{"id":"https://openalex.org/W2522291077","doi":"https://doi.org/10.1145/2961111.2962600","title":"Clustering Mobile Apps Based on Mined Textual Features","display_name":"Clustering Mobile Apps Based on Mined Textual Features","publication_year":2016,"publication_date":"2016-09-08","ids":{"openalex":"https://openalex.org/W2522291077","doi":"https://doi.org/10.1145/2961111.2962600","mag":"2522291077"},"language":"en","primary_location":{"id":"doi:10.1145/2961111.2962600","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2961111.2962600","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 10th ACM/IEEE International Symposium on Empirical Software Engineering and Measurement","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://durham-repository.worktribe.com/output/1142351","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5022748858","display_name":"Afnan Al-Subaihin","orcid":null},"institutions":[{"id":"https://openalex.org/I45129253","display_name":"University College London","ror":"https://ror.org/02jx3x895","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I45129253"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"A. A. Al-Subaihin","raw_affiliation_strings":["CREST, Department of Computer Science, University College London, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CREST, Department of Computer Science, University College London, UK","institution_ids":["https://openalex.org/I45129253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012165852","display_name":"Federica Sarro","orcid":"https://orcid.org/0000-0002-9146-442X"},"institutions":[{"id":"https://openalex.org/I45129253","display_name":"University College London","ror":"https://ror.org/02jx3x895","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I45129253"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"F. Sarro","raw_affiliation_strings":["CREST, Department of Computer Science, University College London, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CREST, Department of Computer Science, University College London, UK","institution_ids":["https://openalex.org/I45129253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042115480","display_name":"Sue Black","orcid":"https://orcid.org/0000-0002-9315-9517"},"institutions":[{"id":"https://openalex.org/I45129253","display_name":"University College London","ror":"https://ror.org/02jx3x895","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I45129253"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"S. Black","raw_affiliation_strings":["CREST, Department of Computer Science, University College London, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CREST, Department of Computer Science, University College London, UK","institution_ids":["https://openalex.org/I45129253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023892723","display_name":"Licia Capra","orcid":"https://orcid.org/0000-0003-1425-3837"},"institutions":[{"id":"https://openalex.org/I45129253","display_name":"University College London","ror":"https://ror.org/02jx3x895","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I45129253"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"L. Capra","raw_affiliation_strings":["CREST, Department of Computer Science, University College London, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CREST, Department of Computer Science, University College London, UK","institution_ids":["https://openalex.org/I45129253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000019783","display_name":"Mark Harman","orcid":"https://orcid.org/0000-0002-5864-4488"},"institutions":[{"id":"https://openalex.org/I45129253","display_name":"University College London","ror":"https://ror.org/02jx3x895","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I45129253"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"M. Harman","raw_affiliation_strings":["CREST, Department of Computer Science, University College London, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CREST, Department of Computer Science, University College London, UK","institution_ids":["https://openalex.org/I45129253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100725719","display_name":"Yantao Jia","orcid":"https://orcid.org/0000-0003-0349-7617"},"institutions":[{"id":"https://openalex.org/I45129253","display_name":"University College London","ror":"https://ror.org/02jx3x895","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I45129253"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Y. Jia","raw_affiliation_strings":["CREST, Department of Computer Science, University College London, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CREST, Department of Computer Science, University College London, UK","institution_ids":["https://openalex.org/I45129253"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100412295","display_name":"Yujie Zhang","orcid":"https://orcid.org/0009-0009-9305-2718"},"institutions":[{"id":"https://openalex.org/I45129253","display_name":"University College London","ror":"https://ror.org/02jx3x895","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I45129253"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Y. Zhang","raw_affiliation_strings":["CREST, Department of Computer Science, University College London, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CREST, Department of Computer Science, University College London, UK","institution_ids":["https://openalex.org/I45129253"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I45129253"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":83,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"10"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9977999925613403,"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/T12016","display_name":"Web Data Mining and Analysis","score":0.9977999925613403,"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/T10260","display_name":"Software Engineering Research","score":0.9794999957084656,"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/T11241","display_name":"Advanced Malware Detection Techniques","score":0.9728999733924866,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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":0.7861002087593079},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7860302925109863},{"id":"https://openalex.org/keywords/granularity","display_name":"Granularity","score":0.5931131839752197},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5334731936454773},{"id":"https://openalex.org/keywords/hierarchical-clustering","display_name":"Hierarchical clustering","score":0.5292572379112244},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.5220070481300354},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5141199231147766},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.48638108372688293},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.46139049530029297},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.41932979226112366},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3366037905216217},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.32479482889175415}],"concepts":[{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.7861002087593079},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7860302925109863},{"id":"https://openalex.org/C177774035","wikidata":"https://www.wikidata.org/wiki/Q1246948","display_name":"Granularity","level":2,"score":0.5931131839752197},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5334731936454773},{"id":"https://openalex.org/C92835128","wikidata":"https://www.wikidata.org/wiki/Q1277447","display_name":"Hierarchical clustering","level":3,"score":0.5292572379112244},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5220070481300354},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5141199231147766},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.48638108372688293},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.46139049530029297},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.41932979226112366},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3366037905216217},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.32479482889175415},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","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/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/2961111.2962600","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2961111.2962600","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 10th ACM/IEEE International Symposium on Empirical Software Engineering and Measurement","raw_type":"proceedings-article"},{"id":"pmh:oai:durham-repository.worktribe.com:1142351","is_oa":true,"landing_page_url":"https://durham-repository.worktribe.com/output/1142351","pdf_url":null,"source":{"id":"https://openalex.org/S4306400188","display_name":"Durham Research Online (Durham University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I190082696","host_organization_name":"Durham University","host_organization_lineage":["https://openalex.org/I190082696"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Presentation / Conference Contribution"},{"id":"pmh:oai:eprints.ucl.ac.uk.OAI2:1538221","is_oa":false,"landing_page_url":"https://discovery.ucl.ac.uk/id/eprint/1538221/","pdf_url":null,"source":{"id":"https://openalex.org/S4306400024","display_name":"UCL Discovery (University College London)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I45129253","host_organization_name":"University College London","host_organization_lineage":["https://openalex.org/I45129253"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"In: ESEM '16 Proceedings of the 10th ACM/IEEE International Symposium on Empirical Software Engineering and Measurement. ACM (Association for Computing Machinery) (2016)","raw_type":"Proceedings paper"}],"best_oa_location":{"id":"pmh:oai:durham-repository.worktribe.com:1142351","is_oa":true,"landing_page_url":"https://durham-repository.worktribe.com/output/1142351","pdf_url":null,"source":{"id":"https://openalex.org/S4306400188","display_name":"Durham Research Online (Durham University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I190082696","host_organization_name":"Durham University","host_organization_lineage":["https://openalex.org/I190082696"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Presentation / Conference Contribution"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G6794522244","display_name":null,"funder_award_id":"EP/J017515/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"}],"funders":[{"id":"https://openalex.org/F4320334627","display_name":"Engineering and Physical Sciences Research Council","ror":"https://ror.org/0439y7842"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":51,"referenced_works":["https://openalex.org/W64019278","https://openalex.org/W70230128","https://openalex.org/W79696261","https://openalex.org/W601550353","https://openalex.org/W640156484","https://openalex.org/W1449208847","https://openalex.org/W1516600607","https://openalex.org/W1530266187","https://openalex.org/W1790954942","https://openalex.org/W1963314207","https://openalex.org/W1964963535","https://openalex.org/W1969738752","https://openalex.org/W1975879668","https://openalex.org/W1979100395","https://openalex.org/W1987971958","https://openalex.org/W1993344876","https://openalex.org/W1998871699","https://openalex.org/W2011781116","https://openalex.org/W2016381774","https://openalex.org/W2020438140","https://openalex.org/W2037789405","https://openalex.org/W2040810008","https://openalex.org/W2041575831","https://openalex.org/W2044428238","https://openalex.org/W2049017883","https://openalex.org/W2068731595","https://openalex.org/W2074975950","https://openalex.org/W2075395364","https://openalex.org/W2075876574","https://openalex.org/W2078483536","https://openalex.org/W2081580037","https://openalex.org/W2116907335","https://openalex.org/W2126129257","https://openalex.org/W2136148671","https://openalex.org/W2138968539","https://openalex.org/W2162181963","https://openalex.org/W2165401136","https://openalex.org/W2165612380","https://openalex.org/W2168649891","https://openalex.org/W2170982140","https://openalex.org/W2248438390","https://openalex.org/W2470924201","https://openalex.org/W2493732476","https://openalex.org/W2546780486","https://openalex.org/W2559490865","https://openalex.org/W2744136779","https://openalex.org/W3123920865","https://openalex.org/W4285719527","https://openalex.org/W4299301436","https://openalex.org/W6620748881","https://openalex.org/W6630849909"],"related_works":["https://openalex.org/W2931688134","https://openalex.org/W2377919138","https://openalex.org/W2378857091","https://openalex.org/W4256502920","https://openalex.org/W103652678","https://openalex.org/W4226090359","https://openalex.org/W2999756192","https://openalex.org/W1081706099","https://openalex.org/W2370730867","https://openalex.org/W3200375535"],"abstract_inverted_index":{"Context:":[0],"Categorising":[1],"software":[2],"systems":[3],"according":[4],"to":[5,11,19,58,66,110,118],"their":[6],"functionality":[7],"yields":[8],"many":[9],"benefits":[10],"both":[12,106],"users":[13],"and":[14,54,86,114,135,145,197],"developers.":[15],"Goal:":[16],"In":[17],"order":[18],"uncover":[20],"the":[21,68,84,101,141,146,166,180],"latent":[22],"clustering":[23,200],"of":[24,143,179],"mobile":[25],"apps":[26,69,81,144],"in":[27,90,165,177],"app":[28,37,88,167],"stores,":[29],"we":[30],"propose":[31],"a":[32,126,173,185,192,198],"novel":[33],"technique":[34,196],"that":[35,96,153],"measures":[36],"similarity":[38],"based":[39],"on":[40,79,112,120],"claimed":[41,181],"behaviour.":[42],"Method:":[43],"Features":[44],"are":[45,63],"extracted":[46],"using":[47,70,191],"information":[48],"retrieval":[49],"augmented":[50],"with":[51,157],"ontological":[52],"analysis":[53],"used":[55,65],"as":[56,160],"attributes":[57,62],"characterise":[59],"apps.":[60],"These":[61],"then":[64],"cluster":[67],"agglomerative":[71],"hierarchical":[72],"clustering.":[73],"We":[74,123],"empirically":[75],"evaluate":[76],"our":[77,97],"approach":[78,98],"17,877":[80],"mined":[82],"from":[83],"BlackBerry":[85],"Google":[87,115,134],"stores":[89,168],"2014.":[91],"Results:":[92],"The":[93],"results":[94],"show":[95],"dramatically":[99],"improves":[100],"existing":[102],"categorisation":[103,164],"quality":[104,176,187],"for":[105,133,138],"Blackberry":[107],"(from":[108,116],"0.02":[109],"0.41":[111],"average)":[113,121],"0.03":[117],"0.21":[119],"stores.":[122],"also":[124],"find":[125],"strong":[127],"Spearman":[128],"rank":[129],"correlation":[130],"(\u03c1=":[131],"0.96":[132],"\u03c1=":[136],"0.99":[137],"BlackBerry)":[139],"between":[140],"number":[142],"ideal":[147,154],"granularity":[148,155],"within":[149],"each":[150],"category,":[151],"indicating":[152],"increases":[156],"category":[158],"size,":[159],"expected.":[161],"Conclusions:":[162],"Current":[163],"studied":[169],"do":[170],"not":[171],"exhibit":[172],"good":[174,193],"classification":[175],"terms":[178],"feature":[182,194],"space.":[183],"However,":[184],"better":[186],"can":[188],"be":[189],"achieved":[190],"extraction":[195],"traditional":[199],"method.":[201]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":7},{"year":2023,"cited_by_count":8},{"year":2022,"cited_by_count":16},{"year":2021,"cited_by_count":12},{"year":2020,"cited_by_count":13},{"year":2019,"cited_by_count":8},{"year":2018,"cited_by_count":6},{"year":2017,"cited_by_count":5},{"year":2016,"cited_by_count":5}],"updated_date":"2026-07-19T07:52:34.831488","created_date":"2025-10-10T00:00:00"}