{"id":"https://openalex.org/W4225663894","doi":"https://doi.org/10.1145/3508230.3508247","title":"STIF: Semi-Supervised Taxonomy Induction using Term Embeddings and Clustering","display_name":"STIF: Semi-Supervised Taxonomy Induction using Term Embeddings and Clustering","publication_year":2021,"publication_date":"2021-12-17","ids":{"openalex":"https://openalex.org/W4225663894","doi":"https://doi.org/10.1145/3508230.3508247"},"language":"en","primary_location":{"id":"doi:10.1145/3508230.3508247","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3508230.3508247","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 5th International Conference on Natural Language Processing and Information Retrieval (NLPIR)","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/A5015657656","display_name":"Maryam Mousavi","orcid":"https://orcid.org/0000-0003-2317-3409"},"institutions":[{"id":"https://openalex.org/I55732556","display_name":"Arizona State University","ror":"https://ror.org/03efmqc40","country_code":"US","type":"education","lineage":["https://openalex.org/I55732556"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Maryam Mousavi","raw_affiliation_strings":["School of Computing and Augmented Intelligence, Arizona State University, USA"],"affiliations":[{"raw_affiliation_string":"School of Computing and Augmented Intelligence, Arizona State University, USA","institution_ids":["https://openalex.org/I55732556"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013515031","display_name":"Elena Steiner","orcid":"https://orcid.org/0000-0003-2097-3099"},"institutions":[{"id":"https://openalex.org/I55732556","display_name":"Arizona State University","ror":"https://ror.org/03efmqc40","country_code":"US","type":"education","lineage":["https://openalex.org/I55732556"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Elena Steiner","raw_affiliation_strings":["Hugh Downs School of Human Communication, Arizona State University, USA"],"affiliations":[{"raw_affiliation_string":"Hugh Downs School of Human Communication, Arizona State University, USA","institution_ids":["https://openalex.org/I55732556"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108429764","display_name":"Steven R. Corman","orcid":null},"institutions":[{"id":"https://openalex.org/I55732556","display_name":"Arizona State University","ror":"https://ror.org/03efmqc40","country_code":"US","type":"education","lineage":["https://openalex.org/I55732556"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Steven R.Corman","raw_affiliation_strings":["Hugh Downs School of Human Communication, Arizona State University, USA"],"affiliations":[{"raw_affiliation_string":"Hugh Downs School of Human Communication, Arizona State University, USA","institution_ids":["https://openalex.org/I55732556"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110561148","display_name":"Scott Ruston","orcid":null},"institutions":[{"id":"https://openalex.org/I55732556","display_name":"Arizona State University","ror":"https://ror.org/03efmqc40","country_code":"US","type":"education","lineage":["https://openalex.org/I55732556"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Scott Ruston","raw_affiliation_strings":["Center on Narrative, Disinformation and Strategic Influence, Arizona State University, USA"],"affiliations":[{"raw_affiliation_string":"Center on Narrative, Disinformation and Strategic Influence, Arizona State University, USA","institution_ids":["https://openalex.org/I55732556"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067640833","display_name":"Dylan Weber","orcid":"https://orcid.org/0000-0003-1129-0851"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dylan Weber","raw_affiliation_strings":["Artificial Intelligence Research Lab, Artis Research, USA"],"affiliations":[{"raw_affiliation_string":"Artificial Intelligence Research Lab, Artis Research, USA","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5084781695","display_name":"Hasan Davulcu","orcid":"https://orcid.org/0000-0001-5602-8270"},"institutions":[{"id":"https://openalex.org/I55732556","display_name":"Arizona State University","ror":"https://ror.org/03efmqc40","country_code":"US","type":"education","lineage":["https://openalex.org/I55732556"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hasan Davulcu","raw_affiliation_strings":["School of Computing and Augmented Intelligence, Arizona State University, USA"],"affiliations":[{"raw_affiliation_string":"School of Computing and Augmented Intelligence, Arizona State University, USA","institution_ids":["https://openalex.org/I55732556"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5015657656"],"corresponding_institution_ids":["https://openalex.org/I55732556"],"apc_list":null,"apc_paid":null,"fwci":0.136,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.58297857,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"115","last_page":"123"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9954000115394592,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9954000115394592,"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":0.9940999746322632,"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":0.9921000003814697,"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/cluster-analysis","display_name":"Cluster analysis","score":0.7523485422134399},{"id":"https://openalex.org/keywords/taxonomy","display_name":"Taxonomy (biology)","score":0.6823883652687073},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6632130146026611},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6462574601173401},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6118125915527344},{"id":"https://openalex.org/keywords/noun-phrase","display_name":"Noun phrase","score":0.6025294065475464},{"id":"https://openalex.org/keywords/noun","display_name":"Noun","score":0.5031723380088806},{"id":"https://openalex.org/keywords/codebook","display_name":"Codebook","score":0.502655029296875},{"id":"https://openalex.org/keywords/term","display_name":"Term (time)","score":0.4929683208465576},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.47655776143074036},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3707754611968994}],"concepts":[{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.7523485422134399},{"id":"https://openalex.org/C58642233","wikidata":"https://www.wikidata.org/wiki/Q8269924","display_name":"Taxonomy (biology)","level":2,"score":0.6823883652687073},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6632130146026611},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6462574601173401},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6118125915527344},{"id":"https://openalex.org/C153962237","wikidata":"https://www.wikidata.org/wiki/Q1401131","display_name":"Noun phrase","level":3,"score":0.6025294065475464},{"id":"https://openalex.org/C121934690","wikidata":"https://www.wikidata.org/wiki/Q1084","display_name":"Noun","level":2,"score":0.5031723380088806},{"id":"https://openalex.org/C127759330","wikidata":"https://www.wikidata.org/wiki/Q637416","display_name":"Codebook","level":2,"score":0.502655029296875},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.4929683208465576},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.47655776143074036},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3707754611968994},{"id":"https://openalex.org/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3508230.3508247","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3508230.3508247","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 5th International Conference on Natural Language Processing and Information Retrieval (NLPIR)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":49,"referenced_works":["https://openalex.org/W90362830","https://openalex.org/W655994999","https://openalex.org/W1502957213","https://openalex.org/W1516184288","https://openalex.org/W1966907789","https://openalex.org/W1970972959","https://openalex.org/W1987971958","https://openalex.org/W2016381774","https://openalex.org/W2024932032","https://openalex.org/W2029344051","https://openalex.org/W2033403400","https://openalex.org/W2038880450","https://openalex.org/W2041590596","https://openalex.org/W2081580037","https://openalex.org/W2085487226","https://openalex.org/W2100071287","https://openalex.org/W2103931177","https://openalex.org/W2107598941","https://openalex.org/W2122678284","https://openalex.org/W2138605095","https://openalex.org/W2155734303","https://openalex.org/W2162833336","https://openalex.org/W2164746077","https://openalex.org/W2193209126","https://openalex.org/W2250539671","https://openalex.org/W2336378194","https://openalex.org/W2549809486","https://openalex.org/W2561885448","https://openalex.org/W2595918108","https://openalex.org/W2604724996","https://openalex.org/W2611267947","https://openalex.org/W2733628661","https://openalex.org/W2738669462","https://openalex.org/W2760204057","https://openalex.org/W2777203405","https://openalex.org/W2798904209","https://openalex.org/W2809189384","https://openalex.org/W2883559670","https://openalex.org/W2907607062","https://openalex.org/W2917458986","https://openalex.org/W2930957955","https://openalex.org/W2945967707","https://openalex.org/W2962814626","https://openalex.org/W2997591727","https://openalex.org/W3042401844","https://openalex.org/W3081051539","https://openalex.org/W3104217184","https://openalex.org/W3134455255","https://openalex.org/W3161829609"],"related_works":["https://openalex.org/W2293149949","https://openalex.org/W2026099691","https://openalex.org/W4284672201","https://openalex.org/W2377486419","https://openalex.org/W2943202426","https://openalex.org/W2736714427","https://openalex.org/W2950156284","https://openalex.org/W2163679795","https://openalex.org/W2025590371","https://openalex.org/W2122100102"],"abstract_inverted_index":{"In":[0],"this":[1,150],"paper,":[2],"we":[3],"developed":[4],"a":[5,17,44,62,85,97,117,122],"semi-supervised":[6],"taxonomy":[7,99],"induction":[8],"framework":[9],"using":[10,80,130],"term":[11,67,125],"embedding":[12],"and":[13,37,69,95,127,132],"clustering":[14,70,128],"methods":[15,71,129],"for":[16,149],"blog":[18,26],"corpus":[19],"comprising":[20],"145,000":[21],"posts":[22],"from":[23],"650":[24],"Ukraine-related":[25],"domains":[27],"dated":[28],"between":[29],"2010-2020.":[30],"We":[31,65,120,135],"extracted":[32],"32,429":[33],"noun":[34],"phrases":[35,76,115],"(NPs)":[36],"proceeded":[38,110],"to":[39,61,72,111],"split":[40],"these":[41],"NPs":[42],"into":[43,77,116],"pair":[45],"of":[46,87,107,124],"categories:":[47],"General/Ambiguous":[48],"phrases,":[49,58],"which":[50,59],"might":[51],"appear":[52],"under":[53],"any":[54],"topic":[55],"vs.":[56],"Topical/Non-Ambiguous":[57],"pertain":[60],"topic\u2019s":[63],"specifics.":[64],"used":[66],"representation":[68,126],"partition":[73],"the":[74,81,92,143],"topical/non-ambiguous":[75,114],"90":[78],"groups":[79],"Silhouette":[82],"method.":[83],"Next,":[84],"team":[86],"10":[88],"communications":[89],"scientists":[90],"analyzed":[91],"NP":[93],"clusters":[94],"inducted":[96],"two-level":[98],"alongside":[100],"its":[101],"codebook.":[102],"Upon":[103],"achieving":[104],"intercoder":[105],"reliability":[106],"94%,":[108],"coders":[109],"map":[112],"all":[113],"gold-standard":[118],"taxonomy.":[119],"evaluated":[121],"range":[123],"extrinsic":[131],"intrinsic":[133],"measures.":[134],"determined":[136],"that":[137],"GloVe":[138],"embeddings":[139],"with":[140],"K-Means":[141],"achieved":[142],"highest":[144],"performance":[145],"(i.e.":[146],"74%":[147],"purity)":[148],"real-world":[151],"dataset.":[152]},"counts_by_year":[{"year":2024,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}