{"id":"https://openalex.org/W2169004485","doi":"https://doi.org/10.1145/1390749.1390763","title":"Opinion mining from noisy text data","display_name":"Opinion mining from noisy text data","publication_year":2008,"publication_date":"2008-07-24","ids":{"openalex":"https://openalex.org/W2169004485","doi":"https://doi.org/10.1145/1390749.1390763","mag":"2169004485"},"language":"en","primary_location":{"id":"doi:10.1145/1390749.1390763","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1390749.1390763","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the second workshop on Analytics for noisy unstructured text data","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/A5102724695","display_name":"Lipika Dey","orcid":"https://orcid.org/0000-0003-3831-5545"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Lipika Dey","raw_affiliation_strings":["TCS Innovation Lab Delhi, Udyog Vihar, Gurgaon, India"],"affiliations":[{"raw_affiliation_string":"TCS Innovation Lab Delhi, Udyog Vihar, Gurgaon, India","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5009858204","display_name":"Shamsul Haque","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"S K Mirajul Haque","raw_affiliation_strings":["TCS Innovation Lab Delhi, Udyog Vihar, Gurgaon, India"],"affiliations":[{"raw_affiliation_string":"TCS Innovation Lab Delhi, Udyog Vihar, Gurgaon, India","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5102724695"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":9.7249,"has_fulltext":false,"cited_by_count":103,"citation_normalized_percentile":{"value":0.97918738,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"83","last_page":"90"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10664","display_name":"Sentiment Analysis and Opinion Mining","score":0.9998000264167786,"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/T10664","display_name":"Sentiment Analysis and Opinion Mining","score":0.9998000264167786,"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":0.9980000257492065,"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/T11644","display_name":"Spam and Phishing Detection","score":0.9853000044822693,"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":0.7938103675842285},{"id":"https://openalex.org/keywords/punctuation","display_name":"Punctuation","score":0.6142046451568604},{"id":"https://openalex.org/keywords/sentiment-analysis","display_name":"Sentiment analysis","score":0.6133401393890381},{"id":"https://openalex.org/keywords/the-internet","display_name":"The Internet","score":0.48671796917915344},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4750226140022278},{"id":"https://openalex.org/keywords/information-extraction","display_name":"Information extraction","score":0.46532317996025085},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4599963128566742},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4577750861644745},{"id":"https://openalex.org/keywords/bottleneck","display_name":"Bottleneck","score":0.44922178983688354},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.4205242991447449},{"id":"https://openalex.org/keywords/plain-text","display_name":"Plain text","score":0.4146419167518616},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.3432673513889313}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7938103675842285},{"id":"https://openalex.org/C540372491","wikidata":"https://www.wikidata.org/wiki/Q82622","display_name":"Punctuation","level":2,"score":0.6142046451568604},{"id":"https://openalex.org/C66402592","wikidata":"https://www.wikidata.org/wiki/Q2271421","display_name":"Sentiment analysis","level":2,"score":0.6133401393890381},{"id":"https://openalex.org/C110875604","wikidata":"https://www.wikidata.org/wiki/Q75","display_name":"The Internet","level":2,"score":0.48671796917915344},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4750226140022278},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.46532317996025085},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4599963128566742},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4577750861644745},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.44922178983688354},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.4205242991447449},{"id":"https://openalex.org/C46503548","wikidata":"https://www.wikidata.org/wiki/Q1145976","display_name":"Plain text","level":3,"score":0.4146419167518616},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.3432673513889313},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.0},{"id":"https://openalex.org/C148730421","wikidata":"https://www.wikidata.org/wiki/Q141090","display_name":"Encryption","level":2,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/1390749.1390763","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1390749.1390763","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the second workshop on Analytics for noisy unstructured text data","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.7599999904632568,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W38739846","https://openalex.org/W47585637","https://openalex.org/W69034622","https://openalex.org/W147952312","https://openalex.org/W171402391","https://openalex.org/W1493553602","https://openalex.org/W1501838223","https://openalex.org/W1502364498","https://openalex.org/W1581485226","https://openalex.org/W1972099155","https://openalex.org/W1994485670","https://openalex.org/W2052935438","https://openalex.org/W2057900969","https://openalex.org/W2074707325","https://openalex.org/W2081375810","https://openalex.org/W2108251622","https://openalex.org/W2114524997","https://openalex.org/W2115023510","https://openalex.org/W2127973959","https://openalex.org/W2141631351","https://openalex.org/W2152119282","https://openalex.org/W2155328222","https://openalex.org/W2160660844","https://openalex.org/W2167072947","https://openalex.org/W2168625136","https://openalex.org/W2199803028","https://openalex.org/W2293633461","https://openalex.org/W2964308366","https://openalex.org/W3146306708"],"related_works":["https://openalex.org/W2165504147","https://openalex.org/W2986643010","https://openalex.org/W1990527953","https://openalex.org/W2030910246","https://openalex.org/W3093218477","https://openalex.org/W4287775364","https://openalex.org/W2529247374","https://openalex.org/W3029858749","https://openalex.org/W36911888","https://openalex.org/W13099415"],"abstract_inverted_index":{"The":[0,37,109],"proliferation":[1],"of":[2,10,16,23,31,69,126,183,192],"Internet":[3],"has":[4,53],"not":[5,90],"only":[6],"generated":[7,27,39],"huge":[8],"volumes":[9],"unstructured":[11,65],"information":[12,63,133],"in":[13,28,199],"the":[14,29,80,100,104,141,246],"form":[15,30],"web":[17],"documents,":[18],"but":[19],"a":[20,196,204,212,238,249,257],"large":[21],"amount":[22],"text":[24,66,82,137,173],"is":[25,56,83,116,176,195],"also":[26,97],"emails,":[32],"blogs,":[33],"and":[34,55,85,162,180,187,219],"feedbacks":[35],"etc.":[36],"data":[38,138],"from":[40,64,134,155,171,185,211,232,256],"online":[41,135],"communication":[42,136],"acts":[43],"as":[44,91,93],"potential":[45],"gold":[46],"mines":[47],"for":[48,99,112,131],"discovering":[49],"knowledge.":[50],"Text":[51],"analytics":[52],"matured":[54],"being":[57],"successfully":[58],"employed":[59,98],"to":[60,102,140,207,228,251],"mine":[61],"important":[62],"documents.":[67],"Most":[68],"these":[70,127],"techniques":[71,76,227],"use":[72],"Natural":[73],"Language":[74],"Processing":[75],"which":[77,200,215,244],"assume":[78],"that":[79,143],"underlying":[81],"clean":[84,107,220],"correct.":[86],"Statistical":[87],"techniques,":[88],"though":[89],"accurate":[92],"linguistic":[94,226],"mechanisms,":[95],"are":[96,129,145,150],"purpose":[101],"overcome":[103],"dependence":[105,119],"on":[106,120,168,241],"text.":[108,221,234],"chief":[110],"bottleneck":[111],"designing":[113],"statistical":[114],"mechanisms":[115],"however":[117],"its":[118],"appropriately":[121],"annotated":[122],"training":[123,213],"data.":[124,174],"None":[125],"methodologies":[128],"suitable":[130],"mining":[132],"due":[139],"fact":[142],"they":[144],"often":[146],"noisy.":[147],"These":[148],"texts":[149],"informally":[151],"written.":[152],"They":[153],"suffer":[154],"spelling":[156],"mistakes,":[157],"grammatical":[158],"errors,":[159],"improper":[160],"punctuation":[161],"irrational":[163],"capitalization.":[164],"This":[165],"paper":[166],"focuses":[167],"opinion":[169,230,253],"extraction":[170],"noisy":[172,218,233],"It":[175],"aimed":[177],"at":[178,189],"extracting":[179],"consolidating":[181],"opinions":[182],"customers":[184],"blogs":[186],"feedbacks,":[188],"multiple":[190],"levels":[191],"granularity.":[193],"Ours":[194],"hybrid":[197],"approach,":[198,243],"we":[201,223],"initially":[202],"employ":[203,224],"semi-supervised":[205],"method":[206],"learn":[208],"domain":[209],"knowledge":[210],"repository":[214],"contains":[216],"both":[217],"Thereafter":[222],"localized":[225],"extract":[229],"expressions":[231,254],"We":[235],"have":[236],"developed":[237],"system":[239],"based":[240],"this":[242],"provides":[245],"user":[247],"with":[248],"platform":[250],"analyze":[252],"extracted":[255],"repository.":[258]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":22},{"year":2019,"cited_by_count":4},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":3},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":20},{"year":2014,"cited_by_count":7},{"year":2013,"cited_by_count":6},{"year":2012,"cited_by_count":10}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}