政大機構典藏-National Chengchi University Institutional Repository(NCCUR):Item 140.119/131171
English  |  正體中文  |  简体中文  |  Post-Print筆數 : 27 |  全文笔数/总笔数 : 114012/145044 (79%)
造访人次 : 52104127      在线人数 : 481
RC Version 6.0 © Powered By DSPACE, MIT. Enhanced by NTU Library IR team.
搜寻范围 查询小技巧：
  • 您可在西文检索词汇前后加上"双引号"，以获取较精准的检索结果
  • 若欲以作者姓名搜寻，建议至进阶搜寻限定作者字段，可获得较完整数据
    •  进阶搜寻


    请使用永久网址来引用或连结此文件: https://nccur.lib.nccu.edu.tw/handle/140.119/131171


    题名: 網路社群情緒對住宅不動產市場之影響
    The Effect of Social Media Sentiment on the Residential Real Estate Market
    作者: 黃暄雅
    Huang, Syuan-Ya
    贡献者: 林左裕
    Lin, Tsoyu Calvin
    黃暄雅
    Huang, Syuan-Ya
    关键词: 社群媒體
    文字探勘
    情緒分析
    住宅不動產市場
    向量自我迴歸模型
    Social Media
    Text Mining
    Sentiment Analysis
    Housing Market
    Vector Auto Regression (VAR)
    日期: 2020
    上传时间: 2020-08-03 18:09:50 (UTC+8)
    摘要: 由於不動產市場對買賣雙方的資訊不對稱性，使市場參與者無法參考足夠資訊並據以理性判斷，因此除了受到個人的心理預期而影響決策外，參與者常常透過與社會網絡互動而形成之市場氛圍互相影響決策。因此除了以總體經濟條件探討不動產市場走向外，近來許多研究嘗試透過消費者信心指數、採購經理人指數或景氣指數等來捕捉市場情緒，顯示預期之指標或行為因素對於不動產市場可能之影響，而透過情緒代理指標也彌補了學理上所認知僅以基本面並不足以解釋市場變化的缺陷。隨網路與智慧型裝置的高度普及，人與人之間除了實質的接觸外，更透過網路在社群網絡上密切互動，各種資訊於無形的社群平台快速傳播，社會大眾亦在社群媒體發表意見並交流，其內容包含了市場情緒與大眾對各種事件之反應，並潛移默化地影響大眾的決策思考與行為，因此社群媒體上的討論內容逐漸備受重視。
    本研究嘗試以網路社群媒體討論內容作為一市場情緒代理指標，探討社群媒體對於不動產市場價格之影響，選擇PTT論壇之Homesale板作為社群媒體討論內容的樣本來源，利用文字探勘與情緒分析技術剖析該社群討論內容，再轉換為樂觀或悲觀之情緒分數作為社群情緒變數；同時計算各月份之討論筆數作為社群討論頻率變數，藉由時間序列分析方法之向量自我迴歸(VAR)模型探究社群情緒分數、討論頻率與不動產市場價格之動態關聯。實證結果發現，前兩季的社群情緒分數將正向影響當期的房價，而前兩季的社群討論頻率將負向影響當期的房價，顯示社群討論內容與頻率確實對於房價具解釋效果。另外，社群情緒越正向時，房價呈現成長趨勢，但討論頻率越高時，房價卻呈趨緩之現象，此結果揭露出社群討論上對於不動產市場多偏向購買力不足的悲觀，反映了近年來大眾對於高房價之擔憂，可見透過社群討論內容不僅可補足過去總體經濟變數所無法解釋之市場意向，亦提供了一項掌握不動產市場走向的判斷指標。研究結果可提供給政府、不動產相關業者及購屋者在觀察市場、制定政策或投資決策時一有效且即時之參考。
    Due to the information asymmetry between buyers and sellers in the real estate market, market participants cannot refer to enough information and make rational judgments. Besides personal expectations that affect decision-making, participants often discuss with others through the social networks and have specific attitude toward some issue. Therefore, in addition to explaining the trend of the real estate market in terms of overall economic conditions(fundamentals), recent studies have tried to capture market sentiment through the consumer confidence index, the purchasing manager’s index, or the prosperity index, etc., showing the possible impact of expected indicators on the real estate market. By this way, the sentiment indicators can improve forecasts of housing market by fundamentals alone.
    With the high popularity of the internet and smart devices, people interact closely through the social network on the Internet. Various information is quickly spread on the internet, and people express and exchange their opinions through the social media. Its content includes market sentiment and the public`s response to different events, and it affects the public`s decision-making behavior in a subtle way. Therefore, the value of content on social media gets more attention gradually.
    This research attempts to get the discussion content from PTT Forum “Homesale” board as a sentiment indicator to explore the impact of social media on housing price, and use Text Mining and Sentiment Analysis skills to analyze the content and convert it into a numerical score as a social media sentiment variable. Besides, the research also calculates the number of discussions in each month as a discussion frequency variable.
    This research uses the vector auto regression of the time series analysis method (VAR) model to explore the dynamic correlation between social media sentiment score, discussion frequency and housing prices. The empirical results suggest that the social media sentiment scores in the last two quarters will positively related to the current housing prices, while the discussion frequency in the last two quarters will negatively be related to the current housing prices, showing that the content and frequency on social media discussions really can explain the housing prices. Furthermore, this result reveals that the discussions on social media tend to be pessimistic due to the lack of purchasing power on real estate, reflecting the public’s concerns about high housing prices.
    There can be seen through the discussion of social media not only to make up the market fluctuation that the overall economic variables cannot explain in the past, but also to provide an effective indicator to grasp the trend of the real estate market. The research results can provide a better and immediate reference for the government, real estate related companies, and home buyers to observe the market, organize policies or make investment decisions.
    參考文獻: 一、 中文參考文獻
    吳鶴窈，2013。「國內房價指標與經濟因素之關聯研究」，國立政治大學經營管理碩士學程(EMBA)學位論文。
    巫啟台，2002，「文件之關連資訊萃取及其概念圖自動建構」，國立成功大學資訊工程學系所碩士論文。
    李佳珍、盧永祥、丁安正，2012，「臺北市各區人口、家庭所得與房屋價格關聯性之研究」，『商業現代化學刊』，6(3):243-254。
    李政德，2019，「從社群網站看資訊流動」，科學人雜誌，取自https://sa.ylib.com/MagArticle.aspx?Unit=featurearticles&id=4287。
    李美杏、陳威廷、彭建文，2014，「亞洲城市房價基值與泡沫」，『都市與計劃』，41(2):169-198。
    周賓凰、池祥萱、周冠男、龔怡霖，2002，「行為財務學：文獻回顧與展望」，『證券市場發展季刊』，14:1-16。
    林左裕，2011，「貨幣政策與房價的關係」，國科會補助計畫。
    林左裕，2018，『不動產投資管理』六版，台北市：智勝文化事業有限公司。
    林秋瑾、王健安、張金鶚，1997，「房地產景氣與總體經濟景氣於時間上領先、同時、落後關係之探討」，『國家科學委員會研究彙刊；人文及社會科學』，7:1:35-56。
    林筱真，2016，「新聞媒體情緒對於房價之影響」，國立政治大學地政研學系碩士論文。
    邱聖皓，2018，「運用文字探勘技術於股價預測：考量基本面、技術面、籌碼面與消息面特徵」，國立中正大學資訊管理系研究所碩士論文。
    張金鶚、彭建文，2000，「總體經濟對房地產景氣之研究」，『國家科學委員會研究彙刊：人文及社會科學，10(3): 330-343』。
    張琇茵，2018，「基於社群與新聞內容之情感分析預測股價指數趨勢」，國立臺北科技大學碩士論文。
    梅強、林尚毅，2017，「臺灣總體經濟變數對六都房價之影響分析」，『亞太經濟管理評論』，21(1):33-48。
    許慶安，2017，「運用探勘技術於社會輿情以預測新竹市房地產市場之研究」，國立勤益科技大學資訊管理學系碩士學位論文。
    陳俊甫，2016，「透過社會大眾情緒預測台灣股市」，國立臺灣大學電機工程學碩士論文。
    陳韋凡、古倫維，2018，「中文情感語意分析套件CSentiPackage發展與應用」，『圖書館學與資訊科學』，44(1):24-41。
    黃裕烈、管中閔，2019，「美國聯準會會議紀要的文字探勘與台灣經濟變數預測」，『經濟論文叢刊 (Taiwan Economic Review)』，47(3): 363–391。
    楊奕農，2009，「時間序列分析 經濟與財務上之應用」。頁99-123、205-235、331-392、395-446，台北，雙葉書廊有限公司。
    劉澤，2015，「以文字探勘為基礎之財務風險分析方法研究」，國立政治大學資訊科學學系碩士論文。
    蕭伃婷，2018，應用文字探勘技術於旅館服務特性品質診斷，國立臺北大學企業管理學系碩士論文。
    賴碧瑩，2003，「從經濟結構變遷探討房地產市場與總體經濟之關連性」，『2003 年中華民國住宅學會第十二屆年會論文集』，45-62。
    嚴嘉慧，2002，「不動產市場各項指標與營建類股價關聯性之研究」，國立政治大學財務管理研究所碩士論文。

    二、 英文參考文獻
    Andreas, V., 2019, Predicting house price trends in The Netherlands between 2008 and 2018 with Twitter, Unpublished doctoral dissertation, Department of Cognitive Science & Artificial Intelligence School of Humanities And Digital Sciences, University of Tilburg, Netherlands.
    Baker and Wugler, 2007, “Investor Sentiment in the Stock Market.”, The Journal of Economic Perspectives, 21(2): 129–151.
    Beracha, E., and Wintoki, M. B., 2013, “Forecasting residential real estate price changes from online search activity.”, Journal of Real Estate Research, 35(3):283-312.
    Beracha, E., Lang, M., and Hausier, J., 2019, "On the Relationship between Market Sentiment and Commercial Real Estate Performance-A Textual Analysis Examination.", The Journal of Real Estate Research, 41(4):605-637.
    Bjørnland, H. C., and Jacobsen, D. H., 2008,“The Role of House Prices in the Monetary Policy Transmission Mechanism in the U.S.,”, Working Paper of Norges Bank, 6(4):218-229.
    Bollen, J., Mao, H., and Zeng, X. J., 2011, “Twitter mood predicts the stock market”, Journal of Computational Science, 2(1):1-8.
    Case, K., and Shiller, R., 1989, “The Efficiency of the Market for Single-Family Homes.“, The American Economic Review, 79(1):125-137.
    Changha, J., Soydemir, G., and Tidwell, A., 2014, “ The U.S. housing market and the pricing of risk: Fundamental analysis and market sentiment.”, Journal of Real Estate, 36(2):187-219.
    Croce, R. M., and Haurin, D. R., 2009, "Predicting turning points in the housing market", Journal of Housing Economics, 18(4):281-293.
    Das, S., and Chen, M. Y., 2007, "Yahoo! for Amazon: Sentiment Extraction from Small Talk on the Web", Management Science, 53(9):1375-1388.
    David, L., Naranjo, A., and Scheick, B., 2014, "Investor Sentiment, Limits to Arbitrage and Private Market Returns", Real Estate Economics, 42(3):531-577
    Dhaoui, C., Webster, C. M., and Tan, L. P., 2017, “Social media sentiment analysis: Lexicon versus machine learning.”, The Journal of Consumer Marketing, 34(6): 480-488.
    Granger, C. W. J., and Newbold P., 1974, “Experience with Forecasting Univariate Time Series and the Combination of Forecasts.”, Journal of the Royal Statistical Society, 137(2):131-165.
    Gupta, R., Marco L., Chi K.; Plakandaras, V., and Wong,W. K.,2019, "The role of housing sentiment in forecasting U.S. home sales growth: evidence from a Bayesian compressed vector autoregressive model.", Ekonomska Istrazivanja: Znanstveno-Strucni Casopis, 32(1): 2554-2567.
    Hohenstatt, R., Kaesbauer, M., and Schaefers,W., 2011, “Geco and its Potential for Real Estate Research: Evidence from the U.S. Housing Market.”, Journal of Real Estate Research, 33(4):471-506.
    Hu, M., and Liu, B., 2004, “Mining and Summarizing Customer Reviews,” Proceedings 13 of ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, 168-177.
    Hui, E. C., and Wang, Z., 2014, ”Market sentiment in private housing market”, Habitat International, 44:75-385.
    Ku, L. W., and Chen, H. H., 2007, “Mining opinions from the Web: Beyond relevance retrieval.”, Journal of the American Society for Information Science and Technology, 58(12):1838-1850.
    López-Cabarcos, M., Piñeiro-Chousa, J., and Pérez-Pico, A., 2017, “The impact technical and non-technical investors have on the stock market: Evidence from the sentiment extracted from social networks”, Journal of Behavioral and Experimental Finance, 15:5-20.
    Marcato G., and Nanda A., 2014, “Information Content and Forecasting Ability of Sentiment Indicators: Case of Real Estate Market.”, Journal of Real Estate Research, 38(2):165-204.
    Reed, M., 2016, "A Study of Social Network Effects on the Stock Market.", Journal of Behavioral Finance, 17(4):342-351.
    Ruscheinsky, Roxanne, J., Marcel, L., and Wolfgang, S., 2018, "Real estate media sentiment through textual analysis.", Journal of Property Investment & Finance, 36(5):410-428.
    Shiller, R.J., 2007, “Understanding recent trends in house prices and home ownership”, paper presented at the Federal Reserve Bank of Kansas City’s Jackson Hole Symposium, Kansas, August 31th - September 1st.
    Stevenson, S., 2008, “Modeling Housing Market Fundamentals: Empirical Evidence of Extreme Market Conditions.”, Real Estate Economics, 36(1):1–29.
    Thien Hai N., Kiyoaki S., and Julien V., 2015,”Sentiment analysis on social media for stock movement prediction,”, Expert Systems with Applications, 42(24): 9603-9611.
    Tumasjan, A., Sprenger, T. O., Sandner, P. G., and Welpe, I. M., 2010, ”Predicting elections with Twitter: what 140 characters reveal about political sentiment” ICWSM, 10:178-185.
    Turney, P. D., 2002, “Thumbs up or thumbs down? Semantic orientation applied to 55 unsupervised classification of reviews,” Paper presented at proceedings of the 40th Annual Meeting of the Association for Computational Linguistic, Philadelphia, Pennsylvania, USA, July 7th -July 12th .
    Weber, W., and Devaney, M., 1996, “Can Consumer Sentiment Surveys Forecast Housing Starts?”, Appraisal Journal, 4:343–350.
    Wheaton, C.W., and Gleb, N., 2008, ”The 1998-2005 Housing `Bubble.”, Journal of Real Estate Research, 30(1):1-26.
    William, D. L., 2002, "The Real Price of Housing and Money Supply Shocks: Time Series Evidence and Theoretical Simulations", Journal of Housing Economics,11(1):40-74.
    Wu, L., and Brynjolfsson, E., 2009, “The Future of Prediction: How Google Searches Foreshadow Housing Prices and Quantities.”, ICIS 2009 Proceedings - Thirtieth International Conference on Information Systems.
    Zamani, M., and Schwartz, H., 2017, “Using Twitter Language to Predict the Real Estate Market.”, Association for Computational Linguistics, 2:28-33.
    描述: 碩士
    國立政治大學
    地政學系
    107257028
    資料來源: http://thesis.lib.nccu.edu.tw/record/#G0107257028
    数据类型: thesis
    DOI: 10.6814/NCCU202000864
    显示于类别:[地政學系] 學位論文

    文件中的档案:

    档案 描述 大小格式浏览次数
    702801.pdf1931KbAdobe PDF216检视/开启


    在政大典藏中所有的数据项都受到原著作权保护.


    社群 sharing

    著作權政策宣告 Copyright Announcement
    1.本網站之數位內容為國立政治大學所收錄之機構典藏，無償提供學術研究與公眾教育等公益性使用，惟仍請適度，合理使用本網站之內容，以尊重著作權人之權益。商業上之利用，則請先取得著作權人之授權。
    The digital content of this website is part of National Chengchi University Institutional Repository. It provides free access to academic research and public education for non-commercial use. Please utilize it in a proper and reasonable manner and respect the rights of copyright owners. For commercial use, please obtain authorization from the copyright owner in advance.

    2.本網站之製作，已盡力防止侵害著作權人之權益，如仍發現本網站之數位內容有侵害著作權人權益情事者，請權利人通知本網站維護人員(nccur@nccu.edu.tw)，維護人員將立即採取移除該數位著作等補救措施。
    NCCU Institutional Repository is made to protect the interests of copyright owners. If you believe that any material on the website infringes copyright, please contact our staff(nccur@nccu.edu.tw). We will remove the work from the repository and investigate your claim.
    DSpace Software Copyright © 2002-2004  MIT &  Hewlett-Packard  /   Enhanced by   NTU Library IR team Copyright ©   - 回馈