{"id":"https://openalex.org/W2473326264","doi":null,"title":"Automated Identification of Computer Science Research Papers","display_name":"Automated Identification of Computer Science Research Papers","publication_year":2016,"publication_date":"2016-01-01","ids":{"openalex":"https://openalex.org/W2473326264","mag":"2473326264"},"language":"en","primary_location":{"id":"pmh:oai:scholar.uwindsor.ca:etd-6776","doi":null,"is_oa":true,"landing_page_url":"https://scholar.uwindsor.ca/etd/5776","pdf_url":"https://scholar.uwindsor.ca/etd/5776","source":{"id":"https://openalex.org/S4306400430","display_name":"Scholarship at UWindsor (University of Windsor)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I74413500","host_organization_name":"University of Windsor","host_organization_lineage":["https://openalex.org/I74413500"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Electronic Theses and Dissertations","raw_type":"info:eu-repo/semantics/masterThesis"},"volume":null,"type":"dissertation","is_traditional":true,"indexed_in":[],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://scholar.uwindsor.ca/etd/5776","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5054170650","display_name":"Tong Zhou","orcid":"https://orcid.org/0000-0002-0159-7414","observed_orcids":["https://orcid.org/0000-0002-0159-7414"]},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Tong Zhou","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0002-0159-7414","affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":["https://openalex.org/A5054170650"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":6,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11550","display_name":"Text and Document Classification Technologies","score":0.9984999895095825,"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/T11550","display_name":"Text and Document Classification Technologies","score":0.9984999895095825,"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/T13083","display_name":"Advanced Text Analysis Techniques","score":0.00019999999494757503,"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/T13910","display_name":"Computational and Text Analysis Methods","score":9.999999747378752e-05,"subfield":{"id":"https://openalex.org/subfields/3300","display_name":"General Social Sciences"},"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/text-classification","display_name":"text classification","score":0.7379999756813049},{"id":"https://openalex.org/keywords/citeseerx","display_name":"CiteSeerX","score":0.9290000200271606},{"id":"https://openalex.org/keywords/arxiv","display_name":"arXiv","score":0.9919999837875366},{"id":"https://openalex.org/keywords/feature-weighting","display_name":"feature weighting","score":0.8790000081062317},{"id":"https://openalex.org/keywords/feature-selection","display_name":"feature selection","score":0.8600000143051147},{"id":"https://openalex.org/keywords/naive-bayes","display_name":"naive Bayes","score":0.8899999856948853},{"id":"https://openalex.org/keywords/logistic-regression","display_name":"logistic regression","score":0.9779999852180481},{"id":"https://openalex.org/keywords/scholarly-data","display_name":"scholarly data","score":0.4699999988079071}],"concepts":[{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.6332831382751465},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5517428517341614},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.45270228385925293},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"pmh:oai:scholar.uwindsor.ca:etd-6776","doi":null,"is_oa":true,"landing_page_url":"https://scholar.uwindsor.ca/etd/5776","pdf_url":"https://scholar.uwindsor.ca/etd/5776","source":{"id":"https://openalex.org/S4306400430","display_name":"Scholarship at UWindsor (University of Windsor)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I74413500","host_organization_name":"University of Windsor","host_organization_lineage":["https://openalex.org/I74413500"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Electronic Theses and Dissertations","raw_type":"info:eu-repo/semantics/masterThesis"},{"id":"pmh:oai:uwindsor.scholaris.ca:20.500.14776/6123","doi":null,"is_oa":true,"landing_page_url":"https://hdl.handle.net/20.500.14776/6123","pdf_url":null,"source":{"id":"https://openalex.org/S4306400430","display_name":"Scholarship at UWindsor (University of Windsor)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I74413500","host_organization_name":"University of Windsor","host_organization_lineage":["https://openalex.org/I74413500"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/masterThesis"},{"id":"mag:2473326264","doi":null,"is_oa":false,"landing_page_url":"https://scholar.uwindsor.ca/cgi/viewcontent.cgi?article=6776&context=etd","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":null}],"best_oa_location":{"id":"pmh:oai:scholar.uwindsor.ca:etd-6776","doi":null,"is_oa":true,"landing_page_url":"https://scholar.uwindsor.ca/etd/5776","pdf_url":"https://scholar.uwindsor.ca/etd/5776","source":{"id":"https://openalex.org/S4306400430","display_name":"Scholarship at UWindsor (University of Windsor)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I74413500","host_organization_name":"University of Windsor","host_organization_lineage":["https://openalex.org/I74413500"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Electronic Theses and Dissertations","raw_type":"info:eu-repo/semantics/masterThesis"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2473326264.pdf","grobid_xml":"https://content.openalex.org/works/W2473326264.grobid-xml"},"referenced_works_count":9,"referenced_works":["https://openalex.org/W126139559","https://openalex.org/W1614298861","https://openalex.org/W1986913017","https://openalex.org/W2005422315","https://openalex.org/W2022322548","https://openalex.org/W2131744502","https://openalex.org/W2263270445","https://openalex.org/W2295508865","https://openalex.org/W3124024751"],"related_works":["https://openalex.org/W7077170774","https://openalex.org/W3126235946","https://openalex.org/W151511080","https://openalex.org/W3102049424","https://openalex.org/W4323341688","https://openalex.org/W2275801136","https://openalex.org/W4296960828","https://openalex.org/W2981819923","https://openalex.org/W7218138305","https://openalex.org/W2969153652"],"abstract_inverted_index":{"The":[0],"fast":[1],"growing":[2],"speed":[3],"of":[4,7,103,149],"the":[5,25,50,113,117],"size":[6,102],"scholarly":[8],"data":[9,63,119,126,157],"have":[10],"made":[11],"it":[12],"necessary":[13],"to":[14,22,30,133],"nd":[15,48],"out":[16,49],"e":[17],"cient":[18],"machine":[19],"learning":[20],"ways":[21],"automatically":[23,37],"categorize":[24,38],"data.":[26],"This":[27],"thesis":[28],"aims":[29],"build":[31],"a":[32],"classi":[33,73,130],"er":[34],"that":[35,99,124],"can":[36,128],"Computer":[39],"Science":[40],"(CS)":[41],"papers":[42],"based":[43],"on":[44],"text":[45],"content.":[46],"To":[47],"best":[51,114],"method":[52],"for":[53,115],"CS":[54],"papers,":[55],"we":[56],"collect":[57],"and":[58,66,68,79,91],"prepare":[59],"two":[60,118],"large":[61,101],"labeled":[62],"sets:":[64],"CiteSeerX":[65,138,150],"arXiv,":[67],"experiment":[69],"with":[70,100,108],"di":[71,82,87,92],"erent":[72,83,88,93],"cation":[74],"approaches":[75],"including":[76],"Naive":[77],"Bayes":[78],"Logistic":[80],"Regression,":[81],"feature":[84,94,110],"selection":[85],"schemes,":[86],"language":[89],"models,":[90],"weighting":[95],"schemes.":[96],"We":[97],"found":[98],"training":[104],"set,":[105],"Bi-gram":[106],"modeling":[107],"normalized":[109],"weight":[111],"performs":[112],"all":[116],"sets.":[120],"It":[121],"is":[122,144,151],"surprising":[123],"arXiv":[125,156],"set":[127],"be":[129],"ed":[131],"up":[132],"0.95":[134],"F1":[135,141],"value,":[136],"while":[137],"reaches":[139],"lower":[140],"(0.764).":[142],"That":[143],"probably":[145],"caused":[146],"by":[147],"labeling":[148],"not":[152],"as":[153,155],"accurate":[154],"set.":[158]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2021,"cited_by_count":2},{"year":2017,"cited_by_count":1}],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2016-07-22T00:00:00"}