{"id":"https://openalex.org/W3155040665","doi":"https://doi.org/10.1145/3404835.3463251","title":"Seer-Dock: A General-Purpose Dockerized Scholarly Document Collection and Management Framework","display_name":"Seer-Dock: A General-Purpose Dockerized Scholarly Document Collection and Management Framework","publication_year":2021,"publication_date":"2021-07-11","ids":{"openalex":"https://openalex.org/W3155040665","doi":"https://doi.org/10.1145/3404835.3463251","mag":"3155040665"},"language":"en","primary_location":{"id":"doi:10.1145/3404835.3463251","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3404835.3463251","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 44th 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/A5058607205","display_name":"Dina Sayed","orcid":null},"institutions":[{"id":"https://openalex.org/I1850255","display_name":"University of Basel","ror":"https://ror.org/02s6k3f65","country_code":"CH","type":"education","lineage":["https://openalex.org/I1850255"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Dina Sayed","raw_affiliation_strings":["University of Basel, Basel, Switzerland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Basel, Basel, Switzerland","institution_ids":["https://openalex.org/I1850255"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006730217","display_name":"Mohamed Abdalla Nour","orcid":"https://orcid.org/0000-0001-7252-3546"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mohamed Nour","raw_affiliation_strings":["Independent Researcher, Cairo, Egypt"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Independent Researcher, Cairo, Egypt","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5034703920","display_name":"Heiko Schuldt","orcid":"https://orcid.org/0000-0001-9865-6371"},"institutions":[{"id":"https://openalex.org/I1850255","display_name":"University of Basel","ror":"https://ror.org/02s6k3f65","country_code":"CH","type":"education","lineage":["https://openalex.org/I1850255"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Heiko Schuldt","raw_affiliation_strings":["University of Basel, Basel, Switzerland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Basel, Basel, Switzerland","institution_ids":["https://openalex.org/I1850255"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2485","last_page":"2490"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11986","display_name":"Scientific Computing and Data Management","score":0.9919999837875366,"subfield":{"id":"https://openalex.org/subfields/1802","display_name":"Information Systems and Management"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T11986","display_name":"Scientific Computing and Data Management","score":0.9919999837875366,"subfield":{"id":"https://openalex.org/subfields/1802","display_name":"Information Systems and Management"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T13523","display_name":"Mathematics, Computing, and Information Processing","score":0.9896000027656555,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/T12016","display_name":"Web Data Mining and Analysis","score":0.9865000247955322,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7547467947006226},{"id":"https://openalex.org/keywords/dock","display_name":"DOCK","score":0.7297441959381104},{"id":"https://openalex.org/keywords/license","display_name":"License","score":0.5192263722419739},{"id":"https://openalex.org/keywords/resource-management","display_name":"Resource management (computing)","score":0.43089812994003296},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.4283221364021301},{"id":"https://openalex.org/keywords/resource","display_name":"Resource (disambiguation)","score":0.41277122497558594},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.39580702781677246},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.2943498492240906},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.1412818729877472},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.12779828906059265},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.080343097448349}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7547467947006226},{"id":"https://openalex.org/C93073132","wikidata":"https://www.wikidata.org/wiki/Q24726581","display_name":"DOCK","level":2,"score":0.7297441959381104},{"id":"https://openalex.org/C2780560020","wikidata":"https://www.wikidata.org/wiki/Q79719","display_name":"License","level":2,"score":0.5192263722419739},{"id":"https://openalex.org/C2780609101","wikidata":"https://www.wikidata.org/wiki/Q17156588","display_name":"Resource management (computing)","level":2,"score":0.43089812994003296},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.4283221364021301},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.41277122497558594},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.39580702781677246},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.2943498492240906},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.1412818729877472},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.12779828906059265},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.080343097448349},{"id":"https://openalex.org/C199104240","wikidata":"https://www.wikidata.org/wiki/Q118291","display_name":"Marine engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3404835.3463251","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3404835.3463251","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 44th International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":10,"referenced_works":["https://openalex.org/W1598708917","https://openalex.org/W1970099454","https://openalex.org/W2010879256","https://openalex.org/W2048715559","https://openalex.org/W2084745915","https://openalex.org/W2091339784","https://openalex.org/W2244650364","https://openalex.org/W2295508865","https://openalex.org/W2978352415","https://openalex.org/W3015319269"],"related_works":["https://openalex.org/W1583884134","https://openalex.org/W2808384273","https://openalex.org/W4225714443","https://openalex.org/W4256111125","https://openalex.org/W4230770129","https://openalex.org/W759941183","https://openalex.org/W2497061382","https://openalex.org/W2022220038","https://openalex.org/W2357049710","https://openalex.org/W4244145541"],"abstract_inverted_index":{"The":[0],"harvesting,":[1],"management,":[2],"and":[3,44,60,72,94,106,114,133,145],"analysis":[4],"of":[5,17,121,143],"thematic":[6],"document":[7,70,104],"collections":[8,25],"is":[9,31,36,76,127,153],"a":[10,14,58,68,102],"major":[11],"challenge":[12],"in":[13],"wide":[15],"variety":[16],"applications.":[18],"While":[19],"the":[20,28,80,118,141],"criteria":[21],"for":[22,91],"compiling":[23],"such":[24],"are":[26],"individual,":[27],"entire":[29],"process":[30],"largely":[32],"standardized.":[33],"Therefore,":[34],"it":[35,116,126],"not":[37],"efficient":[38],"to":[39,47,66,99,117,129],"build":[40,67],"new":[41],"systems":[42],"over":[43,45,49],"again":[46],"take":[48],"these":[50],"tasks.":[51],"In":[52,135],"this":[53,136],"work,":[54],"we":[55,139],"introduce":[56,140],"Seer-Dock,":[57],"novel":[59],"easy-to":[61],"deploy":[62,101],"general-purpose":[63],"dockerized":[64],"framework":[65],"scholarly":[69,84],"harvesting":[71],"management":[73,107],"system.":[74],"It":[75],"based":[77],"on":[78,109],"CiteSeerX,":[79,151],"most":[81],"widely":[82],"used":[83],"search":[85],"engine.":[86],"Seer-Dock":[87,144,152],"uses":[88],"docker":[89],"containers":[90],"all":[92],"components":[93],"thus":[95],"enables":[96],"its":[97,146,149],"users":[98],"rapidly":[100],"full-fledged":[103],"collection":[105],"system":[108,112],"any":[110],"operating":[111],"platform":[113],"tailor":[115],"specific":[119],"needs":[120],"an":[122,156],"application":[123],"domain.":[124],"Moreover,":[125],"easy":[128],"scale,":[130],"orchestrate,":[131],"maintain,":[132],"recover.":[134],"resource":[137],"paper,":[138],"architecture":[142],"components.":[147],"Like":[148],"kernel":[150],"available":[154],"under":[155],"Apache":[157],"2":[158],"open":[159],"source":[160],"license.":[161]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2022,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
