{"id":"https://openalex.org/W2757203079","doi":"https://doi.org/10.1145/3148011.3148039","title":"Using Titles vs. Full-text as Source for Automated Semantic Document Annotation","display_name":"Using Titles vs. Full-text as Source for Automated Semantic Document Annotation","publication_year":2017,"publication_date":"2017-12-04","ids":{"openalex":"https://openalex.org/W2757203079","doi":"https://doi.org/10.1145/3148011.3148039","mag":"2757203079"},"language":"en","primary_location":{"id":"doi:10.1145/3148011.3148039","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3148011.3148039","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Knowledge Capture Conference","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/A5077989893","display_name":"Lukas Galke","orcid":"https://orcid.org/0000-0001-6124-1092"},"institutions":[{"id":"https://openalex.org/I2800024560","display_name":"ZBW \u2013 Leibniz-Informationszentrum Wirtschaft","ror":"https://ror.org/03a96gc12","country_code":"DE","type":"facility","lineage":["https://openalex.org/I2800024560","https://openalex.org/I315704651"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Lukas Galke","raw_affiliation_strings":["ZBW-Leibniz Information Centre for Economics, Kiel"],"affiliations":[{"raw_affiliation_string":"ZBW-Leibniz Information Centre for Economics, Kiel","institution_ids":["https://openalex.org/I2800024560"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102917205","display_name":"Florian Mai","orcid":"https://orcid.org/0000-0003-1370-9740"},"institutions":[{"id":"https://openalex.org/I32021983","display_name":"Kiel University","ror":"https://ror.org/04v76ef78","country_code":"DE","type":"education","lineage":["https://openalex.org/I32021983"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Florian Mai","raw_affiliation_strings":["Kiel University"],"affiliations":[{"raw_affiliation_string":"Kiel University","institution_ids":["https://openalex.org/I32021983"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011701078","display_name":"Alan Schelten","orcid":null},"institutions":[{"id":"https://openalex.org/I32021983","display_name":"Kiel University","ror":"https://ror.org/04v76ef78","country_code":"DE","type":"education","lineage":["https://openalex.org/I32021983"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Alan Schelten","raw_affiliation_strings":["Kiel University"],"affiliations":[{"raw_affiliation_string":"Kiel University","institution_ids":["https://openalex.org/I32021983"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034088391","display_name":"Dennis Brunsch","orcid":null},"institutions":[{"id":"https://openalex.org/I32021983","display_name":"Kiel University","ror":"https://ror.org/04v76ef78","country_code":"DE","type":"education","lineage":["https://openalex.org/I32021983"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Dennis Brunsch","raw_affiliation_strings":["Kiel University"],"affiliations":[{"raw_affiliation_string":"Kiel University","institution_ids":["https://openalex.org/I32021983"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5005533034","display_name":"Ansgar Scherp","orcid":"https://orcid.org/0000-0002-2653-9245"},"institutions":[{"id":"https://openalex.org/I2800024560","display_name":"ZBW \u2013 Leibniz-Informationszentrum Wirtschaft","ror":"https://ror.org/03a96gc12","country_code":"DE","type":"facility","lineage":["https://openalex.org/I2800024560","https://openalex.org/I315704651"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Ansgar Scherp","raw_affiliation_strings":["ZBW-Leibniz Information Centre for Economics, Kiel"],"affiliations":[{"raw_affiliation_string":"ZBW-Leibniz Information Centre for Economics, Kiel","institution_ids":["https://openalex.org/I2800024560"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5077989893"],"corresponding_institution_ids":["https://openalex.org/I2800024560"],"apc_list":null,"apc_paid":null,"fwci":1.6629,"has_fulltext":false,"cited_by_count":16,"citation_normalized_percentile":{"value":0.88311712,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"4"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11550","display_name":"Text and Document Classification Technologies","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9984999895095825,"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/T10028","display_name":"Topic Modeling","score":0.9965000152587891,"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":0.8394704461097717},{"id":"https://openalex.org/keywords/annotation","display_name":"Annotation","score":0.7027530074119568},{"id":"https://openalex.org/keywords/naive-bayes-classifier","display_name":"Naive Bayes classifier","score":0.6294209957122803},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5913473963737488},{"id":"https://openalex.org/keywords/metadata","display_name":"Metadata","score":0.5825443863868713},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5574561953544617},{"id":"https://openalex.org/keywords/rank","display_name":"Rank (graph theory)","score":0.525757372379303},{"id":"https://openalex.org/keywords/support-vector-machine","display_name":"Support vector machine","score":0.5153738856315613},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.43458572030067444},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.1969815492630005}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8394704461097717},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.7027530074119568},{"id":"https://openalex.org/C52001869","wikidata":"https://www.wikidata.org/wiki/Q812530","display_name":"Naive Bayes classifier","level":3,"score":0.6294209957122803},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5913473963737488},{"id":"https://openalex.org/C93518851","wikidata":"https://www.wikidata.org/wiki/Q180160","display_name":"Metadata","level":2,"score":0.5825443863868713},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5574561953544617},{"id":"https://openalex.org/C164226766","wikidata":"https://www.wikidata.org/wiki/Q7293202","display_name":"Rank (graph theory)","level":2,"score":0.525757372379303},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.5153738856315613},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.43458572030067444},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.1969815492630005},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/3148011.3148039","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3148011.3148039","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Knowledge Capture Conference","raw_type":"proceedings-article"},{"id":"pmh:oai:pub.zbw.eu:11108/346","is_oa":false,"landing_page_url":"http://hdl.handle.net/11108/346","pdf_url":null,"source":{"id":"https://openalex.org/S4306402552","display_name":"ZBW Publication Archive (ZBW \u2013 Leibniz Information Centre for Economics)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I2800024560","host_organization_name":"ZBW \u2013 Leibniz-Informationszentrum Wirtschaft","host_organization_lineage":["https://openalex.org/I2800024560"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"","raw_type":"doc-type:conferenceObject"},{"id":"pmh:oai:dspace.stir.ac.uk:1893/28018","is_oa":false,"landing_page_url":"http://dspace.stir.ac.uk/bitstream/1893/28018/1/Galke%20et%20al%202017.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306400268","display_name":"Stirling Online Research Repository (University of Stirling)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I12093191","host_organization_name":"University of Stirling","host_organization_lineage":["https://openalex.org/I12093191"],"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":[],"awards":[{"id":"https://openalex.org/G3143778357","display_name":null,"funder_award_id":"693092","funder_id":"https://openalex.org/F4320332999","funder_display_name":"Horizon 2020 Framework Programme"}],"funders":[{"id":"https://openalex.org/F4320332999","display_name":"Horizon 2020 Framework Programme","ror":"https://ror.org/00k4n6c32"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W1511053376","https://openalex.org/W1576514601","https://openalex.org/W1863422369","https://openalex.org/W2046352419","https://openalex.org/W2052684427","https://openalex.org/W2068903979","https://openalex.org/W2091825929","https://openalex.org/W2114315281","https://openalex.org/W2150102617","https://openalex.org/W2152143870","https://openalex.org/W2757203079","https://openalex.org/W2951829787"],"related_works":["https://openalex.org/W2058118494","https://openalex.org/W2392768766","https://openalex.org/W2361861616","https://openalex.org/W2382021449","https://openalex.org/W2095118173","https://openalex.org/W2263699433","https://openalex.org/W2106424170","https://openalex.org/W2377979023","https://openalex.org/W1985426483","https://openalex.org/W2501188010"],"abstract_inverted_index":{"We":[0],"conduct":[1],"the":[2,13,18,25,47,62,65,74,78,82],"first":[3],"systematic":[4],"comparison":[5],"of":[6,21,38,58,64,73],"automated":[7],"semantic":[8],"annotation":[9],"based":[10],"on":[11,17],"either":[12],"full-text":[14],"or":[15],"only":[16,68],"title":[19],"metadata":[20],"documents.":[22],"Apart":[23],"from":[24],"prominent":[26],"text":[27],"classification":[28],"baselines":[29],"kNN":[30],"and":[31,42,45,53],"SVM,":[32],"we":[33],"also":[34],"compare":[35],"recent":[36],"techniques":[37],"Learning":[39],"to":[40,77],"Rank":[41],"neural":[43],"networks":[44],"revisit":[46],"traditional":[48],"methods":[49],"logistic":[50],"regression,":[51],"Rocchio,":[52],"Naive":[54],"Bayes.":[55],"Across":[56],"three":[57],"our":[59],"four":[60],"datasets,":[61],"performance":[63,79],"classifications":[66],"using":[67,81],"titles":[69],"reaches":[70],"over":[71],"90%":[72],"quality":[75],"compared":[76],"when":[80],"full-text.":[83]},"counts_by_year":[{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":5},{"year":2017,"cited_by_count":1}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}
