Making use of recent trends within our social lives, internet data sources are used to get information about the sentiment of market participants. So far, current academic research is applying “Google Trends” to investigate what people are searching for on the internet on a weekly basis. The consequential results, mostly a sentiment indicator, are tested with respect to their predictive power on real estate market movements. 

This paper wants to begin one stage earlier, by examining the information people get on the internet and perform a daily analysis. This study analyzes, if real estate related news or Twitter posts do reflect, cause or enhance market performance in the real estate sector.

For this purpose, real estate related news from renowned newspapers as well as posts from Twitter are collected as a representative data basis. Following the approach of Bollen et al. (2009), sentiment analysis is applied with a term based methodology, by counting words that indicate positive or negative sentiment derived from different research approaches. Moreover, this dictionary-based methodology will be supplemented by and compared to the results of a machine learning tool, the “Google Prediction API”. In consequence, qualitative information from news stories and posts are converted into a quantifiable measure achieved by analyzing the positive and negative tone of the information.

The created sentiment measure is tested on its explanatory power for market movements on the U.S. real estate securities market. Therefore, the FTSE EPRA/NAREIT and GPR 250 indices are collected on a daily basis over the same time period and tested against the innovative sentiment index. 

To the best of our knowledge, this is the first research work applying textual analysis to capture sentiment on the real estate market. The practical and theoretical implication of this work is to generate a real estate sentiment index, which is able to explain and possibly predict real estate market movements.