房地產被視為經濟成長的火車頭產業，可同時帶動營建業、零售業及金融業之發展，影響層面廣泛。由於在經濟活動中扮演重要角色，因此房地產通常為各國政府所重視的產業，具有容易受到政府政策影的特性。除此之外，房地產也具有高異質性、高交易成本及低流動等特性，使其價格的調整較為緩慢，無法立即反應市場的基本面訊息，導致房地產容易受到市場情緒的影響。在過去的文獻中對於房地產市場多有所探討，主要從政府政策面及市場情緒面分別與房地產做討論，尚無將二者合併一起列入研究，且過去文獻也偏重探討消費面如房價、報酬率、交易量或貸款違約率等議題。為了捕捉投資人對於房地產市場的情緒，我們從 Mobil01 論壇中擷取文字資料，將論壇內房地產討論版中所有文章及回覆等作為資料，並且參考 Baker et al. (2016) 編制 EPU (economic policy uncertainty) 指標作法選取及整理房地產政策關鍵字，把政府房地產相關政策的文字內容納入考量，建立一同時涵蓋政府政策面及市場情緒二種因子之指標。此外，我們也增加探討生產面之變數 (如建築貸款新增核貸筆數及建案開工數) 議題，並使用迴歸模型、決策樹 (decision tree) 以及決策森林 (random forest) 來預測該情緒指標與房地產相關變數及經濟變數間之關聯性。

The real estate industry is regarded as the “economic driver”, which can drive the development of the construction, retail and financial sectors, and plays an important role in economic activities. In addition, the high heterogeneity, high transaction costs and low liquidity of real estate make the adjustment of housing price slowly. That is, the real estate market not only reflects the fundamental information immediately, but also sensitives to sentiment. In the literature, the real estate market has been discussed mainly in terms of government policies and market sentiment, but these two issues have not yet been studied together. To capture investors' sentiment on the real estate market, we extracted textual data from the Mobil01 forum and used all textual articles and responses from the real estate discussion forum. To reflect social media sentiment, following Baker et al. (2016), some sentiment and policies keywords are adopted for constructing the proposed textual-based real estate market indicator. Then, we analyzed the relationships between the proposed indicator and real estate market-related statistics, such as the number of new approval of construction loans and the number of construction starts. Lastly, we use regression models、decision tree and random forest model to predict the correlation between the sentiment indicators and real estate related and economic variables.

參考文獻
1.朱芳妮、楊茜文、蘇子涵與陳明吉 (2020)，「情緒會影響房市嗎？指數編制與驗證」， 《住宅學報》，29，35-68
2.陳明吉與曾琬婷 (2008)，「台灣不動產市場從眾行為之檢視」， 《管理與系統》，15，591-615
3.郭又瑋 (2020)，「以 DID 計量方法分析:央行貸款成數限制對房貸逾期之影響」，碩士論文，台北:國立臺灣大學經濟學研究所。
4.黃裕烈與管中閔 (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》，47，363-391
5.Armstrong, J., H. Skilling and F. Yao (2019), “Loan-to-value Ratio Restrictions and House Prices: Micro Evidence from New Zealand,” Journal of Housing Economics, 44, 88-98.
6.Baker, S. R., N. Bloom and S.J. Davis (2016), “Measuring Economic Policy Uncertainty,” The Quarterly Journal of Economics, 131, 1593-1636.
7.Baker, M. and J. Wurgler (2006), “Investor Sentiment and the Cross-Section of Stock Returns,” The Journal of Finance, 61, 1645-1680.
8.Chauvet, M., S. A. Gabriel and C. Lutz (2016), “Mortgage Default Risk: New Evidence from Internet Search Queries,” Journal of Urban Economics, 96, 91-111.
9.Crowe, C., G. D. Ariccia, D. Igan, and P. Rabanal (2011), “How to Deal with Real Estate Booms: Lessons from Country Experiences,” IMF Working Paper.
10.Dokko, J., B.M. Doyle, M.T. Kiley, J. Kim, S. Sherlund, J. Sim, S.V. Den and J.P. L'Huillier (2011), “Monetary Policy and the Global Housing Bubble,” Economic Policy, 26, 237-287.
11.Gallimore, P. and A. Gray (2002) “The Role of Investor Sentiment in Property Investment Decisions,” Journal of Property Research, 19, 111-120.
12.Granger C.W.J. and P. Newbold (1974), “Spurious Regression in Econometrics,” Journal of Econometrics, 2, 111-120.
13.Hui, E. and Z. Wang (2014), “Market Sentiment in Private Housing Market,” Habitat International, 44, 375-385.
14.Hui, E., Z. Dong, S. Jia, and C. Lam (2017), “How Does Sentiment Affect Returns of Urban Housing?” Habitat International, 64, 71-84.
15.Lai, R.-N. and R.-A. Van (2010), “Momentum and House Price Growth in the United States: Anatomy of a Bubble,” Real Estate Economics, 38, 753-773.
16.Lastrapes, W. D. (2002), “The Real Price of Housing and Money Supply Shocks: Time Series Evidence and Theoretical Stimulations,” Journal of Housing Economics, 11, 40-74.
17.Liu, J. and S. Wang (2010), “Empirical Study on the Relationship between Money Supply and the Property Market,” Paper presented at the International Conference on Management and Service Science.
18.Loughran, T. and B. Mcdonald (2011), “When Is a Liability Not a Liability? Textual Analysis, Dictionaries, and 10-Ks,” Journal of Finance, 66, 35-65.
19.Marcato, G. and A. Nanda (2016), “Information Content and Forecasting Ability of Sentiment Indicators: Case of Real Estate Market,” Journal of Real Estate Research, 38, 165-204.
20.Mishkin, F. S. (2007), “Housing and the Monetary Transmission,” Mechanism Finance and Economics Discussion Series Divisions of Research & Statistics and Monetary Affairs Federal Reserve Board, Washington, D.C.
21.Morgan, P.J., P. JoséRegisb and N. Salike (2019), “LTV Policy as a Macroprudential Tool and its Effects on Residential Mortgage Loans,” Journal of Financial Intermediation, 37, 89-103.
22.Said, E. S. and D. A., Dickey (1984), “Testing for Unit Roots in Autoregressive-Moving Average Models of Unknown Order,” Biometrika, 71, 599-607.
23.Soo, C.K. (2018), “Quantifying Sentiment with News Media across Local Housing Markets,” The Review of Financial Studies, 31, 3689-3719.
24.Wu, L. and E. Brynjolfsson (2015), “The Future of Prediction: How Google Searches Foreshadow Housing Prices and Sales,” NBER Chapters, Economic Analysis of the Digital Economy, 89-118, National Bureau of Economic Research.
25.Zhu, E.-W., J. Wu., H.-Y. Liu and K.-Y. Lia (2018), “A Sentiment Index of the Housing Market: Text Mining of Narratives on Social Media,” Tsinghua University, China.