{"id":"https://openalex.org/W2725310424","doi":"https://doi.org/10.18653/v1/w18-5406","title":"On the Role of Text Preprocessing in Neural Network Architectures: An Evaluation Study on Text Categorization and Sentiment Analysis","display_name":"On the Role of Text Preprocessing in Neural Network Architectures: An Evaluation Study on Text Categorization and Sentiment Analysis","publication_year":2018,"publication_date":"2018-01-01","ids":{"openalex":"https://openalex.org/W2725310424","doi":"https://doi.org/10.18653/v1/w18-5406","mag":"2725310424"},"language":"en","primary_location":{"id":"doi:10.18653/v1/w18-5406","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w18-5406","pdf_url":"https://www.aclweb.org/anthology/W18-5406.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2018 EMNLP Workshop BlackboxNLP: Analyzing and Interpreting Neural Networks for NLP","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.aclweb.org/anthology/W18-5406.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5086289154","display_name":"Jos\u00e9 Camacho-Collados","orcid":"https://orcid.org/0000-0003-1618-7239"},"institutions":[{"id":"https://openalex.org/I79510175","display_name":"Cardiff University","ror":"https://ror.org/03kk7td41","country_code":"GB","type":"education","lineage":["https://openalex.org/I79510175"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Jose Camacho-Collados","raw_affiliation_strings":["Cardiff University, Cardiff, United Kingdom"],"affiliations":[{"raw_affiliation_string":"Cardiff University, Cardiff, United Kingdom","institution_ids":["https://openalex.org/I79510175"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5091017313","display_name":"Mohammad Taher Pilehvar","orcid":"https://orcid.org/0000-0003-3694-4006"},"institutions":[{"id":"https://openalex.org/I241749","display_name":"University of Cambridge","ror":"https://ror.org/013meh722","country_code":"GB","type":"education","lineage":["https://openalex.org/I241749"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Mohammad Taher Pilehvar","raw_affiliation_strings":["University of Cambridge, Cambridge, United Kingdom"],"affiliations":[{"raw_affiliation_string":"University of Cambridge, Cambridge, United Kingdom","institution_ids":["https://openalex.org/I241749"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5086289154"],"corresponding_institution_ids":["https://openalex.org/I79510175"],"apc_list":null,"apc_paid":null,"fwci":2.1999,"has_fulltext":true,"cited_by_count":25,"citation_normalized_percentile":{"value":0.90320227,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"40","last_page":"46"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":1.0,"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":1.0,"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":0.9994999766349792,"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/lexical-analysis","display_name":"Lexical analysis","score":0.8527175188064575},{"id":"https://openalex.org/keywords/preprocessor","display_name":"Preprocessor","score":0.8440775871276855},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8141354918479919},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7156407833099365},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6536847352981567},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.6300133466720581},{"id":"https://openalex.org/keywords/categorization","display_name":"Categorization","score":0.620689868927002},{"id":"https://openalex.org/keywords/sentiment-analysis","display_name":"Sentiment analysis","score":0.5980886816978455},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.5477029085159302},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5027508735656738},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.44467946887016296},{"id":"https://openalex.org/keywords/data-pre-processing","display_name":"Data pre-processing","score":0.428510844707489},{"id":"https://openalex.org/keywords/text-processing","display_name":"Text processing","score":0.42376866936683655},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.38534101843833923},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.09690222144126892}],"concepts":[{"id":"https://openalex.org/C176982825","wikidata":"https://www.wikidata.org/wiki/Q835922","display_name":"Lexical analysis","level":2,"score":0.8527175188064575},{"id":"https://openalex.org/C34736171","wikidata":"https://www.wikidata.org/wiki/Q918333","display_name":"Preprocessor","level":2,"score":0.8440775871276855},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8141354918479919},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7156407833099365},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6536847352981567},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.6300133466720581},{"id":"https://openalex.org/C94124525","wikidata":"https://www.wikidata.org/wiki/Q912550","display_name":"Categorization","level":2,"score":0.620689868927002},{"id":"https://openalex.org/C66402592","wikidata":"https://www.wikidata.org/wiki/Q2271421","display_name":"Sentiment analysis","level":2,"score":0.5980886816978455},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.5477029085159302},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5027508735656738},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.44467946887016296},{"id":"https://openalex.org/C10551718","wikidata":"https://www.wikidata.org/wiki/Q5227332","display_name":"Data pre-processing","level":2,"score":0.428510844707489},{"id":"https://openalex.org/C2779500292","wikidata":"https://www.wikidata.org/wiki/Q14802672","display_name":"Text processing","level":2,"score":0.42376866936683655},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.38534101843833923},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.09690222144126892},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","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":4,"locations":[{"id":"doi:10.18653/v1/w18-5406","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w18-5406","pdf_url":"https://www.aclweb.org/anthology/W18-5406.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2018 EMNLP Workshop BlackboxNLP: Analyzing and Interpreting Neural Networks for NLP","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1707.01780","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1707.01780","pdf_url":"https://arxiv.org/pdf/1707.01780","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"mag:2725310424","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/1707.01780","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.1707.01780","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1707.01780","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"doi:10.18653/v1/w18-5406","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w18-5406","pdf_url":"https://www.aclweb.org/anthology/W18-5406.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2018 EMNLP Workshop BlackboxNLP: Analyzing and Interpreting Neural Networks for NLP","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.7799999713897705,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2725310424.pdf","grobid_xml":"https://content.openalex.org/works/W2725310424.grobid-xml"},"referenced_works_count":21,"referenced_works":["https://openalex.org/W1010415138","https://openalex.org/W1493036841","https://openalex.org/W1498763386","https://openalex.org/W2015861736","https://openalex.org/W2064675550","https://openalex.org/W2114524997","https://openalex.org/W2118020653","https://openalex.org/W2120615054","https://openalex.org/W2151835172","https://openalex.org/W2250539671","https://openalex.org/W2252215182","https://openalex.org/W2511478665","https://openalex.org/W2563361286","https://openalex.org/W2587019100","https://openalex.org/W2818642484","https://openalex.org/W2950133940","https://openalex.org/W2950577311","https://openalex.org/W2952186591","https://openalex.org/W2963042536","https://openalex.org/W2963921497","https://openalex.org/W3098090436"],"related_works":["https://openalex.org/W2963023579","https://openalex.org/W3005962342","https://openalex.org/W3034480528","https://openalex.org/W3128381090","https://openalex.org/W2904689355","https://openalex.org/W3021093086","https://openalex.org/W2991360844","https://openalex.org/W3124228121","https://openalex.org/W3189479912","https://openalex.org/W2950758593","https://openalex.org/W3004372417","https://openalex.org/W3136715451","https://openalex.org/W3046189927","https://openalex.org/W3185916216","https://openalex.org/W2966419214","https://openalex.org/W3105625590","https://openalex.org/W2370737581","https://openalex.org/W2885626378","https://openalex.org/W2897055746","https://openalex.org/W3157140304"],"abstract_inverted_index":{"Text":[0],"preprocessing":[1,28,49,103,132],"is":[2,92],"often":[3],"the":[4,8,35,44,59,107,117,130],"first":[5],"step":[6,115],"in":[7,20,34,116],"pipeline":[9],"of":[10,46,61,89,100,109],"a":[11,62,86],"Natural":[12],"Language":[13],"Processing":[14],"(NLP)":[15],"system,":[16],"with":[17],"potential":[18],"impact":[19,45],"its":[21,25],"final":[22],"performance.":[23],"Despite":[24],"importance,":[26],"text":[27,48,65,76,91],"has":[29],"not":[30],"received":[31],"much":[32],"attention":[33,111],"deep":[36],"learning":[37],"literature.":[38],"In":[39],"this":[40,113],"paper":[41],"we":[42],"investigate":[43],"simple":[47,87],"decisions":[50],"(particularly":[51],"tokenizing,":[52],"lemmatizing,":[53],"lowercasing":[54],"and":[55,78],"multiword":[56],"grouping)":[57],"on":[58,72],"performance":[60],"standard":[63,73],"neural":[64],"classifier.":[66],"We":[67],"perform":[68],"an":[69],"extensive":[70],"evaluation":[71,126],"benchmarks":[74],"from":[75],"categorization":[77],"sentiment":[79],"analysis.":[80],"While":[81],"our":[82,125],"experiments":[83],"show":[84],"that":[85],"tokenization":[88],"input":[90],"generally":[93],"adequate,":[94],"they":[95],"also":[96],"highlight":[97],"significant":[98],"degrees":[99],"variability":[101],"across":[102],"techniques.":[104],"This":[105],"reveals":[106],"importance":[108],"paying":[110],"to":[112],"usually-overlooked":[114],"pipeline,":[118],"particularly":[119],"when":[120],"comparing":[121],"different":[122],"models.":[123],"Finally,":[124],"provides":[127],"insights":[128],"into":[129],"best":[131],"practices":[133],"for":[134],"training":[135],"word":[136],"embeddings.":[137]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":7},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":6},{"year":2020,"cited_by_count":5},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}