{"id":"https://openalex.org/W2758820997","doi":"https://doi.org/10.18653/v1/w17-4407","title":"Simple Queries as Distant Labels for Predicting Gender on Twitter","display_name":"Simple Queries as Distant Labels for Predicting Gender on Twitter","publication_year":2017,"publication_date":"2017-01-01","ids":{"openalex":"https://openalex.org/W2758820997","doi":"https://doi.org/10.18653/v1/w17-4407","mag":"2758820997"},"language":"en","primary_location":{"id":"doi:10.18653/v1/w17-4407","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w17-4407","pdf_url":"https://www.aclweb.org/anthology/W17-4407.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 3rd Workshop on Noisy User-generated Text","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.aclweb.org/anthology/W17-4407.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5023265600","display_name":"Chris Emmery","orcid":"https://orcid.org/0000-0002-2179-559X"},"institutions":[{"id":"https://openalex.org/I149213910","display_name":"University of Antwerp","ror":"https://ror.org/008x57b05","country_code":"BE","type":"education","lineage":["https://openalex.org/I149213910"]},{"id":"https://openalex.org/I193700539","display_name":"Tilburg University","ror":"https://ror.org/04b8v1s79","country_code":"NL","type":"education","lineage":["https://openalex.org/I193700539"]}],"countries":["BE","NL"],"is_corresponding":false,"raw_author_name":"Chris Emmery","raw_affiliation_strings":["CLiPS, University of Antwerp, Prinsstraat 13, B-2000 Antwerpen, Belgium","TiCC, Tilburg University, 5000 LE Tilburg, The Netherlands"],"affiliations":[{"raw_affiliation_string":"CLiPS, University of Antwerp, Prinsstraat 13, B-2000 Antwerpen, Belgium","institution_ids":["https://openalex.org/I149213910"]},{"raw_affiliation_string":"TiCC, Tilburg University, 5000 LE Tilburg, The Netherlands","institution_ids":["https://openalex.org/I193700539"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022698890","display_name":"Grzegorz Chrupa\u0142a","orcid":"https://orcid.org/0000-0001-9498-6912"},"institutions":[{"id":"https://openalex.org/I193700539","display_name":"Tilburg University","ror":"https://ror.org/04b8v1s79","country_code":"NL","type":"education","lineage":["https://openalex.org/I193700539"]}],"countries":["NL"],"is_corresponding":true,"raw_author_name":"Grzegorz Chrupa\u0142a","raw_affiliation_strings":["TiCC, Tilburg University, 5000 LE Tilburg, The Netherlands"],"affiliations":[{"raw_affiliation_string":"TiCC, Tilburg University, 5000 LE Tilburg, The Netherlands","institution_ids":["https://openalex.org/I193700539"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5083411784","display_name":"Walter Daelemans","orcid":"https://orcid.org/0000-0002-9832-7890"},"institutions":[{"id":"https://openalex.org/I149213910","display_name":"University of Antwerp","ror":"https://ror.org/008x57b05","country_code":"BE","type":"education","lineage":["https://openalex.org/I149213910"]}],"countries":["BE"],"is_corresponding":false,"raw_author_name":"Walter Daelemans","raw_affiliation_strings":["CLiPS, University of Antwerp, Prinsstraat 13, B-2000 Antwerpen, Belgium"],"affiliations":[{"raw_affiliation_string":"CLiPS, University of Antwerp, Prinsstraat 13, B-2000 Antwerpen, Belgium","institution_ids":["https://openalex.org/I149213910"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5022698890"],"corresponding_institution_ids":["https://openalex.org/I193700539"],"apc_list":null,"apc_paid":null,"fwci":3.7054,"has_fulltext":true,"cited_by_count":26,"citation_normalized_percentile":{"value":0.94664201,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"50","last_page":"55"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12380","display_name":"Authorship Attribution and Profiling","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"}},"topics":[{"id":"https://openalex.org/T12380","display_name":"Authorship Attribution and Profiling","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/T11644","display_name":"Spam and Phishing Detection","score":0.9987000226974487,"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"}},{"id":"https://openalex.org/T12262","display_name":"Hate Speech and Cyberbullying Detection","score":0.9972000122070312,"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/computer-science","display_name":"Computer science","score":0.840861976146698},{"id":"https://openalex.org/keywords/annotation","display_name":"Annotation","score":0.6601409316062927},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6381275653839111},{"id":"https://openalex.org/keywords/social-media","display_name":"Social media","score":0.6288108229637146},{"id":"https://openalex.org/keywords/heuristic","display_name":"Heuristic","score":0.6016714572906494},{"id":"https://openalex.org/keywords/simple","display_name":"Simple (philosophy)","score":0.5924268960952759},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5314169526100159},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5297760963439941},{"id":"https://openalex.org/keywords/reliability","display_name":"Reliability (semiconductor)","score":0.48078030347824097},{"id":"https://openalex.org/keywords/supervised-learning","display_name":"Supervised learning","score":0.4753791391849518},{"id":"https://openalex.org/keywords/labeled-data","display_name":"Labeled data","score":0.46918344497680664},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4010104835033417},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3651393949985504},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.18856051564216614},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.06526285409927368}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.840861976146698},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.6601409316062927},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6381275653839111},{"id":"https://openalex.org/C518677369","wikidata":"https://www.wikidata.org/wiki/Q202833","display_name":"Social media","level":2,"score":0.6288108229637146},{"id":"https://openalex.org/C173801870","wikidata":"https://www.wikidata.org/wiki/Q201413","display_name":"Heuristic","level":2,"score":0.6016714572906494},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.5924268960952759},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5314169526100159},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5297760963439941},{"id":"https://openalex.org/C43214815","wikidata":"https://www.wikidata.org/wiki/Q7310987","display_name":"Reliability (semiconductor)","level":3,"score":0.48078030347824097},{"id":"https://openalex.org/C136389625","wikidata":"https://www.wikidata.org/wiki/Q334384","display_name":"Supervised learning","level":3,"score":0.4753791391849518},{"id":"https://openalex.org/C2776145971","wikidata":"https://www.wikidata.org/wiki/Q30673951","display_name":"Labeled data","level":2,"score":0.46918344497680664},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4010104835033417},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3651393949985504},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.18856051564216614},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.06526285409927368},{"id":"https://openalex.org/C163258240","wikidata":"https://www.wikidata.org/wiki/Q25342","display_name":"Power (physics)","level":2,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","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},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/w17-4407","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w17-4407","pdf_url":"https://www.aclweb.org/anthology/W17-4407.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 3rd Workshop on Noisy User-generated Text","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/w17-4407","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w17-4407","pdf_url":"https://www.aclweb.org/anthology/W17-4407.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 3rd Workshop on Noisy User-generated Text","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Quality Education","score":0.6499999761581421,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2758820997.pdf","grobid_xml":"https://content.openalex.org/works/W2758820997.grobid-xml"},"referenced_works_count":26,"referenced_works":["https://openalex.org/W9292421","https://openalex.org/W1014449310","https://openalex.org/W1614298861","https://openalex.org/W1770543141","https://openalex.org/W1914856875","https://openalex.org/W2025403586","https://openalex.org/W2033444463","https://openalex.org/W2051140133","https://openalex.org/W2138243089","https://openalex.org/W2144364794","https://openalex.org/W2152460337","https://openalex.org/W2154819126","https://openalex.org/W2250194349","https://openalex.org/W2250238316","https://openalex.org/W2250545651","https://openalex.org/W2250747954","https://openalex.org/W2251329024","https://openalex.org/W2251812186","https://openalex.org/W2252191003","https://openalex.org/W2252241921","https://openalex.org/W2466778245","https://openalex.org/W2468547970","https://openalex.org/W2572403455","https://openalex.org/W2950577311","https://openalex.org/W2963626623","https://openalex.org/W4393675269"],"related_works":["https://openalex.org/W3170999895","https://openalex.org/W4287117940","https://openalex.org/W34092691","https://openalex.org/W2131513867","https://openalex.org/W4312414840","https://openalex.org/W2952937263","https://openalex.org/W2036486025","https://openalex.org/W4300902524","https://openalex.org/W1614742790","https://openalex.org/W970023169"],"abstract_inverted_index":{"The":[0],"majority":[1],"of":[2,39,55,103],"research":[3],"on":[4,28,46,76,83],"extracting":[5],"missing":[6],"user":[7],"attributes":[8],"from":[9],"social":[10],"media":[11],"profiles":[12],"use":[13],"costly":[14],"hand-annotated":[15],"labels":[16,42,67],"for":[17,43,68],"supervised":[18,21],"learning.":[19],"Distantly":[20],"methods":[22],"exist,":[23],"although":[24],"these":[25,66],"generally":[26],"rely":[27],"knowledge":[29],"gathered":[30],"using":[31,48,65],"external":[32],"sources.":[33],"This":[34],"paper":[35],"demonstrates":[36],"the":[37,53,77,101],"effectiveness":[38],"gathering":[40],"distant":[41,69],"self-reported":[44],"gender":[45,104],"Twitter":[47],"simple":[49],"queries.":[50],"We":[51],"confirm":[52],"reliability":[54],"this":[56],"query":[57],"heuristic":[58],"by":[59],"comparing":[60],"with":[61],"manual":[62,84],"annotation.":[63],"Moreover,":[64],"supervision,":[70],"we":[71,88],"demonstrate":[72],"competitive":[73],"model":[74],"performance":[75],"same":[78],"data":[79],"as":[80],"models":[81],"trained":[82],"annotations.":[85],"As":[86],"such,":[87],"offer":[89],"a":[90],"cheap,":[91],"extensible,":[92],"and":[93],"fast":[94],"alternative":[95],"that":[96],"can":[97],"be":[98],"employed":[99],"beyond":[100],"task":[102],"classification.":[105]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":15}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}