Can Social Media Information Amplify Short-term Housing Price Changes? An Investigation in China’s Major Cities

Abstract

Human economic activities are inherently embedded in social networks. Nevertheless, whether social media information can affect short-term housing price changes, one of the most fundamental economic elements in modern economies, remains unclear. In this paper, we empirically investigate the effect of public expectations expressed on social media on the short-term housing price fluctuations of cities in China. The data were collected from Sina Weibo, one of the largest Twitter-like services in China. We first use a lexicon-based method to mine public expectations of housing price on Sina Weibo, and then use panel econometric models to empirically verify whether the public expectations on Sina Weibo can help more effectively explain short-term housing price changes of cities in China. Our results suggest that housing price expectations expressed on social media have a positive effect on housing price changes; that is, a 0.1 increase in bullish expectations on social media will result in a 0.2% increase in the housing price growth rate monthly but lagged by two months. The results are robust after additional tests. Our results are theoretically and empirically consistent with the findings of behavioural economics in emphasizing the importance of expectations and the failure of economic fundamentals in explaining the short-term changes of urban housing prices, which can not only shed light on the amplifying role of social media information on housing price changes, but also help investors use information technologies to assist their investment decision-makings.

Keywords

Social media / public expectations / housing price fluctuations / rational expectation theory

References

[1] AbdallaA M, CarabiasJ M. From accounting to economics: The role of aggregate special items in gauging the state of the economy. The Accounting Review, 2022, 97(1): 1-27

[2] AkpolatA G. The asymmetric effects of real variables on real housing prices: A nonlinear ARDL analysis for Turkey. International Journal of Housing Markets and Analysis, 2024, 17(3): 565-590

[3] AlhijawiB, AwajanA. Prediction of movie success using Twitter temporal mining. Proceedings of Sixth International Congress on Information and Communication Technology, 2022

[4] AntweilerW, FrankM Z. Is all that talk just noise? The information content of internet stock message boards. The Journal of Finance, 2004, 59(3): 1259-1294

[5] AtalayK, EdwardsR. House prices, housing wealth and financial well-being. Journal of Urban Economics, 2022, 129: 103438

[6] BaileyM, CaoR, KuchlerT, StroebelJ. The economic effects of social networks: Evidence from the housing market. Journal of Political Economy, 2018, 126(6): 2224-2276

[7] Baradaran M G, Zeng Z (2023). Housing market regimes and the macroeconomy: A nonlinear study of the effects of housing price shocks. Applied Economics 1–23.

[8] BartovE, FaurelL, MohanramP S. Can Twitter help predict firm-level earnings and stock returns?. The Accounting Review, 2018, 93(3): 25-57

[9] BhattV, KishorN K. Role of credit and expectations in house price dynamics. Finance Research Letters, 2022, 50: 103203

[10] BordaloP, GennaioliN, MaY, ShleiferA. Overreaction in macroeconomic expectations. American Economic Review, 2020, 110(9): 2748-2782

[11] BorkL, MllerS V, PedersenT Q. A new index of housing sentiment. Management Science, 2020, 66(4): 1563-1583

[12] BrooksM M. The changing landscape of affordable housing in the rural and urban United States, 1990–2016. Rural Sociology, 2022, 87(2): 511-546

[13] CaseK E, ShillerR J. The behavior of home buyers in boom and post-boom markets. Working Paper, 1988

[14] CaseK E, ShillerR J. Is there a bubble in the housing market?. Brookings Papers on Economic Activity, 2003, 2003(2): 299-362

[15] ChabakauriG, YuanK, ZachariadisK E. Multi-asset noisy rational expectations equilibrium with contingent claims. The Review of Economic Studies, 2022, 89(5): 2445-2490

[16] ChengY, DagsvikJ K, HanX. Real estate market policy and household demand for housing. Pacific Economic Review, 2014, 19(2): 237-253

[17] CuiH, WangG, LiY, WelschR E. Self-training method based on GCN for semi-supervised short text classification. Information Sciences, 2022, 611: 18-29

[18] DingY, LeeC, LuM. Does market sentiment push up China’s housing prices? An empirical study based on the data of 45 mainstream cities in China. Journal of Housing and the Built Environment, 2023, 38(2): 1119-1147

[19] FangJ, GozgorG, LauC K M, LuZ. The impact of Baidu Index sentiment on the volatility of China’s stock markets. Finance Research Letters, 2020, 32: 101099

[20] GeY, QiuJ, LiuZ, GuW, XuL. Beyond negative and positive: Exploring the effects of emotions in social media during the stock market crash. Information Processing & Management, 2020, 57(4): 102218

[21] GrandG, BlankI A, PereiraF, FedorenkoE. Semantic projection recovers rich human knowledge of multiple object features from word embeddings. Nature Human Behaviour, 2022, 6(7): 975-987

[22] GranovetterM. The impact of social structure on economic outcomes. Journal of Economic Perspectives, 2005, 19(1): 33-50

[23] HaqueM Z, QianA, HoqueM R, LuckyS A. A unified framework for exploring the determinants of online social networks (OSNs) on institutional investors’ capital market investment decision. Technology in Society, 2022, 70: 102061

[24] HongY, HuY, BurtchG. Embeddedness, prosociality, and social influence: Evidence from online crowdfunding. MIS Quarterly, 2018, 42(4): 1211-1224

[25] HowardG, LiebersohnJ. Regional divergence and house prices. Review of Economic Dynamics, 2023, 49: 312-350

[26] HuM, LiuB. Mining and summarizing customer reviews. Proceedings of the 10th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, 2004

[27] ImK S, PesaranM H, ShinY. Testing for unit roots in heterogeneous panels. Journal of Econometrics, 2003, 115(1): 53-74

[28] KampsJ, MarxM, MokkenR J, De RijkeM. Using WordNet to measure semantic orientations of adjectives. LREC, 2004, 2004: 1115-1118

[29] KimD Y, KimH Y. Trust me, trust me not: A nuanced view of influencer marketing on social media. Journal of Business Research, 2021, 134: 223-232

[30] KuchlerT, PiazzesiM, StroebelJ. Housing market expectations. Handbook of Economic Expectations, 2023

[31] LazziniA, LazziniS, BalluchiF, MazzaM. Emotions, moods and hyperreality: Social media and the stock market during the first phase of COVID-19 pandemic. Accounting, Auditing & Accountability Journal, 2022, 35(1): 199-215

[32] LepersE, ThiemannM. Taming the real estate boom in the EU: Pathways to macroprudential (in) action. Regulation & Governance, 2024, 18(2): 513-533

[33] LewbelA. Using heteroscedasticity to identify and estimate mismeasured and endogenous regressor models. Journal of Business & Economic Statistics, 2012, 30(1): 67-80

[34] LiJ, WangY, LiuC. Spatial effect of market sentiment on housing price: Evidence from social media data in China. International Journal of Strategic Property Management, 2022, 26(1): 72-85

[35] LiX, WuC, MaiF. The effect of online reviews on product sales: A joint sentiment-topic analysis. Information & Management, 2019, 56(2): 172-184

[36] LiY, ZhuD, ZhaoJ, ZhengX, ZhangL. Effect of the housing purchase restriction policy on the Real Estate Market: Evidence from a typical suburb of Beiing, China. Land Use Policy, 2020, 94: 104528

[37] LiuL, LeiM, WangH. Combining domain-specific sentiment lexicon with Hownet for Chinese sentiment analysis. Journal of Computers, 2013, 8(4): 878-884

[38] LiuX, YeQ. The different impacts of news-driven and self-initiated search volume on stock prices. Information & Management, 2016, 53(8): 997-1005

[39] LoewensteinL, WillenP SHouse Prices and Rents in the 21st Century (No. w31013), 2023

[40] MarcatoG, NandaA. Information content and forecasting ability of sentiment indicators: Case of real estate market. Journal of Real Estate Research, 2016, 38(2): 165-203

[41] MøllerS V, PedersenT, Montes SchütteE C, TimmermannA. Search and predictability of prices in the housing market. Management Science, 2024, 70(1): 415-438

[42] MunozS, IglesiasC A. A text classification approach to detect psychological stress combining a lexicon-based feature framework with distributional representations. Information Processing & Management, 2022, 59(5): 103011

[43] OustA, EidjordO M. Can Google search data be used as a housing bubble indicator?. International Real Estate Review, 2020, 23(2): 267-308

[44] PaulS, DasS. Investigating information dissemination and citizen engagement through government social media during the COVID-19 crisis. Online Information Review, 2023, 47(2): 316-332

[45] ShaoJ, HongJ, WangX, YanX. The relationship between social media sentiment and house prices in China: Evidence from text mining and wavelet analysis. Finance Research Letters, 2023, 57: 104212

[46] ShillerR J. Understanding recent trends in house prices and home ownership. Working Paper, 2007

[47] ShillerR J. Narrative economics. American Economic Review, 2017, 107(4): 967-1004

[48] TaboadaM, BrookeJ, TofiloskiM, VollK, StedeM. Lexicon-based methods for sentiment analysis. Computational Linguistics, 2011, 37(2): 267-307

[49] WuL, BrynjolfssonE. The future of prediction: How google searches foreshadow housing prices and sales. Economic Analysis of the Digital Economy, 201589-118

[50] WuJ, DengY. Intercity information diffusion and price discovery in housing markets: Evidence from Google searches. Journal of Real Estate Finance and Economics, 2015, 50(3): 289-306

[51] XuS X, ZhangX. Impact of Wikipedia on market information environment: Evidence on management disclosure and investor reaction. MIS Quarterly, 2013, 37(4): 1043-1068

[52] ZhaoK, HaoY B, WuW S. Asymmetric effect of monetary policy on housing price from short-term and long-term perspectives. Journal of Advanced Computational Intelligence and Intelligent Informatics, 2022, 26(4): 581-589

[53] ZhaoC, LiuF. Impact of housing policies on the real estate market - Systematic literature review. Heliyon, 2023, 9(10): e20704

RIGHTS & PERMISSIONS

Systems Engineering Society of China and Springer-Verlag GmbH Germany