應用文字探勘之自動化新聞文本分析以探討社會對新聞事件之反應

論文名稱(中文):, 應用文字探勘之自動化新聞文本分析以探討社會對新聞事件之反應. 論文名稱(外文):, Automatic Content Analysis Using Text Mining to Investigate ... 資料載入處理中... 圖書館首頁| 網站地圖| 首頁| 本站說明| 聯絡我們| 相關資源| 台聯大論文系統| 操作說明 | English 簡易查詢 進階查詢 論文瀏覽 熱門排行 我的研究室 上傳論文 建檔說明 常見問題 帳號：guest(167.99.71.17)          離開系統 字體大小：       詳目顯示 第1筆/ 共1筆  /1頁 以作者查詢圖書館館藏、以作者查詢臺灣博碩士論文系統、以作者查詢全國書目 論文基本資料 摘要 外文摘要 論文目次 參考文獻 電子全文 作者(中文):戴瑜廷作者(外文):Tai,YuTing論文名稱(中文):應用文字探勘之自動化新聞文本分析以探討社會對新聞事件之反應論文名稱(外文):AutomaticContentAnalysisUsingTextMiningtoInvestigateHowNewsEventsTriggertheResponseofSociety指導教授(中文):林福仁指導教授(外文):Lin,FuRen口試委員(中文):雷松亞徐茉莉口試委員(外文):Ray,SoumyaShmueli,Galit學位類別:碩士校院名稱:國立清華大學系所名稱:服務科學研究所學號:101078505出版年(民國):104畢業學年度:103語文別:英文論文頁數:90中文關鍵詞:新聞摘要、文字探勘、文本分析、食品安全、焦點訪談、社會學習外文關鍵詞:Summarization、TextMining、AutomaticContentAnalysis、Foodsafety、FocusedConversationMethod、ORID、SocialLearning相關次數: 推薦:0點閱:329評分:下載:1收藏:0 近年來食品安全問題層出不窮，接連爆發塑化劑、毒澱粉、假油一連串的事件。

然而，相關報導的數量龐大，一般民眾難以有效閱讀完所有資訊；再者，一連串的事件都與食品安全相關，社會是否從過去事件中學習到經驗，並在類似事件發生時做出不同的因應也是值得探討的議題。

但新聞閱聽者難以從非結構化的訊息中了解事件之間社會反應的差異，因此本研究的目的在於自動化分析同一主題的多個事件，探討社會對新聞事件的反應。

本研究旨在提出一個自動化的文本分析系統，自動分析隸屬同一主題的多個新聞事件。

首先，本研究透過分群技術(Clustering)，以事件發展階段及利害關係人二維向度，呈現各利害關係人在事件各階段的言論內容。

再者，系統將透過摘要技術(summarization)萃取事件發展重點以提供單一事件發展的新聞摘要。

最後，以焦點訪談法(ORID)衡量系統的有效性，並同時探索讀者對於事件的反應。

藉由本研究提出的自動化文本分析系統，一般民眾可以更快速及有效的了解新聞事件的發展，回顧事件發生當下的感受、想法與行動。

Inrecentyears,thecrisisoffoodsafetyeventscontinuedhappenedininterval.Therearethreemainfoodsafetyevents,insequence,“Plasticizer”,“Poisonstarch”and“Fakeoil”.However,therelatednewsreportsaretooenormoustobedigestedefficientlybythereaders.Inaddition,it’sinterestedtoknowifsimilareventshappenagain,wouldtheylearnsomethingfromthepastexperiencesandrespondsinadifferentway.Thisstudyaimedtoproposeasystemthatcanautomaticanalyzetherelatednewsbelongingtothesametopic.First,thisstudypresentstheopinionsofeachstakeholderoneachperiodofthenewsdevelopmentbyclustering.Second,thissystemextractstheimportantcontentofnewsreportsusingsummarizationandprovidesthesummarizationofeachnewseventtoreaders.Finally,thisstudycombinesthesystemwithFocusedConversationMethod(ORID)toevaluatetheeffectiveofthesystemandtoexploretheresponseofreaderstothenewsevents.Withthefacilityofthesystemthatweproposed,thereaderscanunderstandthedevelopmentofnewseventefficientlyandrecalltheirfeeling,thought,andreactionforthenewseventsatthemomentthattheeventhappened. Chapter1Introduction11.1ResearchBackground11.2ResearchMotivation31.3ResearchObjectives4Chapter2LiteratureReview52.1AutomaticContentAnalysis52.2TextSummarization62.3ClusteringAlgorithm82.3.1HierarchicalClusterAnalysis(HCA)82.3.2OtherClusteringMethods92.4FocusedConversationMethod(ORID)11Chapter3SystemFrameworkandMethodology143.1Definition153.2SystemArchitecture163.3DataAcquisition183.4Preprocessing193.4.1Wordsegmentation193.4.2TermAggregation193.4.3FeatureSelection213.5OpinionExtraction223.6Clustering273.7Summarization283.8ContentAnalysis28Chapter4SystemImplementationandResults304.1DataSource304.2SystemImplementation304.3Results33Chapter5EvaluationandResults395.1EvaluationDesign395.2EvaluationResults425.2.1Theunderstandingofnewsevents425.2.2Thechangeofresponseofeachreaderforthreeevents445.2.3Thechangeofresponseofstakeholdersforthreeevents465.3Discussions50Chapter6ConclusionandFutureWork51References53AppendixA.ContentsPresentedtoSubjectinRound157AppendixB.SummarizationResultsandContentsPresentedtoSubjectinRound260AppendixC.ORIDInterviewTranscriptinRound164AppendixD.ORIDInterviewTranscriptinRound272AppendixE.OpinionsofStakeholdersCrossThreeEvents84 Alguliev,R.M.,Aliguliyev,R.M.,&Mehdiyev,C.A.(2011).Sentenceselectionforgenericdocumentsummarizationusinganadaptivedifferentialevolutionalgorithm.SwarmandEvolutionaryComputation,1(4),213-222.Allan,J.,Gupta,R.,&Khandelwal,V.(2001,September).Temporalsummariesofnewtopics.InProceedingsofthe24thannualinternationalACMSIGIRconferenceonResearchanddevelopmentininformationretrieval(pp.10-18).ACM.Baptiste,N.(1995).ProfessionaldevelopmentAlwaysgrowingandlearning:TheORID—Atechniquetoenhancecommunication.EarlyChildhoodEducationJournal,22(4),39-40.Berghel,H.(1997).Cyberspace2000:Dealingwithinformationoverload.CommunicationsoftheACM,40(2),19-24.Cheney,D.(2013).Textminingnewspapersandnewscontent:newtrendsandresearchmethodologies.Chang,Y.H.,Chang,C.Y.,&Tseng,Y.H.(2010).Trendsofscienceeducationresearch:Anautomaticcontentanalysis.JournalofScienceEducationandTechnology,19(4),315-331.Carbonell,J.,&Goldstein,J.(1998,August).TheuseofMMR,diversity-basedrerankingforreorderingdocumentsandproducingsummaries.InProceedingsofthe21stannualinternationalACMSIGIRconferenceonResearchanddevelopmentininformationretrieval(pp.335-336).ACM.Feldman,R.,&Sanger,J.(2007).Thetextmininghandbook:advancedapproachesinanalyzingunstructureddata.CambridgeUniversityPress.Hsu,C.H.(2004).AutomaticallyConstructingOntologyonSemanticWeb(Doctoraldissertation,MSthesis,FuJenCatholicUniversity,Taiwan).Hu,J.Y.(2009).追蹤進行中新聞議題產生事件主軸摘要.清華大學科技管理研究所學位論文,1-81.Han,J.,Kamber,M.,&Pei,J.(2011).Datamining:conceptsandtechniques:conceptsandtechniques.Elsevier.Hevner,A.R.,March,S.T.,Park,J.,&Ram,S.(2004).Designscienceininformationsystemsresearch.MisQuarterly,28(1),75-105.Hsieh,H.F.,&Shannon,S.E.(2005).Threeapproachestoqualitativecontentanalysis.Qualitativehealthresearch,15(9),1277-1288.Ilango,M.R.,&Mohan,V.(2010).Asurveyofgridbasedclusteringalgorithms.InternationalJournalofEngineeringScienceandTechnology,2(8),3441-3446.King,B.(1967).Step-wiseclusteringprocedures.JournaloftheAmericanStatisticalAssociation,62(317),86-101.Kriegel,H.P.,Kröger,P.,Sander,J.,&Zimek,A.(2011).Density‐basedclustering.WileyInterdisciplinaryReviews:DataMiningandKnowledgeDiscovery,1(3),231-240.Luhn,H.P.(1958).Theautomaticcreationofliteratureabstracts.IBMJournalofresearchanddevelopment,2(2),159-165.Lin,F.R.,&Liang,C.H.(2008).Storyline-basedsummarizationfornewstopicretrospection.DecisionSupportSystems,45(3),473-490.Lai,Y.S.,&Wang,R.J.(2003,October).Towardsautomaticknowledgeacquisitionfromtextbasedonontology-centricknowledgerepresentationandacquisition.InProceedingoftheSemAnnot2003Workshop.Mani,I.(2001,October).Recentdevelopmentsintextsummarization.InProceedingsofthetenthinternationalconferenceonInformationandknowledgemanagement(pp.529-531).ACM.McKeown,K.R.,Barzilay,R.,Evans,D.,Hatzivassiloglou,V.,Klavans,J.L.,Nenkova,A.,...&Sigelman,S.(2002,March).TrackingandsummarizingnewsonadailybasiswithColumbia'sNewsblaster.InProceedingsofthesecondinternationalconferenceonHumanLanguageTechnologyResearch(pp.280-285).MorganKaufmannPublishersInc..Radev,D.R.,Hovy,E.,&McKeown,K.(2002).Introductiontothespecialissueonsummarization.Computationallinguistics,28(4),399-408.Mani,I.,&Maybury,M.T.(Eds.).(1999).Advancesinautomatictextsummarization(Vol.293).Cambridge,MA:MITpress.Moretti,F.,vanVliet,L.,Bensing,J.,Deledda,G.,Mazzi,M.,Rimondini,M.,...&Fletcher,I.(2011).Astandardizedapproachtoqualitativecontentanalysisoffocusgroupdiscussionsfromdifferentcountries.Patienteducationandcounseling,82(3),420-428.Radev,D.R.,&Fan,W.(2000,October).Automaticsummarizationofsearchenginehitlists.InProceedingsoftheACL-2000workshoponRecentadvancesinnaturallanguageprocessingandinformationretrieval:heldinconjunctionwiththe38thAnnualMeetingoftheAssociationforComputationalLinguistics-Volume11(pp.99-109).AssociationforComputationalLinguistics.Radev,D.R.,Jing,H.,Styś,M.,&Tam,D.(2004).Centroid-basedsummarizationofmultipledocuments.InformationProcessing&Management,40(6),919-938.Radev,D.,Otterbacher,J.,Winkel,A.,&Blair-Goldensohn,S.(2005).NewsInEssence:summarizingonlinenewstopics.CommunicationsoftheACM,48(10),95-98.Schilling,J.(2006).Onthepragmaticsofqualitativeassessment.EuropeanJournalofPsychologicalAssessment,22(1),28-37.Spee,J.C.(2005).Usingfocusedconversationintheclassroom.JournalofManagementEducation,29(6),833-851.Spangler,W.D.,Gupta,A.,Kim,D.H.,&Nazarian,S.(2012).Developingandvalidatinghistoriometricmeasuresofleaderindividualdifferencesbycomputerizedcontentanalysisofdocuments.TheLeadershipQuarterly,23(6),1152-1172.Stanfield,R.B.(2000).Theartoffocusedconversation.GabriolaIsland,BC:NewSocietyPublishers,17-29.Salvador,S.,&Chan,P.(2004,November).Determiningthenumberofclusters/segmentsinhierarchicalclustering/segmentationalgorithms.InToolswithArtificialIntelligence,2004.ICTAI2004.16thIEEEInternationalConferenceon(pp.576-584).IEEE.Sneath,P.H.,&Sokal,R.R.(1973).Numericaltaxonomy.Theprinciplesandpracticeofnumericalclassification.Salton,G.,Wong,A.,&Yang,C.S.(1975).Avectorspacemodelforautomaticindexing.CommunicationsoftheACM,18(11),613-620.WardJr,J.H.(1963).Hierarchicalgroupingtooptimizeanobjectivefunction.JournaloftheAmericanstatisticalassociation,58(301),236-244.Wang,W.M.,Cheung,C.F.,Lee,W.B.,&Kwok,S.K.(2008).Miningknowledgefromnaturallanguagetextsusingfuzzyassociatedconceptmapping.InformationProcessing&Management,44(5),1707-1719.Wu,S.H.,Day,M.Y.,Tsai,T.H.,&Hsu,W.L.(2002).FAQ-centeredorganizationalmemory.InKnowledgeManagementandOrganizationalMemories(pp.103-112).SpringerUS.Xue,N.(2003).Chinesewordsegmentationascharactertagging.ComputationalLinguisticsandChineseLanguageProcessing,8(1),29-48.Yang,Y.(1995,July).Noisereductioninastatisticalapproachtotextcategorization.InProceedingsofthe18thannualinternationalACMSIGIRconferenceonResearchanddevelopmentininformationretrieval(pp.256-263).ACM.Zou,F.,Wang,F.L.,Deng,X.,Han,S.,&Wang,L.S.(2006,April).AutomaticconstructionofChinesestopwordlist.InProceedingsofthe5thWSEASinternationalconferenceonAppliedcomputerscience(pp.1010-1015). (此全文限內部瀏覽)電子全文摘要 推文 推薦 評分 引用網址 轉寄         top 相關論文 1. EstimatingTrustStrengthforSupportingEffectiveRecommendationServices 2. 運用資料探勘技術協助專利維護決策 3. 人們為什麼願意在虛擬社群上分享?以雅虎奇摩知識家為例 4. 雲端上的商業智慧-不同資訊揭露程度的預測模型整合模式 5. SupportingPatentLicenseDecision:ADataMiningApproach 6. UNDERSTANDINGTHECONTINUANCEUSAGEOFE-READERSTOREAD–FROMAFLOWTHEORYPERSPECTIVE 7. 根據個人關注議題探索商業生態資訊 8. 健保論人計酬支付制度下對社區健康照護服務模式發展之影響-以台北市欒樹社區醫療群為例 9. 從「服務設計」到「為服務人而設計」—以H醫院遠距健康照護第一線員工為例 10. 服務設計活動中邏輯交互使用之研究-以家戶電視使用行為為例 11. LearningClassificationModelsFromDatasetswithBlockMissing 12. 以行動者網絡理論觀點探討有機農業之服務價值網絡的形成 13. 應用文件探勘技術進行立法文本自動化分析 14. 提升基於宣告結構進行專利前案搜尋之時間效率與準確性 15. 透過腦機介面技術擷取資料進行認知負荷分類:應用於服務設計的初步努力     簡易查詢 | 進階查詢 | 論文瀏覽 | 熱門排行 | 管理/審核者登入