社群大數據－重建消費者信心指標於大台北房市需求預測

Sales Forecast for Taipei House Markets-Based on Social Listening

黃紹軒(Shao-Hsuan Huang)

指導教授 ： 任立中

國立臺灣大學/管理學院/國際企業學研究所/碩士(2019年)

https://doi.org/10.6342/NTU201900040

摘要

在這人手一隻智慧型手機的年代，以臉書為首等其他的社群網站篷勃發展，一般大眾早已習慣上網獲取新聞與發表意見。議題除了一般的生活大小事，最近期的著名案例還包括2014年的台北市長選戰，候選人透過網路而非傳統的選戰方式進行政策宣傳與累積人氣。而這些社群言論經過整理與分析後成了近幾年廣為人知的「網路聲量」。

本研究透過意藍資訊的Opview社群口碑資料庫，試著建構出網路上的消費者信心聲量，並且與中央大學透過問卷所進行的結果進行比較，希望透過網路上真實且即時的社群意見來反應消費者對於未來經濟的感受。

透過大台北的房屋交易量當成我們了解消費者對耐久財的購買意願，我們比較傳統透過問卷所得到的消費者信心指數與社群聆聽所得到的網路聲量，來測試何者較能反映出實際的解釋與預測能力。而本研究結果顯示消費者信心聲量對於大台北的房屋需求具有領先5個月的預測能力，而網路聲量又比消費者信心指數更來得有解釋及預測能力。也因此對企業與政府而言，如何將消費者在社群的意見與反應轉換成實際增收與改善策略的依據更顯重要。

關鍵字

網路聲量 ； 社群聆聽 ； 消費者信心指數 ； 耐久財 ； 房市

並列摘要

In the era of smartphones, it’s common people get news and comment on social media. And these opinions may even affect elections. The most famous example is in Taipei City’s mayor election of 2014. Candidates launched their policies and earned popularity through internet rather than traditional ways. Therefore, those comments on social media could be analyzed and arranged to “Internet Sentiments”.

By applying Opview’s database, we tried to build consumers’ Confidence Sentiment Index. Then we compared to the survey method of Consumer Confidence Index which is conducted by National Central University. To understand which indicators can better explain and predict people’s willingness of buying durable goods, we refer Taipei’s houses markets as the proxy variable. The research findings indicate that: (1) Consumer Confidence Sentiments can well predict the demand of Taipei houses selling five months beforehand. (2) Consumer Confidence Sentiments generally out-perform Consumer Confidence Index in predicting and explaining Taipei’s houses demand. (3) Consumer Confidence Sentiments can serve as leading indicator or reference for government or corporates.

並列關鍵字

Internet sentiments ； social listening ； consumer confidence ； durable goods ； houses market

參考文獻

1. Allenby, Greg M., L. Jen, and R. P. Leone (1996) , “Economic Trends and Being Trendy：The Influence of Consumer Confidence on Retail Fashion Sales”, Journal of Business & Economic Statistics, Vol.14, No.1, p.103-111.

2. Choi, H., & Varian, H. (2012) “Predicting the present with Google Trends”, Economic Record, 88(s1), 2–9.

3. Schmidt, T., & Simeon, V. (2009). “Forecasting Private Consumption: Survey-based Indicators vs. Google Trends. Journal of Forecasting”, Vol. 30, No. 6, Ruhr economic papers, No. 155, 565-578.

4. Nick McLaren (2011), “Using internet search data as economic indicators”, Bank’s Conjunctural Assessment and Projections Division and Rachana Shanbhogue of the Bank’s Structural Economic Analysis Division

5. 黃舜卿（2008）。我國消費者信心指數與民間消費支出之研究經濟研究。經濟研究，（8），121-158。