{"id":"https://openalex.org/W2465804994","doi":"https://doi.org/10.1145/2911451.2914677","title":"ArabicWeb16","display_name":"ArabicWeb16","publication_year":2016,"publication_date":"2016-07-07","ids":{"openalex":"https://openalex.org/W2465804994","doi":"https://doi.org/10.1145/2911451.2914677","mag":"2465804994"},"language":"en","primary_location":{"id":"doi:10.1145/2911451.2914677","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2911451.2914677","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 39th International ACM SIGIR conference on Research and Development in Information Retrieval","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/A5047381062","display_name":"Reem Suwaileh","orcid":"https://orcid.org/0000-0001-7341-1407"},"institutions":[{"id":"https://openalex.org/I60342839","display_name":"Qatar University","ror":"https://ror.org/00yhnba62","country_code":"QA","type":"education","lineage":["https://openalex.org/I60342839"]}],"countries":["QA"],"is_corresponding":true,"raw_author_name":"Reem Suwaileh","raw_affiliation_strings":["Qatar University, Doha, Qatar"],"affiliations":[{"raw_affiliation_string":"Qatar University, Doha, Qatar","institution_ids":["https://openalex.org/I60342839"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086826049","display_name":"M\u00fccahid Kutlu","orcid":"https://orcid.org/0000-0002-5660-4992"},"institutions":[{"id":"https://openalex.org/I60342839","display_name":"Qatar University","ror":"https://ror.org/00yhnba62","country_code":"QA","type":"education","lineage":["https://openalex.org/I60342839"]}],"countries":["QA"],"is_corresponding":false,"raw_author_name":"Mucahid Kutlu","raw_affiliation_strings":["Qatar University, Doha, Qatar"],"affiliations":[{"raw_affiliation_string":"Qatar University, Doha, Qatar","institution_ids":["https://openalex.org/I60342839"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027098255","display_name":"Nihal Fathima","orcid":null},"institutions":[{"id":"https://openalex.org/I60342839","display_name":"Qatar University","ror":"https://ror.org/00yhnba62","country_code":"QA","type":"education","lineage":["https://openalex.org/I60342839"]}],"countries":["QA"],"is_corresponding":false,"raw_author_name":"Nihal Fathima","raw_affiliation_strings":["Qatar University, Doha, Qatar"],"affiliations":[{"raw_affiliation_string":"Qatar University, Doha, Qatar","institution_ids":["https://openalex.org/I60342839"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032141720","display_name":"Tamer Elsayed","orcid":"https://orcid.org/0000-0001-5786-4668"},"institutions":[{"id":"https://openalex.org/I60342839","display_name":"Qatar University","ror":"https://ror.org/00yhnba62","country_code":"QA","type":"education","lineage":["https://openalex.org/I60342839"]}],"countries":["QA"],"is_corresponding":false,"raw_author_name":"Tamer Elsayed","raw_affiliation_strings":["Qatar University, Doha, Qatar"],"affiliations":[{"raw_affiliation_string":"Qatar University, Doha, Qatar","institution_ids":["https://openalex.org/I60342839"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5023397430","display_name":"Matthew Lease","orcid":"https://orcid.org/0000-0002-0056-2834"},"institutions":[{"id":"https://openalex.org/I86519309","display_name":"The University of Texas at Austin","ror":"https://ror.org/00hj54h04","country_code":"US","type":"education","lineage":["https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Matthew Lease","raw_affiliation_strings":["University of Texas at Austin, Austin, USA"],"affiliations":[{"raw_affiliation_string":"University of Texas at Austin, Austin, USA","institution_ids":["https://openalex.org/I86519309"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5047381062"],"corresponding_institution_ids":["https://openalex.org/I60342839"],"apc_list":null,"apc_paid":null,"fwci":3.3174,"has_fulltext":false,"cited_by_count":17,"citation_normalized_percentile":{"value":0.93135116,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"673","last_page":"676"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9998999834060669,"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"}},"topics":[{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9998999834060669,"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/T13976","display_name":"Web visibility and informetrics","score":0.9878000020980835,"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/T12285","display_name":"Surface Chemistry and Catalysis","score":0.98580002784729,"subfield":{"id":"https://openalex.org/subfields/2204","display_name":"Biomedical Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7764335870742798},{"id":"https://openalex.org/keywords/arabic","display_name":"Arabic","score":0.6447355151176453},{"id":"https://openalex.org/keywords/variety","display_name":"Variety (cybernetics)","score":0.5782553553581238},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5563783645629883},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.55080246925354},{"id":"https://openalex.org/keywords/limiting","display_name":"Limiting","score":0.49027755856513977},{"id":"https://openalex.org/keywords/web-crawler","display_name":"Web crawler","score":0.4598020911216736},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.15759602189064026},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.08023408055305481},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.06492257118225098}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7764335870742798},{"id":"https://openalex.org/C96455323","wikidata":"https://www.wikidata.org/wiki/Q13955","display_name":"Arabic","level":2,"score":0.6447355151176453},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.5782553553581238},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5563783645629883},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.55080246925354},{"id":"https://openalex.org/C188198153","wikidata":"https://www.wikidata.org/wiki/Q1613840","display_name":"Limiting","level":2,"score":0.49027755856513977},{"id":"https://openalex.org/C13743948","wikidata":"https://www.wikidata.org/wiki/Q45842","display_name":"Web crawler","level":2,"score":0.4598020911216736},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.15759602189064026},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.08023408055305481},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.06492257118225098},{"id":"https://openalex.org/C78519656","wikidata":"https://www.wikidata.org/wiki/Q101333","display_name":"Mechanical engineering","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":2,"locations":[{"id":"doi:10.1145/2911451.2914677","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2911451.2914677","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 39th International ACM SIGIR conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"},{"id":"pmh:oai:qspace.qu.edu.qa:10576/22382","is_oa":false,"landing_page_url":"http://hdl.handle.net/10576/22382","pdf_url":null,"source":{"id":"https://openalex.org/S4306400014","display_name":"Qatar University QSpace (Qatar University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I60342839","host_organization_name":"Qatar University","host_organization_lineage":["https://openalex.org/I60342839"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Conference Paper"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.8199999928474426,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[{"id":"https://openalex.org/G985978767","display_name":null,"funder_award_id":"NPRP 7-1313-1-245","funder_id":"https://openalex.org/F4320332753","funder_display_name":"Qatar National Research Fund"}],"funders":[{"id":"https://openalex.org/F4320332753","display_name":"Qatar National Research Fund","ror":"https://ror.org/01svaqq28"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W84079877","https://openalex.org/W317797172","https://openalex.org/W1489992655","https://openalex.org/W2024244759","https://openalex.org/W2102698119","https://openalex.org/W2118131693","https://openalex.org/W2133986984","https://openalex.org/W2166968190","https://openalex.org/W2250278916","https://openalex.org/W2250783208","https://openalex.org/W2997591727","https://openalex.org/W4238169060","https://openalex.org/W4391418904","https://openalex.org/W6603373351","https://openalex.org/W6630516739","https://openalex.org/W6690971519"],"related_works":["https://openalex.org/W3005260231","https://openalex.org/W2904469652","https://openalex.org/W4362647146","https://openalex.org/W2383572231","https://openalex.org/W2042034567","https://openalex.org/W3179424333","https://openalex.org/W2782340266","https://openalex.org/W4230722125","https://openalex.org/W2149158941","https://openalex.org/W1566984846"],"abstract_inverted_index":{"Web":[0,7,21,47,53,71,77],"crawls":[1,48,54],"provide":[2,131],"valuable":[3],"snapshots":[4],"of":[5,13,25,73,82],"the":[6],"which":[8],"enable":[9],"a":[10,68,121],"wide":[11],"variety":[12],"research,":[14],"be":[15],"it":[16],"distributional":[17],"analysis":[18,28],"to":[19,37,97],"characterize":[20],"properties":[22],"or":[23,32],"use":[24,119],"language,":[26],"content":[27],"in":[29],"social":[30],"science,":[31],"Information":[33],"Retrieval":[34],"(IR)":[35],"research":[36,59,100],"develop":[38],"and":[39,60,115],"evaluate":[40],"effective":[41],"search":[42],"algorithms.":[43],"While":[44],"many":[45],"English-centric":[46],"exist,":[49],"existing":[50],"public":[51,70],"Arabic":[52,76,84,123],"are":[55,127],"quite":[56],"limited,":[57],"limiting":[58],"development.":[61],"To":[62],"remedy":[63],"this,":[64],"we":[65,94,126],"present":[66],"ArabicWeb16,":[67],"new":[69],"crawl":[72],"roughly":[74],"150M":[75],"pages":[78],"with":[79,120],"significant":[80],"coverage":[81],"dialectal":[83],"as":[85,87],"well":[86],"Modern":[88],"Standard":[89],"Arabic.":[90],"For":[91],"IR":[92],"researchers,":[93],"expect":[95],"ArabicWeb16":[96],"support":[98],"various":[99],"areas:":[101],"ad-hoc":[102],"search,":[103,108,112,114],"question":[104],"answering,":[105],"filtering,":[106],"cross-dialect":[107],"dialect":[109],"detection,":[110],"entity":[111],"blog":[113],"spam":[116],"detection.":[117],"Combined":[118],"separate":[122],"Twitter":[124],"dataset":[125],"also":[128],"collecting":[129],"may":[130],"further":[132],"value.":[133]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":3},{"year":2017,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2016-07-22T00:00:00"}
