Spatial analysis of Twitter sentiment and district-level housing prices

Abstract

Purpose Studies have shown a correlation and predictive impact of sentiment on asset prices, including Twitter sentiment on markets and individual stocks. This paper aims to determine whether there exists such a correlation between Twitter sentiment and property prices. Design/methodology/approach The authors construct district-level sentiment indices for every district of Istanbul using a dictionary-based polarity scoring method applied to a data set of 1.7 million original tweets that mention one or more of those districts. The authors apply a spatial lag model to estimate the relationship between Twitter sentiment regarding a district and housing prices or housing price appreciation in that district. Findings The findings indicate a significant but negative correlation between Twitter sentiment and property prices and price appreciation. However, the percentage of check-in tweets is found to be positively correlated with prices and price appreciation. Research limitations/implications The analysis is cross-sectional, and therefore, unable to answer the question of whether Twitter can Granger-cause changes in housing markets. Future research should focus on creation of a property-focused lexicon and panel analysis over a longer time horizon. Practical implications The findings suggest a role for Twitter-derived sentiment in predictive models for local variation in property prices as it can be observed in real time. Originality/value This is the first study to analyze the link between sentiment measures derived from Twitter, rather than surveys or news media, on property prices.

COVID-19 Vaccination: A Retrospective Observation and Sentiment Analysis of the Twitter Social Media Platform in Indonesia

“…In simple terms, data mining is the mining or discovery of new information by looking for certain patterns or rules from a very large amount of data [15]. Data mining is also referred to as a series of processes to explore added value in the form of knowledge that has not been known manually from a data set [16]. Data mining, also known as knowledge discovery in database (KDD).…”

“…According to Hannum [16] sentiment analysis or opinion mining refers to a broad field of natural language processing, computational linguistics and text mining which has the aim of analyzing opinions, sentiments, evaluations, attitudes, judgments and emotions of a person whether the speaker or writer relates to a topic, specific product, service, organization, individual or activity. In addition, the journal written by Hannum [16] explains that sentiment analysis is a field of study that analyzes a person's opinions, sentiments, evaluations, attitudes, and emotions from written language. Sentiment analysis is one of the most active research areas in natural language processing and is also widely studied in data mining, web mining, and text mining.…”

Sentiment Measurement and its Relationship with Housing Prices: Review of Contemporary Dimensions

“…However, the use of the stock market proxies developed by (Baker & Wurgler, 2007) to predict movements in asset prices is the chief among all other approaches used. Nontheless, twitter sentiment (Hannum, Arslanli, &Kalay, 2019 andGrover &Grover, 2014) are once a while use by some researchers but incomparable to the earlier one's mentioned. Please, refer to Note 1 for details on the summary of literature.…”

“…Heinig & Nanda, (2018) stated that in measuring sentiment, online search volume data gives a better result compared to the other approaches. In a spatial analysis of twitter sentiment in Turkey involving a data set of 1.7 million tweets (Hannum, Arslanli, & Kalay, 2019) posits that twitter sentiment have a significant negative relationship with house price appreciation. However, considering the percentage of check-in tweets few positive relationships were recorded.…”

Forecasting commercial real estate indicators under COVID-19 by adopting human activity using social big data

“…Another study investigates the correlation between housing prices and Twitter sentiment using 1.7 million original tweets mentioning 39 districts of İstanbul, and the results indicate that Twitter sentiment is negatively correlated. However, the percentage of check-in tweets are positively correlated with housing prices and price appreciation within the relevant districts (Hannum et al 2019 ). A similar study applies Twitter sentiment to housing prices in the U.S., and conversely, finds a positive correlation between them (Tan and Guan 2021 ).…”