texts":[33],"sometimes":[35],"improvised":[36],"or":[37],"misspelled.":[38],"Therefore,":[39],"this":[41],"paper,":[42],"we":[43],"propose":[44],"combining":[45],"four":[46],"feature":[47],"extraction":[48],"techniques":[49],"namely":[50],"character":[51],"n-grams,":[52,54],"word":[53],"Flexible":[55],"Patterns":[56],"new":[59],"sub-word":[60],"embedding":[61],"using":[62],"skip-gram":[64],"model.":[65],"Our":[66],"system":[67,85],"uses":[68],"Multi-Layer":[70],"Perceptron":[71],"utilize":[73],"tweets":[77],"analyze":[79],"messages.":[82],"This":[83],"proposed":[84],"achieves":[86],"85%":[87],"accuracy,":[88],"which":[89],"considerable":[92],"improvement":[93],"over":[94],"previous":[95],"systems.":[96]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":1}],"updated_date":"2026-01-13T01:12:25.745995","created_date":"2019-12-05T00:00:00"}