{"created":"2020-09-01T14:30:14.276157+00:00","id":4318,"links":{},"metadata":{"_buckets":{"deposit":"fc5c4802-7f49-464a-9a36-d3339cf5981c"},"_deposit":{"id":"4318","owners":[],"pid":{"revision_id":0,"type":"recid","value":"4318"},"status":"published"},"_oai":{"id":"oai:meral.edu.mm:recid/4318","sets":["1582963302567:1597824322519"]},"communities":["ucsy"],"item_1583103067471":{"attribute_name":"Title","attribute_value_mlt":[{"subitem_1551255647225":"Sentiment Analysis System in Big Data Environment","subitem_1551255648112":"en_US"}]},"item_1583103085720":{"attribute_name":"Description","attribute_value_mlt":[{"interim":"Nowadays, Big Data, a large volume of both structured and unstructured data,is generated from Social Media. Social Media are powerful marketing tools andSocial Big Data can offer the business insights. The major challenge facing Social BigData is attaining efficient techniques to collect a large volume of social data andextract insights from the huge amount of collected data. Sentiment Analysis of SocialBig Data can provide business insights by extracting the public opinions. Thetraditional analytic platforms need to be scaled up for analyzing a large volume ofSocial Big Data. Social data are by nature shorter and generally not constructed withproper grammatical rules and hence difficult to achieve high reliable result inSentiment Analysis. Acquiring effective training data is a challenge, although learningbased approaches are good for sentiment classification. Manual Labeling for trainingdata is time and labor consuming. Sentiment analysis based on multiclassclassification scheme is oriented towards classification of text into more detailedsentiment labels. However, multiclass classification with Single-tier architecturewhere single model is developed and entire labeled data is trained may decrease theclassification accuracy. The presence of sarcasm, an interfering factor that can flip thesentiment of the given text, is one of the challenges of Sentiment Analysis. Real-timetracking and analytics is important for Social Big Data because the speed may indeedbe the most important competitive business profits. Compared to batch processing ofSentiment Analysis on Big Data Analytics platform, Real-time analytic is dataintensive in nature and require to efficiently collect and process large volume andhigh velocity of data.In this research, proposed Sentiment Analysis system is implemented withdifferent architectures on different platforms to provide valuable information byanalyzing large scale social data in an efficient and timely manner. Firstly, SentimentAnalysis is implemented on traditional analytics platform by performing modelselection which is evaluated by comparing the performance of three different machinelearning algorithm (Naïve Bayes, Random Forest and Linear Regression). Fordeveloping scalable and high performance Sentiment Analysis system, SentimentAnalysis is implemented on Big Data Analytics Platform (Hadoop MapReduce). Thesystem enables high-level performance of sentiment classification while takingadvantage of combining lexicon-based classifier’s effortless setup process andiiilearning based classifier. Multi-tier Sentiment Analysis system on Big DataAnalytics Platform (MSABDP) is developed for achieving high level performance ofmulticlass classification. This system is implemented by combining lexicon andlearning based classification scheme with Multi-tier architecture. Multi-tier SentimentAnalysis system with sarcasm detection on Hadoop (MSASDH) is proposed toachieve high-level performance of sentiment classification. MSASDH identifiessarcasm and sentiment-emotion by conducting rule based sarcasm-sentiment detectionscheme and sentiment classification with Multi-tier architecture. Real-time Multi-tierSentiment Analysis system (RMSA) is implemented to achieve high levelperformance of multi-class classification in Real-time manner. To improve theclassification accuracy, the suitable classifier is selected by comparing the accuracy ofthree different learning based multiclass classification techniques: Naïve Bayes,Linear SVC and Logistic Regression.On the traditional analytics platform, Naïve Bayes classifier is better and theproposed system can achieved the promising accuracy. The evaluation result showsthat the proposed system on Big Data Analytics Platform has enabled to achieve thepromising accuracy by 84.2% and is able to scale up to analyze the large scale data bydecreasing the running time when adding more nodes in the cluster. The evaluationresults show that the proposed MSABDP is able to significantly improve theclassification accuracy over multi-class classification based on Single-tier architectureby 7%. The evaluation results show that detecting sarcasm can enhance the accuracyof Sentiment Analysis. The evaluation results show that Real-time Multi-tierSentiment Analysis achieves the promising accuracy and Linear SVC is better thanother techniques for Real-time Multi-tier Sentiment Analysis."}]},"item_1583103108160":{"attribute_name":"Keywords","attribute_value":[]},"item_1583103120197":{"attribute_name":"Files","attribute_type":"file","attribute_value_mlt":[{"accessrole":"open_access","date":[{"dateType":"Available","dateValue":"2019-09-23"}],"displaytype":"preview","filename":"Sentiment Analysis System in Big Data Environment(WNC).pdf","filesize":[{"value":"4768 Kb"}],"format":"application/pdf","licensetype":"license_note","mimetype":"application/pdf","url":{"url":"https://meral.edu.mm/record/4318/files/Sentiment Analysis System in Big Data Environment(WNC).pdf"},"version_id":"e9dedc7d-b7e6-4154-925e-e43e17e5f85c"}]},"item_1583103131163":{"attribute_name":"Journal articles","attribute_value_mlt":[{"subitem_issue":"","subitem_journal_title":"","subitem_pages":"","subitem_volume":""}]},"item_1583103147082":{"attribute_name":"Conference papers","attribute_value_mlt":[{"subitem_acronym":"","subitem_c_date":"","subitem_conference_title":"","subitem_part":"","subitem_place":"","subitem_session":"","subitem_website":""}]},"item_1583103211336":{"attribute_name":"Books/reports/chapters","attribute_value_mlt":[{"subitem_book_title":"","subitem_isbn":"","subitem_pages":"","subitem_place":"","subitem_publisher":""}]},"item_1583103233624":{"attribute_name":"Thesis/dissertations","attribute_value_mlt":[{"subitem_awarding_university":"University of Computer Studies, Yangon","subitem_supervisor(s)":[{"subitem_supervisor":""}]}]},"item_1583105942107":{"attribute_name":"Authors","attribute_value_mlt":[{"subitem_authors":[{"subitem_authors_fullname":"Chan, Wint Nyein"}]}]},"item_1583108359239":{"attribute_name":"Upload type","attribute_value_mlt":[{"interim":"Publication"}]},"item_1583108428133":{"attribute_name":"Publication type","attribute_value_mlt":[{"interim":"Thesis"}]},"item_1583159729339":{"attribute_name":"Publication date","attribute_value":"2019-01"},"item_1583159847033":{"attribute_name":"Identifier","attribute_value":"http://onlineresource.ucsy.edu.mm/handle/123456789/2257"},"item_title":"Sentiment Analysis System in Big Data Environment","item_type_id":"21","owner":"1","path":["1597824322519"],"publish_date":"2019-09-23","publish_status":"0","recid":"4318","relation_version_is_last":true,"title":["Sentiment Analysis System in Big Data Environment"],"weko_creator_id":"1","weko_shared_id":-1},"updated":"2021-12-13T00:54:22.737370+00:00"}