Does investor interaction on social media influence financial market volatility? A text-based network analysis of CSI 300 constituents

Zhongxiu Chen; Zhenghui Li; Zhongxiu Chen; Zhenghui Li

doi:10.3934/DSFE.2026021

Data Science in Finance and Economics

2026, Volume 6, Issue 4: 595-621. doi: 10.3934/DSFE.2026021

Previous Article Next Article

Research article

Does investor interaction on social media influence financial market volatility? A text-based network analysis of CSI 300 constituents

Zhongxiu Chen ¹,
Zhenghui Li ^{1,2
,
,}

1.
School of Economics and Statistics, Guangzhou University, Guangzhou, 510000, China
2.
Guangzhou Institute of International Finance, Guangzhou University, Guangzhou, 510000, China

Received: 12 March 2026 Revised: 04 June 2026 Accepted: 17 July 2026 Published: 05 November 2026
JEL Codes: G14, G12, D85

The advancement of information technology and the widespread adoption of social media have accelerated information exchange among investors. This study investigated the impact of investor-driven information flow on financial market volatility. We collected 5,258,185 comments from the Eastmoney Stock Forum covering the CSI 300 constituent stocks between June 1, 2023, and May 31, 2024, and constructed 48 weekly investor-driven information flow networks. Using panel data comprising 14,400 firm-week observations and regression analysis, we found that market volatility responds significantly to the structural properties of these networks. Firms with higher network centrality experience a 1.3% increase in return volatility and a 17.1% rise in trading volume. While volatility declines over time (−8.4%), trading activity remains higher (34.5%). We further confirmed that network centrality drives greater message activity and promotes opinion convergence, supporting two mechanisms: prompt information incorporation and consensus formation. These insights contribute to a deeper understanding of the mechanisms through which information networks on social media shape market dynamics.
- investor interaction,
- information flow network,
- social media,
- financial market volatility,
- trading behavior
Citation: Zhongxiu Chen, Zhenghui Li. Does investor interaction on social media influence financial market volatility? A text-based network analysis of CSI 300 constituents[J]. Data Science in Finance and Economics, 2026, 6(4): 595-621. doi: 10.3934/DSFE.2026021

Related Papers:

Abstract

The advancement of information technology and the widespread adoption of social media have accelerated information exchange among investors. This study investigated the impact of investor-driven information flow on financial market volatility. We collected 5,258,185 comments from the Eastmoney Stock Forum covering the CSI 300 constituent stocks between June 1, 2023, and May 31, 2024, and constructed 48 weekly investor-driven information flow networks. Using panel data comprising 14,400 firm-week observations and regression analysis, we found that market volatility responds significantly to the structural properties of these networks. Firms with higher network centrality experience a 1.3% increase in return volatility and a 17.1% rise in trading volume. While volatility declines over time (−8.4%), trading activity remains higher (34.5%). We further confirmed that network centrality drives greater message activity and promotes opinion convergence, supporting two mechanisms: prompt information incorporation and consensus formation. These insights contribute to a deeper understanding of the mechanisms through which information networks on social media shape market dynamics.

References

[1]	Albery GF, Bansal S, Silk MJ (2024) Comparative approaches in social network ecology. Ecol Lett 27: e14345. https://doi.org/ 10.1111/ele.14345 doi: 10.1111/ele.14345
[2]	Alinaghian L, Qiu J, Razmdoost K (2021) The role of network structural properties in supply chain sustainability: A systematic literature review and agenda for future research. Supply Chain Manag 26: 192–211. https://doi.org/ 10.1108/SCM-11-2019-0407 doi: 10.1108/SCM-11-2019-0407
[3]	An J, Mikhaylov A, Chang T (2024) Relationship between the popularity of a platform and the price of NFT assets. Financ Res Lett 61: 105057. https://doi.org/ 10.1016/j.frl.2024.105057 doi: 10.1016/j.frl.2024.105057
[4]	Ang A, Hodrick RJ, Xing Y, et al. (2006) The cross-section of volatility and expected returns. J Financ 61: 259–299. https://doi.org/ 10.1111/j.1540-6261.2006.00836.x doi: 10.1111/j.1540-6261.2006.00836.x
[5]	Ayala MJ, Gonzálvez-Gallego N, Arteaga-Sánchez R (2024) Google search volume index and investor attention in stock market: A systematic review. Financ Innov 10: 70. https://doi.org/ 10.1186/s40854-023-00606-y doi: 10.1186/s40854-023-00606-y
[6]	Bahari NN, Bahaludin H, Ismail M, et al. (2024) Network, correlation, and community structure of the financial sector of Bursa Malaysia before, during, and after COVID-19. Data Sci Financ Econ 4: 362–387. https://doi.org/ 10.3934/DSFE.2024016 doi: 10.3934/DSFE.2024016
[7]	Bellemare MF, Masaki T, Pepinsky TB (2017) Lagged explanatory variables and the estimation of causal effect. J Poli 79: 949–963. https://doi.org/ 10.1086/690946 doi: 10.1086/690946
[8]	Benkraiem R, Goutte S, Saadi S, et al. (2022) Investor heterogeneity and negative skewness in stock returns: Evidence from institutional investors. J Int Financ Mark Institutions and Money 81: 101690. https://doi.org/ 10.1016/j.intfin.2022.101690 doi: 10.1016/j.intfin.2022.101690
[9]	Bi J, Jin J, Qu C, et al. (2021) Temporal gravity model for important node identification in temporal networks. Chaos Soliton Fract 147: 110934. https://doi.org/ 10.1016/j.chaos.2021.110934 doi: 10.1016/j.chaos.2021.110934
[10]	Chen X, An L, Wang Z, et al. (2023) Attention spillover in asset pricing. J Financ 78: 3515–3559. https://doi.org/ 10.1111/jofi.13281 doi: 10.1111/jofi.13281
[11]	Chen Z, Tian H, Li Z (2026) Online monitoring of financial market information-flow networks under external shocks: A rolling directed-ERGM and control-chart framework. Mathematics 14: 961. https://doi.org/ 10.3390/math14060961 doi: 10.3390/math14060961
[12]	Chen Z, Yin J (2025) Detecting jumps in stochastic volatility jump-diffusion models via the power variation approach. AIMS Mathematics 10: 19189–19216. https://doi.org/ 10.3934/math.2025858 doi: 10.3934/math.2025858
[13]	Cookson JA, Lu R, Mullins W, et al. (2024) The social signal. J Financ Econ 158: 103870. https://doi.org/ 10.1016/j.jfineco.2024.103870 doi: 10.1016/j.jfineco.2024.103870
[14]	Du Q, Kwaramba CS, Li C, et al. (2023) A contest between users and marketers? The economic value of social media content for adverse events. Inform Process Manag 60: 103496. https://doi.org/ 10.1016/j.ipm.2023.103496 doi: 10.1016/j.ipm.2023.103496
[15]	Fedyk A (2024) Front-page news: The effect of news positioning on financial markets. J Financ 79: 5–33. https://doi.org/ 10.1111/jofi.13287 doi: 10.1111/jofi.13287
[16]	Ge S, Li S, Zheng H (2025) Diamond cuts diamond: News co-mention momentum spillover prevails in China. J Bank Financ 171: 107356. https://doi.org/ 10.1016/j.jbankfin.2024.107356 doi: 10.1016/j.jbankfin.2024.107356
[17]	Han B, Yang L (2013) Social networks, information acquisition, and asset prices. Manage Sci 59: 1444–1457. https://doi.org/ 10.1287/mnsc.1120.1678 doi: 10.1287/mnsc.1120.1678
[18]	Harvey CR, Mazzoleni MG, Melone A (2025) The unintended consequences of rebalancing. NBER Working Paper No. 33554. https://doi.org/10.3386/w33554
[19]	Hirshleifer D, Peng L, Wang Q (2025) News diffusion in social networks and stock market reactions. Rev Financ Stud 38: 883–937. https://doi.org/ 10.1093/rfs/hhae025 doi: 10.1093/rfs/hhae025
[20]	Huang C, Cao Y, Lu M, et al. (2023) Messages in online stock forums and stock price synchronicity: Evidence from China. Account Financ 63: 3011–3041. https://doi.org/ 10.1111/acfi.13005 doi: 10.1111/acfi.13005
[21]	Huang Y, Li Y, Li P, et al. (2025) The unseen guardian: News co-mention and stock market manipulation. Financ Res Lett 86: 108648. https://doi.org/ 10.1016/j.frl.2025.108648 doi: 10.1016/j.frl.2025.108648
[22]	Hutton AP (2005) Determinants of managerial earnings guidance prior to regulation fair disclosure and bias in analysts' earnings forecasts. Contemp Account Res 22: 867–914. https://doi.org/ 10.1506/6QUR-CR5M-AQQX-KX1A doi: 10.1506/6QUR-CR5M-AQQX-KX1A
[23]	Irshad AS, Zakir MN, Rashad SS, et al. (2024) Comparative analyses and optimizations of hybrid biomass and solar energy systems based upon a variety of biomass technologies. Energ Convers Man-X 23: 100640. https://doi.org/ 10.1016/j.ecmx.2024.100640 doi: 10.1016/j.ecmx.2024.100640
[24]	Jiang Z, Liu H, Peng C, et al. (2025) Investor memory and biased beliefs: Evidence from the field. Q J Econ 140: 2749–2804. https://doi.org/ 10.1093/qje/qjaf035 doi: 10.1093/qje/qjaf035
[25]	Leszczensky L, Wolbring T (2022) How to deal with reverse causality using panel data? Recommendations for researchers based on a simulation study. Sociol Method Res 51: 837–865. https://doi.org/ 10.1177/0049124119882473 doi: 10.1177/0049124119882473
[26]	Li Z, Chen Z, Huang Z (2026) Modelling the data-generating mechanism of China's commodity market by identifying hidden information flow regimes. Financ Innov 12: 28. https://doi.org/ 10.1186/s40854-025-00804-w doi: 10.1186/s40854-025-00804-w
[27]	Liang Z, Ye Q (2024) Despite absolute information advantages, all investors incur welfare loss. arXiv preprint arXiv: 2405.08822. https://doi.org/10.48550/arXiv.2405.08822
[28]	Liao G, Li Y, Wang M (2024) Contagion network of idiosyncratic volatility: Does corporate environmental responsibility matter? Energy Econ 129: 107168. https://doi.org/ 10.1016/j.eneco.2023.107168 doi: 10.1016/j.eneco.2023.107168
[29]	Luo R, Zhao S, Zhou J (2023) Information network, public disclosure and asset prices. Pac-Basin Financ J 77: 101882. https://doi.org/ 10.1016/j.pacfin.2022.101882 doi: 10.1016/j.pacfin.2022.101882
[30]	Messaoud D, Ben Amar A, Boujelbene Y (2023) Investor sentiment and liquidity in emerging stock markets. J Econom Adm Sci 39: 867–891. https://doi.org/ 10.1108/JEAS-11-2020-0198 doi: 10.1108/JEAS-11-2020-0198
[31]	Mikhaylov A (2021) Development of Friedrich von Hayek's theory of private money and economic implications for digital currencies. Terra Econ 19: 53–62. https://doi.org/ 10.18522/2073-6606-2021-19-1-53-62 doi: 10.18522/2073-6606-2021-19-1-53-62
[32]	Mikhaylov A, Bhatti IM, Dinçer H, et al. (2024) Integrated decision recommendation system using iteration-enhanced collaborative filtering, golden cut bipolar for analyzing the risk-based oil market spillovers. Comput Econ 63: 305–338. https://doi.org/ 10.1007/s10614-022-10341-8 doi: 10.1007/s10614-022-10341-8
[33]	Mikhaylov A, Dinçer H, Yüksel S, et al. (2023) Bitcoin mempool growth and trading volumes: Integrated approach based on QROF Multi-SWARA and aggregation operators. J Innov Knowl 8: 100378. https://doi.org/ 10.1016/j.jik.2023.100378 doi: 10.1016/j.jik.2023.100378
[34]	Nguyen MT, Meesad P, Nguyen HS (2024) On a stock prediction aligned to natural language sentiments. In: Proceedings of the 2024 8th International Conference on Natural Language Processing and Information Retrieval, 395–400. https://doi.org/10.1145/3711542.3711597
[35]	Ortega-Rodríguez C, Vena-Oya J, Barreal J, et al. (2024) How to finance sustainable tourism: Factors influencing the attitude and willingness to pay green taxes among university students. Green Financ 6: 649–665. https://doi.org/ 10.3934/GF.2024025 doi: 10.3934/GF.2024025
[36]	Ozsoylev HN, Walden J (2011) Asset pricing in large information networks. J Econ Theor 146: 2252–2280. https://doi.org/ 10.1016/j.jet.2011.10.003 doi: 10.1016/j.jet.2011.10.003
[37]	Ozsoylev HN, Walden J, Yavuz MD, et al. (2014) Investor networks in the stock market. Rev Financ Stud 27: 1323–1366. https://doi.org/ 10.1093/rfs/hht065 doi: 10.1093/rfs/hht065
[38]	Qian H, Zhou H, Zhao Q, et al. (2024) MDGNN: Multi-relational dynamic graph neural network for comprehensive and dynamic stock investment prediction. Proceedings of the AAAI Conference on Artificial Intelligence 38: 14642–14650. https://doi.org/ 10.1609/aaai.v38i13.29381 doi: 10.1609/aaai.v38i13.29381
[39]	Reichenbach F, Walther M (2025) Attention allocation of investors on social media: The role of prospect theory. J Behav Financ 26: 317–334. https://doi.org/ 10.1080/15427560.2024.2309145 doi: 10.1080/15427560.2024.2309145
[40]	Rossi AG, Blake D, Timmermann A, et al. (2018) Network centrality and delegated investment performance. J Financ Econ 128: 183–206. https://doi.org/ 10.1016/j.jfineco.2018.02.003 doi: 10.1016/j.jfineco.2018.02.003
[41]	Schwenkler G, Zheng H (2025) News-driven peer co-movement in crypto markets. J Corp Financ 93: 102772. https://doi.org/ 10.1016/j.jcorpfin.2025.102772 doi: 10.1016/j.jcorpfin.2025.102772
[42]	Shaikh ZA, Kraikin A, Mikhaylov A, et al. (2022) Forecasting stock prices of companies producing solar panels using machine learning methods. Complexity 2022: 9186265. https://doi.org/ 10.1155/2022/9186265 doi: 10.1155/2022/9186265
[43]	Shi Y, Wang Y, Qu Y, et al. (2024) Integrated GCN-LSTM stock prices movement prediction based on knowledge-incorporated graphs construction. Int J Mach Learn Cybern 15: 161–176. https://doi.org/ 10.1007/s13042-023-01817-6 doi: 10.1007/s13042-023-01817-6
[44]	Szczygielski JJ, Charteris A, Bwanya PR, et al. (2024) Google search trends and stock markets: Sentiment, attention or uncertainty? Int Rev Financ Anal 91: 102549. https://doi.org/ 10.1016/j.irfa.2023.102549 doi: 10.1016/j.irfa.2023.102549
[45]	Vamossy DF (2026) Social media emotions and market behavior. Int Rev Financ Anal 114: 105162. https://doi.org/ 10.1016/j.irfa.2026.105162 doi: 10.1016/j.irfa.2026.105162
[46]	Vozlyublennaia N (2013) Do firm characteristics matter for the dynamics of idiosyncratic risk? J Int Financ Mark Inst Money 27: 35–46. https://doi.org/ 10.1016/j.intfin.2013.07.006 doi: 10.1016/j.intfin.2013.07.006
[47]	Walden J (2019) Trading, profits, and volatility in a dynamic information network model. Rev Econ Stud 86: 2248–2283. https://doi.org/ 10.1093/restud/rdy058 doi: 10.1093/restud/rdy058
[48]	Wang J, Liao L, Zhong K, et al. (2025) MRRFGNN: Multi-relation reconstruction and fusion graph neural network for stock crash prediction. Inform Sci 689: 121507. https://doi.org/ 10.1016/j.ins.2024.121507 doi: 10.1016/j.ins.2024.121507
[49]	Wang LH (2018) Which firm characteristics affect foreign analyst coverage? Evidence from the Taiwan stock market. J Math Financ 8: 64–85. https://doi.org/ 10.4236/jmf.2018.81006 doi: 10.4236/jmf.2018.81006
[50]	Wang MC, Chang T, Mikhaylov A, et al. (2024) A measure of quantile-on-quantile connectedness for the US treasury yield curve spread, the US Dollar, and gold price. North Am J Econ Financ 74: 102232. https://doi.org/ 10.1016/j.najef.2024.102232 doi: 10.1016/j.najef.2024.102232
[51]	Warkulat S, Pelster M (2024) Social media attention and retail investor behavior: Evidence from r/wallstreetbets. Int Rev Financ Anal 96: 103721. https://doi.org/ 10.1016/j.irfa.2024.103721 doi: 10.1016/j.irfa.2024.103721
[52]	Wen T, Chen YW, Syed TA, et al. (2025) Examining communication network behaviors, structure and dynamics in an organizational hierarchy: A social network analysis approach. Inform Process Manag 62: 103927. https://doi.org/ 10.1016/j.ipm.2024.103927 doi: 10.1016/j.ipm.2024.103927
[53]	Xu Z, Du Z, Cheng Q, et al. (2024) Institutional investor information networks and stock price synchronicity. Emerg Mark Financ Trade 60: 3559–3573. https://doi.org/ 10.1080/1540496X.2024.2354803 doi: 10.1080/1540496X.2024.2354803
[54]	Ying J (2024) Gradual information diffusion across commonly owned firms. J Financ Econ 156: 103852. https://doi.org/ 10.1016/j.jfineco.2024.103852 doi: 10.1016/j.jfineco.2024.103852
[55]	Yu M, Hu X, Zhong A (2024) Network centrality, information diffusion and asset pricing. Int Rev Financ Anal 93: 103223. https://doi.org/ 10.1016/j.irfa.2024.103223 doi: 10.1016/j.irfa.2024.103223
[56]	Yu X, Nie Y, Li W, et al. (2024) Key nodes of misinformation source inference: A message-passing-based approach. Int J Mod Phys C 35: 2450146. https://doi.org/ 10.1142/S0129183124501468 doi: 10.1142/S0129183124501468
[57]	Zhai X, Ma H, Zhang Y, et al. (2024) Institutional investor network and idiosyncratic volatility of stocks. Econ Polit 36: 1261–1288. https://doi.org/ 10.1111/ecpo.12289 doi: 10.1111/ecpo.12289
[58]	Zhang Z, Luo Q (2024) Retail investor attention and analyst earnings forecasts: Evidence from China. Pac-Basin Financ J 83: 102238. https://doi.org/ 10.1016/j.pacfin.2023.102238 doi: 10.1016/j.pacfin.2023.102238
[59]	Zhao X, Zhang Y, Zhai Q, et al. (2024) A multi-attribute decision-making approach for critical node identification in complex networks. Entropy 26: 1075. https://doi.org/ 10.3390/e26121075 doi: 10.3390/e26121075
[60]	Zhu M, Liang Y, Wu Z (2020) Internet information interaction networks and stock price crash risk: Public opinion supervision or irrational contagion. China Ind Econ 2020: 81–99. https://doi.org/10.19581/j.cnki.ciejournal.2020.10.003 doi: 10.19581/j.cnki.ciejournal.2020.10.003

Reader Comments

Your name:*

Email:*
© 2026 the Author(s), licensee AIMS Press. This is an open access article distributed under the terms of the Creative Commons Attribution License (http://creativecommons.org/licenses/by/4.0)