A Sentiment Index of the Housing Market: Text Mining of Narratives on Social Media

Abstract

Many efforts have been made to measure investor sentiment in financial markets, but only a few studies focus on housing markets. We build sentiment indexes for the Chinese housing market while observing that house price narratives are abundantly documented on social media. With the help of cutting-edge text analysis techniques from the deep learning and natural language processing fields, our indexes provide a solid basis for understanding the semantic meanings of textual data. Highlighting the temporality of text, we build separate future and past sentiment indexes to capture people’s prior beliefs and posterior feelings about price movements, respectively. The future sentiment index could serve as an alternative to survey-based expectations, measure the impacts of policies on people’s beliefs, and have remarkable power in predicting the future movements of both house prices and listed developers’ stock prices.

Keywords: Investor sentiment, Narrative economics, Housing market, Text mining, Social media, Deep learning