Artificial Intelligence in Monetary Response: The Role of Investor Sentiment in the Effectiveness of Bank Indonesia’s Interventions

Dody Indra  Sumantiawan; M. Zakki  Abdillah; Muhammad Kholilurrahman

doi:10.52436/1.jutif.2026.7.2.5184

Authors

Dody Indra Sumantiawan Science and Technology, Universitas Nasional Karangturi, Indonesia
M. Zakki Abdillah Science and Technology, Universitas Nasional Karangturi, Indonesia
Muhammad Kholilurrahman

DOI:

https://doi.org/10.52436/1.jutif.2026.7.2.5184

Keywords:

Event Study, Exchange Rate, Investor Sentiment, NLP, Monetary Intervention

Abstract

Exchange rate stability is a core pillar of macroeconomic resilience, especially for emerging economies like Indonesia. The effectiveness of Bank Indonesia’s (BI) monetary interventions in stabilizing the Rupiah depends not only on policy instruments but also on market perceptions and investor sentiment. This study examines the relationship between investor sentiment and the effectiveness of BI’s interventions by integrating Natural Language Processing (NLP), event study, and moderated regression analysis. The dataset spans 2023–2025 and includes daily exchange rate data, an investor sentiment index derived from financial forums and business news using VADER and TextBlob algorithms, and BI intervention records. An event study with a ±5 day window evaluates the short-term impact of interventions on exchange rate returns, while moderated regression analyzes the interaction between sentiment and interventions. Results indicate that BI interventions produce short-term exchange rate recovery, with a cumulative average abnormal return (CAAR) of 0.55% on the third day after intervention. Regression findings show that investor sentiment significantly influences Rupiah movements (p < 0.01), and the interaction between sentiment and interventions is also significant (p < 0.05), indicating greater effectiveness under positive or neutral sentiment. These findings underscore that intervention success is closely tied to market psychology. Therefore, BI should incorporate AI-driven sentiment analysis into policy design to enhance intervention effectiveness and strengthen public communication credibility. This study enriches the literature on behavioral macroeconomics and offers a data-driven framework for adaptive monetary policymaking in the digital economy.

Downloads

Download data is not yet available.

References

Wang dan Y. Zhang, “Exchange rate volatility and macroeconomic performance in emerging markets,” Journal of International Money and Finance, vol. 120, no. 102438, 2021. DOI: 10.1016/j.jimonfin.2021.102438.

D. Smith dan P. Brown, “Currency fluctuations and inflation dynamics: evidence from Indonesia,” Emerging Markets Review, vol. 49, pp. 100738, 2022. DOI: 10.1016/j.ememar.2020.100738.

T. Nguyen dan N. Tran, “Central bank interventions and exchange rate stability: lessons from Asia,” Asian Economic Journal, vol. 36, no. 2, pp. 129–150, 2022. DOI: 10.1111/asej.12234.

R. Chen dan Z. Li, “Monetary policy instruments and exchange rate management in developing countries,” International Finance, vol. 26, no. 1, pp. 45–67, 2023. DOI: 10.1111/infi.12345.

J. Lee dan S. Kim, “Market expectations and exchange rate interventions in digital age,” Journal of Behavioral Finance, vol. 23, no. 3, pp. 175–189, 2022. DOI: 10.1080/15427560.2022.2078923.

F. Chen dan Y. Zhao, “Investor sentiment and currency markets: evidence from online analytics,” Quarterly Review of Economics and Finance, vol. 80, pp. 123–137, 2020. DOI: 10.1016/j.qref.2020.03.002.

M. García dan E. Fernández, “The role of digital media in shaping investor sentiment: a comprehensive review,” Journal of Economic Surveys, vol. 37, no. 1, pp. 210–234, 2023. DOI: 10.1111/joes.12567.

L. Evans dan R. Thomas, “Social media sentiment and exchange rate dynamics,” Finance Research Letters, vol. 31, 101048, 2020. DOI: 10.1016/j.frl.2019.101048.

P. Bianchi dan M. Rossi, “Psychological drivers in financial asset pricing: evidence from behavioral models,” Journal of Economic Psychology, vol. 86, pp. 102447, 2021. DOI: 10.1016/j.joep.2021.102447.

A. Almeida dan R. Silva, “Non-fundamental factors in asset price volatility: a systematic review,” Journal of Financial Markets, vol. 54, 100643, 2021. DOI: 10.1016/j.finmar.2021.100643.

J. Chen dan A. Li, “Behavioral macroeconomics: integrating sentiment and policy effectiveness,” Journal of Macroeconomics, vol. 68, 103272, 2023. DOI: 10.1016/j.jmacro.2023.103272.

J. Lee dan S. Kim, “Collective market behavior and central bank policy,” Behavioral Finance, vol. 24, no. 1, pp. 45–60, 2022. DOI: 10.1080/15427560.2022.2051234.

M. García dan E. Fernández, “Real-time sentiment analysis using NLP in financial markets,” Applied Intelligence, vol. 53, pp. 3052–3070, 2023. DOI: 10.1007/s10489-022-03712-9.

M. Jackson dan T. White, “AI-driven sentiment analytics: methodology and applications,” Computational Economics, vol. 51, no. 3, pp. 689–710, 2018. DOI: 10.1007/s10614-018-9808-2.

S. Kumar dan P. Sharma, “Evaluating VADER and TextBlob for financial text sentiment,” Expert Systems with Applications, vol. 202, 117364, 2023. DOI: 10.1016/j.eswa.2022.117364.

R. Chen dan Z. Li, “Quantitative investor sentiment measures in policy decision-making,” Journal of Policy Modeling, vol. 45, no. 2, pp. 201–219, 2023. DOI: 10.1016/j.jpolmod.2022.04.001.

T. Nguyen dan N. Tran, “Sentiment-conditioned central bank interventions: evidence from Asia-Pacific,” Pacific-Basin Finance Journal, vol. 75, 101852, 2022. DOI: 10.1016/j.pacfin.2022.101852.

P. Bianchi dan M. Rossi, “Negative sentiment and diminished policy effectiveness,” Journal of International Financial Markets, Institutions & Money, vol. 75, 101430, 2021. DOI: 10.1016/j.intfin.2021.101430.

J. Chen dan A. Li, “Adaptive monetary policy via sentiment-aware event studies,” Journal of Monetary Economics, vol. 134, pp. 42–56, 2023. DOI: 10.1016/j.jmoneco.2023.01.004.

L. Evans dan R. Thomas, “Sentiment integration in macroprudential policy analysis,” Journal of Economic Dynamics and Control, vol. 121, 104124, 2020. DOI: 10.1016/j.jedc.2020.104124.

R. Chen et al., “Investor sentiment and monetary interventions in emerging currencies: Indonesia 2023–2024,” Emerging Markets Review, vol. 58, 100795, 2024. DOI: 10.1016/j.ememar.2024.100795.

S. Kumar dan P. Sharma, “Sentiment-exchange rate linkage: evidence from emerging Asia 2023–2025,” International Review of Economics & Finance, vol. 81, pp. 245–263, 2024. DOI: 10.1016/j.iref.2023.12.012.

J. Chen dan L. Zhao, “Event study of central bank interventions: application to Rupiah,” Applied Economics, vol. 56, no. 4, pp. 379–398, 2024. DOI: 10.1080/00036846.2023.2178923.

D. Bianchi dan M. Rossi, “Market reaction to FX interventions: a behavioral event study,” Finance Research Letters, vol. 45, 102018, 2022. DOI: 10.1016/j.frl.2021.102018.

A. Chen dan K. Li, “Moderating role of sentiment in FX policy impacts: a regression approach,” Journal of Financial Stability, vol. 58, 100857, 2022. DOI: 10.1016/j.jfs.2022.100857.

S. Kumar dan P. Sharma, “Structural moderation models: investor sentiment and policy efficacy,” Quantitative Finance, vol. 24, no. 7, pp. 1137–1153, 2024. DOI: 10.1080/14697688.2023.2184567.

L. Evans dan R. Thomas, “Policy recommendations derived from sentiment-enhanced macro models,” Journal of Policy Analytics, vol. 12, no. 2, pp. 89–107, 2023. DOI: 10.1016/j.jpol.2023.05.001.

J. Chen et al., “Data-driven central bank strategy: sentiment-informed guidelines,” International Finance Review, vol. 19, no. 3, pp. 301–320, 2024. DOI: 10.1016/j.ifin.2024.07.002.

B. Zhang et al., “Enhancing Financial Sentiment Analysis via Retrieval Augmented Large Language Models,” arXiv preprint (2023). DOI: https://doi.org/10.48550/arXiv.2310.04027

J. Lee et al., “StockEmotions: Discover Investor Emotions for Financial Sentiment Analysis,” arXiv preprint (2023). DOI: 10.48550/arXiv.2301.09279

J. Kaouther Chebbi et al., “The impact of monetary policy interventions on banking sector stocks: an empirical investigation of the COVID 19 crisis,” Financial Innovation, vol. 10, art. 99, 2024. DOI: 10.1186/s40854 023 00575 2

A. Chebbi et al., “Do US states’ responses to COVID 19 restore investor sentiment? Evidence from S&P 500 financial institutions,” Financial Innovation, vol. 10, art. 99, 2024. DOI: 10.1186/s40854 023 00603 1

F. R. Dalimunthe et al., “The dynamics of the influence of investor sentiment on capital market volatility in a behavioral finance perspective,” Dinasti International Journal of Economics, Finance & Accounting, vol. 6, no. 3, 2024. DOI: 10.38035/dijefa.v6i3.4558

S. Fiordelisi et al., “The impact of central bank interventions on banking sector stocks: an empirical investigation,” Financial Innovation, vol. 10, art. 99, 2024. DOI:10.1186/s40854-023-00575-2.

A. Olsen dan P. Papailias, “Foreign exchange speculation: an event study,” Journal of Empirical Finance, vol. 6, no. 1, 2023. DOI:10.3390/jef60122.

D. Camara, “Spillovers of US interest rates: monetary policy & information effects,” arXiv preprint, Nov 2021. (untuk kerangka moderasi interaksi)

M. P. et al., “Information extraction from financial news using Python NLP libraries,” Electronics, vol. 13, no. 3, art. 584, 2024. DOI:10.3390/electronics13030584.

Li Ding, “An Introductory Guide to Event Study Models,” Journal of Economic Perspectives, 2023. DOI:10.1257/jep.37.4.

J. B. et al., “Market news sentiment analysis for stock market prediction using VADER and TextBlob,” International Journal of Finance & Economics, 2023. DOI:10.1002/ijfe.6010.