{"id":"https://openalex.org/W4306670816","doi":"https://doi.org/10.1007/s10579-022-09620-5","title":"The impact of preprocessing on word embedding quality: a comparative study","display_name":"The impact of preprocessing on word embedding quality: a comparative study","publication_year":2022,"publication_date":"2022-10-18","ids":{"openalex":"https://openalex.org/W4306670816","doi":"https://doi.org/10.1007/s10579-022-09620-5"},"language":"en","primary_location":{"id":"doi:10.1007/s10579-022-09620-5","is_oa":false,"landing_page_url":"https://doi.org/10.1007/s10579-022-09620-5","pdf_url":null,"source":{"id":"https://openalex.org/S4306424877","display_name":"Language Resources and Evaluation","issn_l":"1574-020X","issn":["1574-020X","1574-0218"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Language Resources and Evaluation","raw_type":"journal-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/A5108555937","display_name":"Zahra Rahimi","orcid":null},"institutions":[{"id":"https://openalex.org/I158248296","display_name":"Amirkabir University of Technology","ror":"https://ror.org/04gzbav43","country_code":"IR","type":"education","lineage":["https://openalex.org/I158248296"]}],"countries":["IR"],"is_corresponding":false,"raw_author_name":"Zahra Rahimi","raw_affiliation_strings":["Department of Computer Engineering and Information Technology, Amirkabir University of Technology, No. 350, Hafez Ave, Valiasr Square, Tehran, Iran"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Engineering and Information Technology, Amirkabir University of Technology, No. 350, Hafez Ave, Valiasr Square, Tehran, Iran","institution_ids":["https://openalex.org/I158248296"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5048230415","display_name":"Mohammad Mehdi Homayounpour","orcid":"https://orcid.org/0000-0002-2379-4427"},"institutions":[{"id":"https://openalex.org/I158248296","display_name":"Amirkabir University of Technology","ror":"https://ror.org/04gzbav43","country_code":"IR","type":"education","lineage":["https://openalex.org/I158248296"]}],"countries":["IR"],"is_corresponding":true,"raw_author_name":"Mohammad Mehdi Homayounpour","raw_affiliation_strings":["Department of Computer Engineering and Information Technology, Amirkabir University of Technology, No. 350, Hafez Ave, Valiasr Square, Tehran, Iran"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Engineering and Information Technology, Amirkabir University of Technology, No. 350, Hafez Ave, Valiasr Square, Tehran, Iran","institution_ids":["https://openalex.org/I158248296"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5048230415"],"corresponding_institution_ids":["https://openalex.org/I158248296"],"apc_list":{"value":3090,"currency":"USD","value_usd":3090},"apc_paid":null,"fwci":3.1317,"has_fulltext":false,"cited_by_count":34,"citation_normalized_percentile":{"value":0.92543851,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":100},"biblio":{"volume":"57","issue":"1","first_page":"257","last_page":"291"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","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/T10028","display_name":"Topic Modeling","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/T10181","display_name":"Natural Language Processing Techniques","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/T10664","display_name":"Sentiment Analysis and Opinion Mining","score":0.9983999729156494,"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/word","display_name":"Word (group theory)","score":0.780453085899353},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7574781179428101},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.7264423370361328},{"id":"https://openalex.org/keywords/preprocessor","display_name":"Preprocessor","score":0.6562063694000244},{"id":"https://openalex.org/keywords/analogy","display_name":"Analogy","score":0.6491332054138184},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6217530965805054},{"id":"https://openalex.org/keywords/word2vec","display_name":"Word2vec","score":0.6178051829338074},{"id":"https://openalex.org/keywords/word-embedding","display_name":"Word embedding","score":0.587690532207489},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.5398215055465698},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.32459554076194763},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.25801771879196167},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.17030873894691467}],"concepts":[{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.780453085899353},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7574781179428101},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.7264423370361328},{"id":"https://openalex.org/C34736171","wikidata":"https://www.wikidata.org/wiki/Q918333","display_name":"Preprocessor","level":2,"score":0.6562063694000244},{"id":"https://openalex.org/C521332185","wikidata":"https://www.wikidata.org/wiki/Q185816","display_name":"Analogy","level":2,"score":0.6491332054138184},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6217530965805054},{"id":"https://openalex.org/C2776461190","wikidata":"https://www.wikidata.org/wiki/Q22673982","display_name":"Word2vec","level":3,"score":0.6178051829338074},{"id":"https://openalex.org/C2777462759","wikidata":"https://www.wikidata.org/wiki/Q18395344","display_name":"Word embedding","level":3,"score":0.587690532207489},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.5398215055465698},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.32459554076194763},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.25801771879196167},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.17030873894691467},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"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:10.1007/s10579-022-09620-5","is_oa":false,"landing_page_url":"https://doi.org/10.1007/s10579-022-09620-5","pdf_url":null,"source":{"id":"https://openalex.org/S4306424877","display_name":"Language Resources and Evaluation","issn_l":"1574-020X","issn":["1574-020X","1574-0218"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Language Resources and Evaluation","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G6412334845","display_name":null,"funder_award_id":"97009308","funder_id":"https://openalex.org/F4320322243","funder_display_name":"Iran National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320322243","display_name":"Iran National Science Foundation","ror":"https://ror.org/03sr1ma14"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":51,"referenced_works":["https://openalex.org/W1614298861","https://openalex.org/W1714704734","https://openalex.org/W1854884267","https://openalex.org/W2014545475","https://openalex.org/W2026306693","https://openalex.org/W2026487812","https://openalex.org/W2067438047","https://openalex.org/W2080100102","https://openalex.org/W2103318667","https://openalex.org/W2142625445","https://openalex.org/W2164019165","https://openalex.org/W2176085882","https://openalex.org/W2250539671","https://openalex.org/W2251012068","https://openalex.org/W2477122767","https://openalex.org/W2493916176","https://openalex.org/W2509219942","https://openalex.org/W2749027244","https://openalex.org/W2753546666","https://openalex.org/W2753628379","https://openalex.org/W2754587509","https://openalex.org/W2756108899","https://openalex.org/W2765147810","https://openalex.org/W2767338551","https://openalex.org/W2794132063","https://openalex.org/W2889544455","https://openalex.org/W2892839738","https://openalex.org/W2898641722","https://openalex.org/W2900751963","https://openalex.org/W2900975931","https://openalex.org/W2902446432","https://openalex.org/W2918071347","https://openalex.org/W2920359981","https://openalex.org/W2923528470","https://openalex.org/W2953497520","https://openalex.org/W2963023579","https://openalex.org/W2963341956","https://openalex.org/W2963366649","https://openalex.org/W2963923670","https://openalex.org/W2965373594","https://openalex.org/W2970582332","https://openalex.org/W2980889633","https://openalex.org/W2982424689","https://openalex.org/W2982724023","https://openalex.org/W2993055513","https://openalex.org/W2997873848","https://openalex.org/W3098999920","https://openalex.org/W3125733373","https://openalex.org/W6679840752","https://openalex.org/W6680094886","https://openalex.org/W6751896580"],"related_works":["https://openalex.org/W2946409105","https://openalex.org/W2803176955","https://openalex.org/W2905749112","https://openalex.org/W3152932816","https://openalex.org/W2985392712","https://openalex.org/W3101154008","https://openalex.org/W3099354896","https://openalex.org/W3046869600","https://openalex.org/W4287599800","https://openalex.org/W2890749918"],"abstract_inverted_index":null,"counts_by_year":[{"year":2026,"cited_by_count":7},{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":12},{"year":2023,"cited_by_count":8},{"year":2022,"cited_by_count":1}],"updated_date":"2026-07-23T08:03:31.855105","created_date":"2025-10-10T00:00:00"}
