{"id":"https://openalex.org/W2741456980","doi":"https://doi.org/10.1145/3077136.3080711","title":"One Million Posts","display_name":"One Million Posts","publication_year":2017,"publication_date":"2017-07-28","ids":{"openalex":"https://openalex.org/W2741456980","doi":"https://doi.org/10.1145/3077136.3080711","mag":"2741456980"},"language":"en","primary_location":{"id":"doi:10.1145/3077136.3080711","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3077136.3080711","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 40th International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"},"type":"conference-paper","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/A5021462938","display_name":"Dietmar Schabus","orcid":null},"institutions":[{"id":"https://openalex.org/I161878677","display_name":"Austrian Research Institute for Artificial Intelligence","ror":"https://ror.org/04j47vk14","country_code":"AT","type":"facility","lineage":["https://openalex.org/I161878677","https://openalex.org/I4210107880"]}],"countries":["AT"],"is_corresponding":false,"raw_author_name":"Dietmar Schabus","raw_affiliation_strings":["Austrian Research Institute for Artificial Intelligence (OFAI), Vienna, Austria"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Austrian Research Institute for Artificial Intelligence (OFAI), Vienna, Austria","institution_ids":["https://openalex.org/I161878677"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080235124","display_name":"Marcin Skowron","orcid":null},"institutions":[{"id":"https://openalex.org/I161878677","display_name":"Austrian Research Institute for Artificial Intelligence","ror":"https://ror.org/04j47vk14","country_code":"AT","type":"facility","lineage":["https://openalex.org/I161878677","https://openalex.org/I4210107880"]}],"countries":["AT"],"is_corresponding":false,"raw_author_name":"Marcin Skowron","raw_affiliation_strings":["Austrian Research Institute for Artificial Intelligence (OFAI), Vienna, Austria"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Austrian Research Institute for Artificial Intelligence (OFAI), Vienna, Austria","institution_ids":["https://openalex.org/I161878677"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5060407332","display_name":"Martin Trapp","orcid":"https://orcid.org/0000-0003-1725-3381"},"institutions":[{"id":"https://openalex.org/I161878677","display_name":"Austrian Research Institute for Artificial Intelligence","ror":"https://ror.org/04j47vk14","country_code":"AT","type":"facility","lineage":["https://openalex.org/I161878677","https://openalex.org/I4210107880"]}],"countries":["AT"],"is_corresponding":false,"raw_author_name":"Martin Trapp","raw_affiliation_strings":["Austrian Research Institute for Artificial Intelligence (OFAI), Vienna, Austria"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Austrian Research Institute for Artificial Intelligence (OFAI), Vienna, Austria","institution_ids":["https://openalex.org/I161878677"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I161878677"],"apc_list":null,"apc_paid":null,"fwci":1.6656,"has_fulltext":false,"cited_by_count":40,"citation_normalized_percentile":{"value":0.88608347,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1241","last_page":"1244"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12262","display_name":"Hate Speech and Cyberbullying Detection","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/T12262","display_name":"Hate Speech and Cyberbullying Detection","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/T13157","display_name":"Cancer-related gene regulation","score":0.9908000230789185,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9707000255584717,"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":0.7665891647338867},{"id":"https://openalex.org/keywords/newspaper","display_name":"Newspaper","score":0.7516127228736877},{"id":"https://openalex.org/keywords/german","display_name":"German","score":0.725354015827179},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5802944302558899},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.5670190453529358},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5521628856658936},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.4854186475276947},{"id":"https://openalex.org/keywords/moderation","display_name":"Moderation","score":0.4810478985309601},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.4750625789165497},{"id":"https://openalex.org/keywords/taxonomy","display_name":"Taxonomy (biology)","score":0.4666424095630646},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.44637569785118103},{"id":"https://openalex.org/keywords/data-set","display_name":"Data set","score":0.4105861783027649},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3476164937019348},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2305871546268463},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.1344992220401764},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.09060770273208618},{"id":"https://openalex.org/keywords/advertising","display_name":"Advertising","score":0.07372429966926575},{"id":"https://openalex.org/keywords/political-science","display_name":"Political science","score":0.06861412525177002}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7665891647338867},{"id":"https://openalex.org/C201280247","wikidata":"https://www.wikidata.org/wiki/Q11032","display_name":"Newspaper","level":2,"score":0.7516127228736877},{"id":"https://openalex.org/C154775046","wikidata":"https://www.wikidata.org/wiki/Q188","display_name":"German","level":2,"score":0.725354015827179},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5802944302558899},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.5670190453529358},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5521628856658936},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.4854186475276947},{"id":"https://openalex.org/C93225998","wikidata":"https://www.wikidata.org/wiki/Q1941972","display_name":"Moderation","level":2,"score":0.4810478985309601},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.4750625789165497},{"id":"https://openalex.org/C58642233","wikidata":"https://www.wikidata.org/wiki/Q8269924","display_name":"Taxonomy (biology)","level":2,"score":0.4666424095630646},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.44637569785118103},{"id":"https://openalex.org/C58489278","wikidata":"https://www.wikidata.org/wiki/Q1172284","display_name":"Data set","level":2,"score":0.4105861783027649},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3476164937019348},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2305871546268463},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.1344992220401764},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.09060770273208618},{"id":"https://openalex.org/C112698675","wikidata":"https://www.wikidata.org/wiki/Q37038","display_name":"Advertising","level":1,"score":0.07372429966926575},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.06861412525177002},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"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/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.0},{"id":"https://openalex.org/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","level":1,"score":0.0},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3077136.3080711","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3077136.3080711","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 40th International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.4300000071525574,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":11,"referenced_works":["https://openalex.org/W2036163530","https://openalex.org/W2061506397","https://openalex.org/W2064675550","https://openalex.org/W2124784993","https://openalex.org/W2131846894","https://openalex.org/W2157884984","https://openalex.org/W2164777277","https://openalex.org/W2340954483","https://openalex.org/W2563826943","https://openalex.org/W2596638843","https://openalex.org/W2950577311"],"related_works":["https://openalex.org/W2376554757","https://openalex.org/W612150824","https://openalex.org/W2361959990","https://openalex.org/W1596512750","https://openalex.org/W2383443050","https://openalex.org/W2367702734","https://openalex.org/W2100945520","https://openalex.org/W2386525189","https://openalex.org/W2360284199","https://openalex.org/W2620505790"],"abstract_inverted_index":{"In":[0,49],"this":[1,52],"paper":[2],"we":[3],"introduce":[4],"a":[5,18,72],"new":[6],"data":[7,58,80],"set":[8,59],"consisting":[9],"of":[10,17,40,46],"user":[11],"comments":[12],"posted":[13],"to":[14,30,51],"the":[15,37,44,57],"website":[16],"German-language":[19],"Austrian":[20],"newspaper.":[21],"Professional":[22],"forum":[23],"moderators":[24],"have":[25],"annotated":[26,55],"11,773":[27],"posts":[28],"according":[29],"seven":[31],"categories":[32],"they":[33],"considered":[34],"crucial":[35],"for":[36,75,86],"efficient":[38],"moderation":[39],"online":[41],"discussions":[42],"in":[43],"context":[45],"news":[47],"articles.":[48],"addition":[50],"taxonomy":[53],"and":[54,81],"posts,":[56],"contains":[60],"one":[61],"million":[62],"unlabeled":[63],"posts.":[64],"Our":[65],"experimental":[66],"results":[67],"using":[68],"six":[69],"methods":[70],"establish":[71],"first":[73],"baseline":[74],"predicting":[76],"these":[77],"categories.":[78],"The":[79],"our":[82],"code":[83],"are":[84],"available":[85],"research":[87],"purposes":[88],"from":[89],"https://ofai.github.io/million-post-corpus.":[90]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":7},{"year":2021,"cited_by_count":9},{"year":2020,"cited_by_count":6},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":4}],"updated_date":"2026-08-27T14:10:00.468798","created_date":"2017-08-08T00:00:00"}
