{"id":"https://openalex.org/W2970004718","doi":"https://doi.org/10.1587/transinf.2018edp7390","title":"Automatic Stop Word Generation for Mining Software Artifact Using Topic Model with Pointwise Mutual Information","display_name":"Automatic Stop Word Generation for Mining Software Artifact Using Topic Model with Pointwise Mutual Information","publication_year":2019,"publication_date":"2019-08-31","ids":{"openalex":"https://openalex.org/W2970004718","doi":"https://doi.org/10.1587/transinf.2018edp7390","mag":"2970004718"},"language":"en","primary_location":{"id":"doi:10.1587/transinf.2018edp7390","is_oa":true,"landing_page_url":"https://doi.org/10.1587/transinf.2018edp7390","pdf_url":"https://www.jstage.jst.go.jp/article/transinf/E102.D/9/E102.D_2018EDP7390/_pdf","source":{"id":"https://openalex.org/S2486202937","display_name":"IEICE Transactions on Information and Systems","issn_l":"0916-8532","issn":["0916-8532","1745-1361"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4320800604","host_organization_name":"Institute of Electronics, Information and Communication Engineers","host_organization_lineage":["https://openalex.org/P4320800604"],"host_organization_lineage_names":["Institute of Electronics, Information and Communication Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEICE Transactions on Information and Systems","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://www.jstage.jst.go.jp/article/transinf/E102.D/9/E102.D_2018EDP7390/_pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5016186529","display_name":"Jung-Been LEE","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jung-Been LEE","raw_affiliation_strings":["Korea University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Korea University","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064167751","display_name":"Taek Lee","orcid":"https://orcid.org/0000-0003-2277-8211"},"institutions":[{"id":"https://openalex.org/I165677929","display_name":"Sungshin Women's University","ror":"https://ror.org/0500xzf72","country_code":"KR","type":"education","lineage":["https://openalex.org/I165677929"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Taek LEE","raw_affiliation_strings":["Sungshin University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sungshin University","institution_ids":["https://openalex.org/I165677929"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5111976379","display_name":"Hoh Peter In","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hoh Peter IN","raw_affiliation_strings":["Korea University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Korea University","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.3444,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":{"value":0.68440673,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":95},"biblio":{"volume":"E102.D","issue":"9","first_page":"1761","last_page":"1772"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10260","display_name":"Software Engineering Research","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/T10260","display_name":"Software Engineering Research","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/T13083","display_name":"Advanced Text Analysis Techniques","score":0.9973999857902527,"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/T12016","display_name":"Web Data Mining and Analysis","score":0.9871000051498413,"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":0.885368824005127},{"id":"https://openalex.org/keywords/artifact","display_name":"Artifact (error)","score":0.7874932885169983},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.6415958404541016},{"id":"https://openalex.org/keywords/topic-model","display_name":"Topic model","score":0.6014975309371948},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.5696592926979065},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4856030344963074},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.46684202551841736},{"id":"https://openalex.org/keywords/pointwise-mutual-information","display_name":"Pointwise mutual information","score":0.4550411105155945},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.41478288173675537},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3728405237197876},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3496062755584717},{"id":"https://openalex.org/keywords/mutual-information","display_name":"Mutual information","score":0.1699410378932953},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.12950116395950317}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.885368824005127},{"id":"https://openalex.org/C2779010991","wikidata":"https://www.wikidata.org/wiki/Q2720909","display_name":"Artifact (error)","level":2,"score":0.7874932885169983},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.6415958404541016},{"id":"https://openalex.org/C171686336","wikidata":"https://www.wikidata.org/wiki/Q3532085","display_name":"Topic model","level":2,"score":0.6014975309371948},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.5696592926979065},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4856030344963074},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.46684202551841736},{"id":"https://openalex.org/C7797323","wikidata":"https://www.wikidata.org/wiki/Q3798612","display_name":"Pointwise mutual information","level":3,"score":0.4550411105155945},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.41478288173675537},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3728405237197876},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3496062755584717},{"id":"https://openalex.org/C152139883","wikidata":"https://www.wikidata.org/wiki/Q252973","display_name":"Mutual information","level":2,"score":0.1699410378932953},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.12950116395950317},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1587/transinf.2018edp7390","is_oa":true,"landing_page_url":"https://doi.org/10.1587/transinf.2018edp7390","pdf_url":"https://www.jstage.jst.go.jp/article/transinf/E102.D/9/E102.D_2018EDP7390/_pdf","source":{"id":"https://openalex.org/S2486202937","display_name":"IEICE Transactions on Information and Systems","issn_l":"0916-8532","issn":["0916-8532","1745-1361"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4320800604","host_organization_name":"Institute of Electronics, Information and Communication Engineers","host_organization_lineage":["https://openalex.org/P4320800604"],"host_organization_lineage_names":["Institute of Electronics, Information and Communication Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEICE Transactions on Information and Systems","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1587/transinf.2018edp7390","is_oa":true,"landing_page_url":"https://doi.org/10.1587/transinf.2018edp7390","pdf_url":"https://www.jstage.jst.go.jp/article/transinf/E102.D/9/E102.D_2018EDP7390/_pdf","source":{"id":"https://openalex.org/S2486202937","display_name":"IEICE Transactions on Information and Systems","issn_l":"0916-8532","issn":["0916-8532","1745-1361"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4320800604","host_organization_name":"Institute of Electronics, Information and Communication Engineers","host_organization_lineage":["https://openalex.org/P4320800604"],"host_organization_lineage_names":["Institute of Electronics, Information and Communication Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEICE Transactions on Information and Systems","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.5}],"awards":[],"funders":[{"id":"https://openalex.org/F4320321373","display_name":"Korea University","ror":"https://ror.org/047dqcg40"},{"id":"https://openalex.org/F4320322617","display_name":"Okawa Foundation for Information and Telecommunications","ror":"https://ror.org/01enbtr31"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2970004718.pdf","grobid_xml":"https://content.openalex.org/works/W2970004718.grobid-xml"},"referenced_works_count":35,"referenced_works":["https://openalex.org/W159693449","https://openalex.org/W1491831284","https://openalex.org/W1608642924","https://openalex.org/W1654173042","https://openalex.org/W1927727507","https://openalex.org/W1974339500","https://openalex.org/W1979991500","https://openalex.org/W1981629032","https://openalex.org/W1984041362","https://openalex.org/W2000518393","https://openalex.org/W2001082470","https://openalex.org/W2006604430","https://openalex.org/W2018663431","https://openalex.org/W2029115643","https://openalex.org/W2042380438","https://openalex.org/W2075006521","https://openalex.org/W2077776641","https://openalex.org/W2079194772","https://openalex.org/W2093605115","https://openalex.org/W2100002341","https://openalex.org/W2109144580","https://openalex.org/W2110307645","https://openalex.org/W2112870206","https://openalex.org/W2133286915","https://openalex.org/W2140124448","https://openalex.org/W2144100511","https://openalex.org/W2147152072","https://openalex.org/W2147946282","https://openalex.org/W2149598089","https://openalex.org/W2156701999","https://openalex.org/W2159426623","https://openalex.org/W2171319841","https://openalex.org/W2344541385","https://openalex.org/W2399980089","https://openalex.org/W4238346259"],"related_works":["https://openalex.org/W52840052","https://openalex.org/W3162837891","https://openalex.org/W1687852313","https://openalex.org/W2270208168","https://openalex.org/W4285244397","https://openalex.org/W190715316","https://openalex.org/W4225003333","https://openalex.org/W3179463712","https://openalex.org/W2625532170","https://openalex.org/W4226087575"],"abstract_inverted_index":{"Mining":[0],"software":[1,13,28,31,47,103,141],"artifacts":[2,32],"is":[3,71,113],"a":[4,37,161,187],"useful":[5],"way":[6,74],"to":[7,23,65,75,87,99,101,115,165],"understand":[8],"the":[9,43,51,77,92,107,110,116,120,150,191],"source":[10],"code":[11],"of":[12,39,53,79,109,140,190],"projects.":[14],"Topic":[15],"modeling":[16,173],"in":[17,119,149,186],"particular":[18],"has":[19],"been":[20],"widely":[21],"used":[22,86,118],"discover":[24],"meaningful":[25],"information":[26],"from":[27,196],"artifacts.":[29,104,142],"However,":[30],"are":[33,85,94],"unstructured":[34],"and":[35,68],"contain":[36],"mix":[38],"textual":[40],"types":[41],"within":[42],"natural":[44,58],"text.":[45],"These":[46],"artifact":[48],"characteristics":[49],"worsen":[50],"performance":[52,108,189],"topic":[54,80,111,138,145,151,172,192],"modeling.":[55],"Among":[56],"several":[57],"language":[59],"pre-processing":[60],"tasks,":[61],"removing":[62],"stop":[63,90,133,167,182],"words":[64,148,159,168,183],"reduce":[66],"meaningless":[67],"uninteresting":[69],"terms":[70],"an":[72,131],"efficient":[73],"improve":[76],"quality":[78],"models.":[81],"Although":[82],"many":[83],"approaches":[84],"generate":[88],"effective":[89],"words,":[91],"lists":[93,195],"outdated":[95],"or":[96],"too":[97],"general":[98],"apply":[100],"mining":[102],"In":[105],"addition,":[106],"model":[112,193],"sensitive":[114],"datasets":[117],"training":[121],"for":[122,137,170],"each":[123],"approach.":[124],"To":[125],"resolve":[126],"these":[127],"problems,":[128],"we":[129,157,178],"propose":[130],"automatic":[132],"word":[134],"generation":[135],"approach":[136],"models":[139],"By":[143],"measuring":[144],"coherence":[146],"among":[147],"using":[152],"Pointwise":[153],"Mutual":[154],"Information":[155],"(PMI),":[156],"added":[158],"with":[160],"low":[162],"PMI":[163],"score":[164],"our":[166,176,181],"list":[169,184],"every":[171],"loop.":[174],"Through":[175],"experiment,":[177],"proved":[179],"that":[180],"results":[185],"higher":[188],"than":[194],"other":[197],"approaches.":[198]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2020,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}