{"id":"https://openalex.org/W2090645789","doi":"https://doi.org/10.1145/1871437.1871588","title":"Building re-usable dictionary repositories for real-world text mining","display_name":"Building re-usable dictionary repositories for real-world text mining","publication_year":2010,"publication_date":"2010-10-26","ids":{"openalex":"https://openalex.org/W2090645789","doi":"https://doi.org/10.1145/1871437.1871588","mag":"2090645789"},"language":"en","primary_location":{"id":"doi:10.1145/1871437.1871588","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1871437.1871588","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 19th ACM international conference on Information and knowledge management","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/A5033214720","display_name":"Shantanu Godbole","orcid":"https://orcid.org/0009-0001-7071-9438"},"institutions":[{"id":"https://openalex.org/I4210103279","display_name":"IBM Research - India","ror":"https://ror.org/014wt7r80","country_code":"IN","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210103279","https://openalex.org/I4210114115"]}],"countries":["IN"],"is_corresponding":true,"raw_author_name":"Shantanu Godbole","raw_affiliation_strings":["IBM Research - India, New Delhi, India"],"affiliations":[{"raw_affiliation_string":"IBM Research - India, New Delhi, India","institution_ids":["https://openalex.org/I4210103279"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111463007","display_name":"Indrajit Bhattacharya","orcid":null},"institutions":[{"id":"https://openalex.org/I59270414","display_name":"Indian Institute of Science Bangalore","ror":"https://ror.org/04dese585","country_code":"IN","type":"education","lineage":["https://openalex.org/I59270414"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Indrajit Bhattacharya","raw_affiliation_strings":["Indian Institute of Science, Bangalore, India"],"affiliations":[{"raw_affiliation_string":"Indian Institute of Science, Bangalore, India","institution_ids":["https://openalex.org/I59270414"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028134056","display_name":"Ajay Gupta","orcid":"https://orcid.org/0000-0001-7881-4010"},"institutions":[{"id":"https://openalex.org/I4210103279","display_name":"IBM Research - India","ror":"https://ror.org/014wt7r80","country_code":"IN","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210103279","https://openalex.org/I4210114115"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Ajay Gupta","raw_affiliation_strings":["IBM Research - India, New Delhi, India"],"affiliations":[{"raw_affiliation_string":"IBM Research - India, New Delhi, India","institution_ids":["https://openalex.org/I4210103279"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101423308","display_name":"Ashish Verma","orcid":"https://orcid.org/0009-0007-3427-3196"},"institutions":[{"id":"https://openalex.org/I4210103279","display_name":"IBM Research - India","ror":"https://ror.org/014wt7r80","country_code":"IN","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210103279","https://openalex.org/I4210114115"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Ashish Verma","raw_affiliation_strings":["IBM Research - India, New Delhi, India"],"affiliations":[{"raw_affiliation_string":"IBM Research - India, New Delhi, India","institution_ids":["https://openalex.org/I4210103279"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5033214720"],"corresponding_institution_ids":["https://openalex.org/I4210103279"],"apc_list":null,"apc_paid":null,"fwci":4.1894,"has_fulltext":false,"cited_by_count":48,"citation_normalized_percentile":{"value":0.94102446,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1189","last_page":"1198"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9987000226974487,"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":0.9987000226974487,"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/T10215","display_name":"Semantic Web and Ontologies","score":0.9983999729156494,"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":0.9973999857902527,"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/usable","display_name":"USable","score":0.840559720993042},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7644311189651489},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.45284852385520935},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.38009113073349},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.3508565425872803},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3496253490447998}],"concepts":[{"id":"https://openalex.org/C2780615836","wikidata":"https://www.wikidata.org/wiki/Q2471869","display_name":"USable","level":2,"score":0.840559720993042},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7644311189651489},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.45284852385520935},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.38009113073349},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.3508565425872803},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3496253490447998}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/1871437.1871588","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1871437.1871588","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 19th ACM international conference on Information and knowledge management","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.423.2281","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.423.2281","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.godbole.net/shantanu/pubs/dictrepo-cikm10.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Industry, innovation and infrastructure","id":"https://metadata.un.org/sdg/9","score":0.5}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W14854443","https://openalex.org/W99485931","https://openalex.org/W197270748","https://openalex.org/W2050712820","https://openalex.org/W2056718876","https://openalex.org/W2060834142","https://openalex.org/W2068599126","https://openalex.org/W2099971677","https://openalex.org/W2115191221","https://openalex.org/W2122075670","https://openalex.org/W2134525017","https://openalex.org/W2163302275","https://openalex.org/W2166776180","https://openalex.org/W2169075700","https://openalex.org/W2612120747","https://openalex.org/W4255198209"],"related_works":["https://openalex.org/W2748952813","https://openalex.org/W2982321410","https://openalex.org/W95465806","https://openalex.org/W2392004567","https://openalex.org/W2046296964","https://openalex.org/W2940029036","https://openalex.org/W4388292429","https://openalex.org/W2756595502","https://openalex.org/W2010789764","https://openalex.org/W2187233292"],"abstract_inverted_index":{"Text":[0],"mining,":[1],"though":[2],"still":[3],"a":[4,36,60,72,120,137],"nascent":[5],"industry,":[6],"has":[7,34],"been":[8,35],"growing":[9,73],"quickly":[10,146],"along":[11],"with":[12],"the":[13,16,40,63,107,143],"awareness":[14],"of":[15,18,42,67,109,116,128,139,170],"importance":[17],"unstructured":[19],"data":[20],"in":[21,39,93,96,174],"business":[22],"analytics,":[23],"customer":[24],"retention":[25],"and":[26,30,47,65,90,98,105,118,126,165,172,180,191,198],"extension,":[27],"social":[28],"media,":[29],"legal":[31],"applications.":[32],"There":[33],"recent":[37],"increase":[38],"number":[41],"commercial":[43],"text":[44,79,88,101,202],"mining":[45,89],"product":[46],"service":[48],"offerings,":[49],"but":[50],"successful":[51],"or":[52,160],"wide-spread":[53],"deployments":[54],"are":[55],"rare,":[56],"mainly":[57],"due":[58],"to":[59,142,145,157],"dependence":[61],"on":[62,86,183],"expertise":[64],"skill":[66],"practitioners.":[68],"Accordingly,":[69],"there":[70],"is":[71],"need":[74],"for":[75,78,113,122,200],"re-usable":[76],"repositories":[77,190],"mining.":[80,203],"In":[81],"this":[82],"paper,":[83],"we":[84],"focus":[85],"dictionary-based":[87,201],"its":[91],"role":[92],"enabling":[94,168],"practitioners":[95],"understanding":[97],"analyzing":[99],"large":[100,151],"datasets.":[102,132,152],"We":[103,153,177],"motivate":[104],"define":[106],"problem":[108],"exploratory":[110],"dictionary":[111],"construction":[112,134],"capturing":[114],"concepts":[115],"interest,":[117],"propose":[119],"framework":[121,135],"efficient":[123],"construction,":[124],"tuning,":[125],"re-use":[127],"these":[129],"dictionaries":[130,149,162],"across":[131,163],"The":[133],"offers":[136],"range":[138],"interaction":[140],"modes":[141],"user":[144],"build":[147],"concept":[148],"over":[150],"also":[154],"show":[155],"how":[156],"adapt":[158],"one":[159],"more":[161],"domains":[164],"tasks,":[166],"thereby":[167],"reuse":[169],"knowledge":[171],"effort":[173,199],"industrial":[175],"practice.":[176],"present":[178],"results":[179],"case":[181],"studies":[182],"real-life":[184],"CRM":[185],"analytics":[186],"datasets,":[187],"where":[188],"such":[189],"tooling":[192],"significantly":[193],"cut":[194],"down":[195],"practitioner":[196],"time":[197]},"counts_by_year":[{"year":2022,"cited_by_count":6},{"year":2021,"cited_by_count":5},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":4},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":3},{"year":2015,"cited_by_count":7},{"year":2014,"cited_by_count":8},{"year":2013,"cited_by_count":6},{"year":2012,"cited_by_count":3}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}