Bitcoin Trend Prediction Using Bitcoin Influence Index Weighted Sentiment and Hybrid Ensemble Learning

Akhlis Munazilin, Mochamad Agung Wibowo, Rizky Parlika
Pages 2679-2690
Abstract Views 23
PDF Downloads 15
Crossref Citations -
DOI https://doi.org/10.47738/jads.v7i4.1322

Abstract


Predicting Bitcoin trends is a complex problem because market movements are influenced not only by historical data and technical indicators but also by sentiment and rapidly evolving information disseminated through social media. Previous studies have shown that sentiment information can improve cryptocurrency prediction; however, most approaches aggregate opinions without explicitly distinguishing the characteristics of their information sources. This study develops the Bitcoin Influence Index (BII) as a multidimensional representation of social media account influence based on four dimensions: Reach Influence, Credibility Influence, Activity Influence, and Content Influence. BII is integrated with FinBERT based sentiment analysis to construct BII weighted sentiment, which is subsequently transformed into temporal features through lag, rolling average, momentum, interaction, and shock measures. Next day Bitcoin direction is predicted using a hybrid ensemble that combines XGBoost, Long Short-Term Memory (LSTM), and Gated Recurrent Unit (GRU) as base learners, with Logistic Regression as the meta learner. The experiment compares two scenarios, Without BII and with BII, using 96 daily observations obtained from the integration of market and social media data. The results show that The with BII scenario increases accuracy from 40.00% to 75.00%, recall from 14.29% to 78.57%, F1-score from 0.2500 to 0.8148, and area under the curve from 0.3809 to 0.6667, while precision changes from 100.00% to 84.62%. Paired t-test yields p=0.030771, and Wilcoxon signed rank produces p=0.034808, while McNemar produces p=0.065430. These findings suggest that opinion source characteristics can provide additional predictive information when integrated with sentiment, technical indicators, and temporal models. The main contribution of this study lies in extending sentiment aware forecasting toward influence aware Bitcoin trend prediction, an approach that considers not only opinion polarity but also the multidimensional characteristics of the information sources conveying those opinions.


Keywords


Bitcoin Influence Index; FinBERT; Hybrid Machine Learning; Sentiment Analysis; Time Series Forecasting

Full Text:

PDF

References


K. Zala, V. Modi, D. Giri, B. Acharya, S. Mallik, and H. Qin, “Unlocking Blockchain Interconnectivity: Smart Contract-Driven Cross-Chain Communication,” IEEE Access, vol. 11, pp. 75365–75380, 2023, doi: 10.1109/ACCESS.2023.3296556.

B. Maram, “Bitcoin generation using blockchain technology,” Int. J. Informatics Vis., vol. 2, no. 3, pp. 127–132, 2018, doi: 10.30630/joiv.2.3.109.

T. Peciulis and A. Vasiliauskaitė, “Effect of Monetary Policy Decisions and Announcements on the Price of Cryptocurrencies: An Elastic-Net With ARIMA Residuals Approach,” Econ. Cult., vol. 21, no. 1, pp. 77–92, 2024, doi: 10.2478/jec-2024-0006.

B. Ruru, I. N. Tjager, A. Mayasari, A. Adhistita, M. R. Hasta A., and A. Santro, “The Impact of Crypto-Asset Utilization as Payment Instrument toward Rupiah as Legal Tender in Indonesia,” J. Cent. Bank. Law Institutions, vol. 1, no. 1, pp. 141–180, 2021, doi: 10.21098/jcli.v1i1.6.

N. A. Tavares, P. V. J. da Gama Silva, and M. C. Klotzle, “Investigation of the intentional and spurious herding effects in the cryptocurrency market with global events,” Q. Rev. Econ. Financ., vol. 102, p. 101992, 2025, doi: 10.1016/j.qref.2025.101992.

S. Aras, M. O. Özdemir, and C. Çılgın, “Can joint modelling of external variables sampled at different frequencies enhance long-term Bitcoin volatility forecasts?,” Financ. Res. Lett., vol. 73, no. November 2024, 2025, doi: 10.1016/j.frl.2024.106679.

A. Munazilin, M. A. Wibowo, and R. Parlika, “Bitcoin Price Prediction : A Systematic Literature Review and Bibliometric Analysis,” 2025 9th Int. Conf. Inf. Technol. Inf. Syst. Electr. Eng., pp. 277–282, 2025, doi: 10.1109/ICITISEE68184.2025.11355086.

E. P. Wahyuddin, R. E. Caraka, R. Kurniawan, W. Caesarendra, P. U. Gio, and B. Pardamean, “Improved LSTM hyperparameters alongside sentiment walk-forward validation for time series prediction,” J. Open Innov. Technol. Mark. Complex., vol. 11, no. 1, p. 100458, 2025, doi: 10.1016/j.joitmc.2024.100458.

Q. Phung Duy, O. Nguyen Thi, P. H. Le Thi, H. D. Pham Hoang, K. L. Luong, and K. N. Nguyen Thi, “Estimating and forecasting bitcoin daily prices using ARIMA-GARCH models,” Bus. Anal. J., vol. 45, no. 1, pp. 11–23, 2024, doi: 10.1108/baj-05-2024-0027.

A. Shelton, “Bitcoin Return Prediction: Is It Possible via Stock-to-Flow, Metcalfe’s Law, Technical Analysis, or Market Sentiment?,” J. Risk Financ. Manag., vol. 17, no. 10, 2024, doi: 10.3390/jrfm17100443.

G. Vlahavas and A. Vakali, “Dynamics between Bitcoin Market Trends and Social Media Activity,” FinTech, vol. 3, no. 3, pp. 349 – 378, 2024, doi: 10.3390/fintech3030020.

J. V. Critien, A. Gatt, and J. Ellul, “Bitcoin price change and trend prediction through twitter sentiment and data volume,” Financ. Innov., vol. 8, no. 1, 2022, doi: 10.1186/s40854-022-00352-7.

Y. Zou and D. Herremans, “PreBit — A multimodal model with Twitter FinBERT embeddings for extreme price movement prediction of Bitcoin,” Expert Syst. Appl., vol. 233, 2023, doi: 10.1016/j.eswa.2023.120838.

Z. Liu, M. Shu, and W. Zhu, “Contrastive Learning Framework for Bitcoin Crash Prediction,” Stats, vol. 7, no. 2, pp. 402 – 433, 2024, doi: 10.3390/stats7020025.

V. Koltun and I. P. Yamshchikov, “Pump It: Twitter Sentiment Analysis for Cryptocurrency Price Prediction,” Risks, vol. 11, no. 9, pp. 1–14, 2023, doi: 10.3390/risks11090159.

H. S. Htay, M. Ghahremani, and S. N. Shiaeles, “Enhancing Bitcoin Price Prediction with Deep Learning: Integrating Social Media Sentiment and Historical Data,” Appl. Sci., vol. 15, no. 3, 2025, doi: 10.3390/app15031554.

Y. E. Akdogan and A. Anbar, “More than just sentiment: Using social, cognitive, and behavioral information of social media to predict stock markets with artificial intelligence and big data,” 2024. doi: 10.1016/j.bir.2024.12.003.

K. Jahanbin and M. A. Z. Chahooki, “Aspect-Based Sentiment Analysis of Twitter Influencers to Predict the Trend of Cryptocurrencies Based on Hybrid Deep Transfer Learning Models,” IEEE Access, vol. 11, pp. 121656 – 121670, 2023, doi: 10.1109/ACCESS.2023.3327060.

R. Bibi, S. Gulzar, and S. J. H. Shahzad, “ESG leaders and crypto currency market: Asymmetric TVP-VAR connectedness and investment approaches,” Res. Int. Bus. Financ., vol. 76, no. July 2024, p. 102833, 2025, doi: 10.1016/j.ribaf.2025.102833.

F. Feizian and B. Amiri, “Cryptocurrency Price Prediction Model Based on Sentiment Analysis and Social Influence,” IEEE Access, vol. 11, pp. 142177–142195, 2023, doi: 10.1109/ACCESS.2023.3342688.

J. Park and Y.-S. Seo, “Twitter Sentiment Analysis-Based Adjustment of Cryptocurrency Action Recommendation Model for Profit Maximization,” IEEE Access, vol. 11, pp. 44828 – 44841, 2023, doi: 10.1109/ACCESS.2023.3273898.

P. D. Quang, N. K. Huyen, and H. N. Quyen, “Analysis and Forecasting of Bitcoin Price Volatility: A Deep Learning Approach Using DNN, LSTM, Transformers, and the ARMA-GARCH Model,” J. Appl. Math., vol. 2025, no. 1, 2025, doi: 10.1155/jama/9089827.

Sarmini, C. R. A. Widiawati, D. R. Febrianti, and D. Yuliana, “Volatility Analysis of Cryptocurrencies using Statistical Approach and GARCH Model a Case Study on Daily Percentage Change,” J. Appl. Data Sci., vol. 5, no. 3, pp. 838–848, 2024, doi: 10.47738/jads.v5i3.261.

S. Arslan, “Bitcoin Price Prediction Using Sentiment Analysis and Empirical Mode Decomposition,” Comput. Econ., vol. 65, no. 4, pp. 2227–2248, 2025, doi: 10.1007/s10614-024-10588-3.

S. Zeinedini, M. S. Karimi, A. Khanzadi, and A. Falahati, “Impact of oil and gold prices on Bitcoin price during Russia-Ukraine and Israel-Gaza wars,” Resour. Policy, vol. 99, no. June, p. 105405, 2024, doi: 10.1016/j.resourpol.2024.105405.

W. Bahloul and W. Dammak, “Online investor sentiment in the financial futures markets,” Res. Int. Bus. Financ., vol. 75, no. May 2023, p. 102708, 2025, doi: 10.1016/j.ribaf.2024.102708.

C. Liu, A. Arulappan, R. Naha, A. Mahanti, J. Kamruzzaman, and I.-H. Ra, “Large Language Models and Sentiment Analysis in Financial Markets: A Review, Datasets, and Case Study,” IEEE Access, vol. 12, pp. 134041 – 134061, 2024, doi: 10.1109/ACCESS.2024.3445413.

P. Han, H. Chen, A. Rasool, Q. Jiang, and M. Yang, “MFB: A Generalized Multimodal Fusion Approach for Bitcoin Price Prediction Using Time-Lagged Sentiment and Indicator Features,” Expert Syst. Appl., vol. 261, 2025, doi: 10.1016/j.eswa.2024.125515.

R. Kaur, S. Singh, and H. Kumar, “Rise of spam and compromised accounts in online social networks: A state-of-the-art review of different combating approaches,” J. Netw. Comput. Appl., vol. 112, no. September 2017, pp. 53–88, 2018, doi: 10.1016/j.jnca.2018.03.015.

S. Ben Jabeur, Z. Dhifaoui, Y. Bakkar, and H. Ballouk, “‘Crypto president’: Do narrative political signals drive cryptocurrency returns?,” Financ. Res. Lett., vol. 78, no. January, p. 107194, 2025, doi: 10.1016/j.frl.2025.107194.

K. Jahanbin and M. A. Z. Chahooki, “Database of twitter influencers in cryptocurrency (2021–2023) with sentiments,” BMC Res. Notes, vol. 17, no. 1, 2024, doi: 10.1186/s13104-023-06548-z.

P. D. Quang, N. H. Duy, P. Q. Khoai, and B. D. Duong, “Integrating Moving Average Indicators with Long Short-Term Memory Model in Bitcoin Price Forecasting,” J. Appl. Data Sci., vol. 6, no. 3, pp. 1850–1864, 2025, doi: 10.47738/jads.v6i3.766.

D. Javed et al., “Towards the future of bot detection: A comprehensive taxonomical review and challenges on Twitter/X,” Comput. Networks, vol. 254, no. October 2023, p. 110808, 2024, doi: 10.1016/j.comnet.2024.110808.

M. Rafi, Q. A. K. Mirza, M. I. Sohail, M. Aliasghar, A. Aziz, and S. Hameed, “Enhancing Cryptocurrency Price Forecasting Accuracy: A Feature Selection and Weighting Approach With Bi-Directional LSTM and Trend-Preserving Model Bias Correction,” IEEE Access, vol. 11, pp. 65700–65710, 2023, doi: 10.1109/ACCESS.2023.3287888.

V. Gurgul, S. Lessmann, and W. K. Härdle, “Deep learning and NLP in cryptocurrency forecasting: Integrating financial, blockchain, and social media data,” Int. J. Forecast., vol. 41, no. 4, pp. 1666–1695, 2025, doi: 10.1016/j.ijforecast.2025.02.007.

J. Michańków, P. Sakowski, and R. Ślepaczuk, “Mean Absolute Directional Loss as a new loss function for machine learning problems in algorithmic investment strategies,” J. Comput. Sci., vol. 81, 2024, doi: 10.1016/j.jocs.2024.102375.




DOI: https://doi.org/10.47738/jads.v7i4.1322

Refbacks

  • There are currently no refbacks.


Barcode

Journal of Applied Data Sciences

ISSN:2723-6471 (Online)
Publisher:Bright Publisher
Website:http://bright-journal.org/JADS
Email:taqwa@amikompurwokerto.ac.id (principal contact)
  support@bright-journal.org (technical issues)

This work is licensed under a Creative Commons Attribution-ShareAlike 4.0