{"id":"https://openalex.org/W2950758593","doi":"https://doi.org/10.1145/3335595.3335632","title":"Comparative analysis of preprocessing tasks over social media texts in Spanish","display_name":"Comparative analysis of preprocessing tasks over social media texts in Spanish","publication_year":2019,"publication_date":"2019-06-20","ids":{"openalex":"https://openalex.org/W2950758593","doi":"https://doi.org/10.1145/3335595.3335632","mag":"2950758593"},"language":"en","primary_location":{"id":"doi:10.1145/3335595.3335632","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3335595.3335632","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the XX International Conference on Human Computer Interaction","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/A5014665895","display_name":"Juan Pablo Tessore","orcid":"https://orcid.org/0000-0002-2111-0976"},"institutions":[{"id":"https://openalex.org/I3130568980","display_name":"National University of Northwestern Buenos Aires","ror":"https://ror.org/00c8e6e47","country_code":"AR","type":"education","lineage":["https://openalex.org/I3130568980"]}],"countries":["AR"],"is_corresponding":true,"raw_author_name":"Juan Pablo Tessore","raw_affiliation_strings":["Instituto de Investigaci\u00f3n y Transferencia en Tecnolog\u00eda, Escuela de Tecnolog\u00eda, Universidad Nacional del Noroeste de la Provincia de Buenos Aires, Jun\u00edn, Buenos Aires, Argentina"],"affiliations":[{"raw_affiliation_string":"Instituto de Investigaci\u00f3n y Transferencia en Tecnolog\u00eda, Escuela de Tecnolog\u00eda, Universidad Nacional del Noroeste de la Provincia de Buenos Aires, Jun\u00edn, Buenos Aires, Argentina","institution_ids":["https://openalex.org/I3130568980"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038021933","display_name":"Leonardo Esnaola","orcid":"https://orcid.org/0000-0001-6298-9019"},"institutions":[{"id":"https://openalex.org/I3130568980","display_name":"National University of Northwestern Buenos Aires","ror":"https://ror.org/00c8e6e47","country_code":"AR","type":"education","lineage":["https://openalex.org/I3130568980"]}],"countries":["AR"],"is_corresponding":false,"raw_author_name":"Leonardo Mart\u00edn Esnaola","raw_affiliation_strings":["Instituto de Investigaci\u00f3n y Transferencia en Tecnolog\u00eda, Escuela de Tecnolog\u00eda, Universidad Nacional del Noroeste de la Provincia de Buenos Aires, Jun\u00edn, Buenos Aires, Argentina"],"affiliations":[{"raw_affiliation_string":"Instituto de Investigaci\u00f3n y Transferencia en Tecnolog\u00eda, Escuela de Tecnolog\u00eda, Universidad Nacional del Noroeste de la Provincia de Buenos Aires, Jun\u00edn, Buenos Aires, Argentina","institution_ids":["https://openalex.org/I3130568980"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101848074","display_name":"Claudia Russo","orcid":"https://orcid.org/0000-0002-0345-4783"},"institutions":[{"id":"https://openalex.org/I3130568980","display_name":"National University of Northwestern Buenos Aires","ror":"https://ror.org/00c8e6e47","country_code":"AR","type":"education","lineage":["https://openalex.org/I3130568980"]}],"countries":["AR"],"is_corresponding":false,"raw_author_name":"Claudia Cecilia Russo","raw_affiliation_strings":["Instituto de Investigaci\u00f3n y Transferencia en Tecnolog\u00eda, Escuela de Tecnolog\u00eda, Universidad Nacional del Noroeste de la Provincia de Buenos Aires, Jun\u00edn, Buenos Aires, Argentina"],"affiliations":[{"raw_affiliation_string":"Instituto de Investigaci\u00f3n y Transferencia en Tecnolog\u00eda, Escuela de Tecnolog\u00eda, Universidad Nacional del Noroeste de la Provincia de Buenos Aires, Jun\u00edn, Buenos Aires, Argentina","institution_ids":["https://openalex.org/I3130568980"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5067130992","display_name":"Sandra Baldassarri","orcid":"https://orcid.org/0000-0002-9315-6391"},"institutions":[{"id":"https://openalex.org/I255234318","display_name":"Universidad de Zaragoza","ror":"https://ror.org/012a91z28","country_code":"ES","type":"education","lineage":["https://openalex.org/I255234318"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Sandra Baldassarri","raw_affiliation_strings":["Departamento de Inform\u00e1tica e Ingenier\u00eda de Sistemas Escuela de Ingenier\u00eda y Arquitectura, Universidad de Zaragoza, Zaragoza, Arag\u00f3n, Espa\u00f1a"],"affiliations":[{"raw_affiliation_string":"Departamento de Inform\u00e1tica e Ingenier\u00eda de Sistemas Escuela de Ingenier\u00eda y Arquitectura, Universidad de Zaragoza, Zaragoza, Arag\u00f3n, Espa\u00f1a","institution_ids":["https://openalex.org/I255234318"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5014665895"],"corresponding_institution_ids":["https://openalex.org/I3130568980"],"apc_list":null,"apc_paid":null,"fwci":0.4201,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.70243535,"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":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10664","display_name":"Sentiment Analysis and Opinion Mining","score":0.9962999820709229,"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/T10664","display_name":"Sentiment Analysis and Opinion Mining","score":0.9962999820709229,"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":0.9319999814033508,"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/T13814","display_name":"Cultural and political discourse analysis","score":0.9135000109672546,"subfield":{"id":"https://openalex.org/subfields/3310","display_name":"Linguistics and Language"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8254595994949341},{"id":"https://openalex.org/keywords/preprocessor","display_name":"Preprocessor","score":0.7405824065208435},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6347628831863403},{"id":"https://openalex.org/keywords/data-pre-processing","display_name":"Data pre-processing","score":0.620837390422821},{"id":"https://openalex.org/keywords/social-media","display_name":"Social media","score":0.5855317115783691},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.5772514939308167},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.49413469433784485},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.48325973749160767},{"id":"https://openalex.org/keywords/noisy-data","display_name":"Noisy data","score":0.47462475299835205},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.4553442895412445},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.21695491671562195},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.08405673503875732}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8254595994949341},{"id":"https://openalex.org/C34736171","wikidata":"https://www.wikidata.org/wiki/Q918333","display_name":"Preprocessor","level":2,"score":0.7405824065208435},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6347628831863403},{"id":"https://openalex.org/C10551718","wikidata":"https://www.wikidata.org/wiki/Q5227332","display_name":"Data pre-processing","level":2,"score":0.620837390422821},{"id":"https://openalex.org/C518677369","wikidata":"https://www.wikidata.org/wiki/Q202833","display_name":"Social media","level":2,"score":0.5855317115783691},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.5772514939308167},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49413469433784485},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.48325973749160767},{"id":"https://openalex.org/C2781170535","wikidata":"https://www.wikidata.org/wiki/Q30587856","display_name":"Noisy data","level":2,"score":0.47462475299835205},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.4553442895412445},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.21695491671562195},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.08405673503875732},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3335595.3335632","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3335595.3335632","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the XX International Conference on Human Computer Interaction","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.4699999988079071}],"awards":[],"funders":[{"id":"https://openalex.org/F4320320300","display_name":"European Commission","ror":"https://ror.org/00k4n6c32"},{"id":"https://openalex.org/F4320324111","display_name":"Universidad de Zaragoza","ror":"https://ror.org/012a91z28"},{"id":"https://openalex.org/F4320330594","display_name":"Universidad Nacional del Noroeste de la Provincia de Buenos Aires","ror":"https://ror.org/00c8e6e47"},{"id":"https://openalex.org/F4320335124","display_name":"Comisi\u00f3n de Investigaciones Cient\u00edficas","ror":"https://ror.org/02s7sax82"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W40563694","https://openalex.org/W1553529581","https://openalex.org/W1970592556","https://openalex.org/W1973400823","https://openalex.org/W2016443085","https://openalex.org/W2025954161","https://openalex.org/W2027860007","https://openalex.org/W2032355794","https://openalex.org/W2107362686","https://openalex.org/W2148506018","https://openalex.org/W2215376118","https://openalex.org/W2276092518","https://openalex.org/W2462631134","https://openalex.org/W2562617836","https://openalex.org/W2588486023","https://openalex.org/W2598551448","https://openalex.org/W2739701878","https://openalex.org/W2911405777","https://openalex.org/W2982068029","https://openalex.org/W3023728302"],"related_works":["https://openalex.org/W3107474891","https://openalex.org/W2382928216","https://openalex.org/W4211198717","https://openalex.org/W3083272626","https://openalex.org/W1585034923","https://openalex.org/W1986684738","https://openalex.org/W2952736244","https://openalex.org/W2116984840","https://openalex.org/W1570070578","https://openalex.org/W2096504421"],"abstract_inverted_index":{"One":[0],"of":[1,5,24,27,59,86,127,143],"the":[2,6,25,57,60,67,77,84,97,144],"key":[3],"aspects":[4],"texts":[7],"coming":[8],"from":[9],"social":[10],"media":[11],"is":[12,21,49,125],"that":[13,69,83,118,132,140],"they":[14],"tend":[15],"to":[16,37,52,134],"be":[17],"very":[18,111],"noisy.":[19],"This":[20,62,123],"mainly":[22],"because":[23],"usage":[26],"informal":[28],"language":[29],"and":[30,55,72,92],"non-standard":[31],"grammatical":[32],"structures.":[33],"Therefore,":[34],"in":[35,113,120],"order":[36],"use":[38,142],"these":[39],"contents":[40],"as":[41,147],"input":[42],"for":[43],"a":[44,128],"text":[45],"analysis":[46],"process,":[47],"it":[48],"highly":[50],"recommended":[51],"previously":[53],"clean":[54],"reduce":[56],"noise":[58],"data.":[61,78],"work":[63],"focuses":[64],"on":[65,76],"measuring":[66],"effectiveness":[68],"diverse":[70],"cleaning":[71],"repairing":[73],"tasks":[74,85,103],"have":[75],"The":[79],"results":[80],"obtained,":[81],"indicate":[82],"\"tokens":[87],"with":[88],"no":[89],"letters":[90],"removal\",":[91],"\"stressed":[93],"words":[94],"processing\"":[95],"are":[96,116],"most":[98],"effective.":[99],"In":[100],"addition,":[101],"some":[102],"like":[104],"hashtags":[105],"or":[106],"usernames":[107],"processing,":[108],"which":[109],"behave":[110],"well":[112],"other":[114],"datasets,":[115],"not":[117],"relevant":[119],"this":[121],"one.":[122],"research":[124],"part":[126],"more":[129],"general":[130],"one":[131],"pursues":[133],"build":[135],"an":[136],"automatic":[137],"emotion":[138],"classifier":[139],"makes":[141],"preprocessed":[145],"comments":[146],"input.":[148]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}