{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,30]],"date-time":"2025-10-30T06:22:57Z","timestamp":1761805377970,"version":"3.28.0"},"reference-count":25,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2018,10]]},"DOI":"10.1109\/aiccsa.2018.8612867","type":"proceedings-article","created":{"date-parts":[[2019,1,18]],"date-time":"2019-01-18T01:26:29Z","timestamp":1547774789000},"page":"1-7","source":"Crossref","is-referenced-by-count":2,"title":["A Cleaning Algorithm for Noiseless Opinion Mining Corpus Construction"],"prefix":"10.1109","author":[{"given":"Otman","family":"Manad","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Anna","family":"Pappa","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Gilles","family":"Bernard","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2014.07.007"},{"key":"ref11","first-page":"83","article-title":"Choosing scrapy","volume":"31","author":"myers","year":"2015","journal-title":"J Comput Sci Coll"},{"key":"ref12","first-page":"4188","article-title":"Developing corpora for sentiment analysis: The case of irony and senti-tut (extended abstract)","author":"bosco","year":"2015","journal-title":"Proceedings of the Twenty-Fourth International Joint Conference on Artificial Intelligence IJCAI 2015 Buenos Aires Argentina"},{"key":"ref13","article-title":"Bolt chinese-english word alignment and tagging - discussion forum training","author":"li","year":"2016","journal-title":"Linguistic Data Consortium"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/1718487.1718542"},{"key":"ref15","article-title":"A survey on web forum crawling techniques","volume":"3","author":"mahara","year":"2014","journal-title":"International Journal of Innovative Research in Science Engineering and Technology"},{"key":"ref16","first-page":"33","article-title":"Focus: Learning to crawl web forums","author":"jingtian","year":"2012","journal-title":"Proceedings of the 21st International Conference on World Wide Web Ser WWW '12"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.5120\/20445-2796"},{"key":"ref18","first-page":"409","article-title":"Building a large-scale corpus for evaluating event detection on twitter","volume":"13","author":"mcminn","year":"2013","journal-title":"Proceedings of the 22Nd ACM International Conference on Information & Knowledge Management ser CIKM '"},{"key":"ref19","first-page":"97","article-title":"An interaction approach between services for extracting relevant data from tweets corpora","volume":"1","author":"dref","year":"2016","journal-title":"CILC 2016 8th International Conference on Corpus Linguistics ser EPiC Series in Language and Linguistics"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/363958.363994"},{"key":"ref3","first-page":"707","author":"levenshtein","year":"1966","journal-title":"Binary Codes Capable of Correcting Deletions Insertions and Reversals"},{"key":"ref6","first-page":"69","article-title":"Lois de distribution florale dans la zone alpine","volume":"38","author":"jaccard","year":"1902","journal-title":"Bulletin de la Socit Vaudoise des Sciences Naturelles"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1016\/S0925-2312(98)00031-9"},{"key":"ref8","article-title":"The state of record linkage and current research problems","author":"winkler","year":"1999","journal-title":"Statistical Research Division U S Census Bureau Tech Rep"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1080\/01621459.1989.10478785"},{"journal-title":"Natural Language Annotation for Machine Learning a Guide to Corpus-building for Applications","year":"2012","author":"pustejovsky","key":"ref2"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1016\/0010-4809(92)90005-U"},{"key":"ref1","article-title":"Multilingual corpus development for opinion mining","author":"schulz","year":"2010","journal-title":"Proceedings of the International Conference on Language Resources and Evaluation LREC 2010 17–23 May 2010 Valletta Malta"},{"key":"ref20","first-page":"274","article-title":"Review web pages collector tool for thematic corpus creation","volume":"1","author":"medrouk","year":"2016","journal-title":"CILC 2016 8th International Conference on Corpus Linguistics ser EPiC Series in Language and Linguistics"},{"key":"ref22","article-title":"Nutch: A Flexible and Scalable Open-Source Web Search Engine","author":"khare","year":"2005","journal-title":"CommerceNet ser CN-TR-04–04"},{"key":"ref21","first-page":"109","article-title":"Roadrunner: Towards automatic data extraction from large web sites","volume":"1","author":"crescenzi","year":"2001","journal-title":"Proceedings of the 20th International Conference on Very Large Data Bases Ser VLDB"},{"journal-title":"Removing boilerplate and duplicate content from web corpora [online]","year":"2011","author":"pomiklek","key":"ref24"},{"key":"ref23","first-page":"1313","article-title":"Bootcat: Bootstrapping corpora and terms from the web","author":"baroni","year":"2004","journal-title":"Proceedings of LREC 2004"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/11581062_24"}],"event":{"name":"2018 IEEE\/ACS 15th International Conference on Computer Systems and Applications (AICCSA)","start":{"date-parts":[[2018,10,28]]},"location":"Aqaba","end":{"date-parts":[[2018,11,1]]}},"container-title":["2018 IEEE\/ACS 15th International Conference on Computer Systems and Applications (AICCSA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8612460\/8612765\/08612867.pdf?arnumber=8612867","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,1,26]],"date-time":"2022-01-26T21:49:58Z","timestamp":1643233798000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8612867\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,10]]},"references-count":25,"URL":"https:\/\/doi.org\/10.1109\/aiccsa.2018.8612867","relation":{},"subject":[],"published":{"date-parts":[[2018,10]]}}}