A Sentiment-Enhanced Machine Learning Framework for Quantitative Trading Based on Pleasure-Arousal-Dominance Theory_Vol. 3 No. 4 (JBDC 2025)_Journal of Big Data and Computing (ISSN: 2959-0590)

Home > Journal of Big Data and Computing (ISSN: 2959-0590) > Vol. 3 No. 4 (JBDC 2025) >

A Sentiment-Enhanced Machine Learning Framework for Quantitative Trading Based on Pleasure-Arousal-Dominance Theory

Download PDF

DOI: https://doi.org/10.62517/jbdc.202501423

Author(s)

Jingwei Yang, Shifan Peng, Yiqian Wang, Zisong Ma, Fanfei Liu, Shiqi Li, Yan Li*

Affiliation(s)

School of Management, China University of Mining and Technology -Beijing, Beijing, China *Corresponding Author.

Abstract

Recent studies emphasize integrating investor sentiment into quantitative strategies, yet existing methods often rely on unidimensional frameworks that inadequately capture sentiment complexity. This study introduces a three- dimensional model based on the Pleasure-Arousal-Dominance (PAD) theory, formalizing sentiment dynamics through Pleasure, Arousal and Dominance. These signals are algorithmically embedded to optimize trade execution, position sizing, and volatility management. Across four futures asset classes, the PAD-enhanced strategies achieved consistent improvements. By averaging performance metrics (annualized returns, Sharpe ratios, drawdowns) across all four categories, the framework yielded a mean annualized return of 298.4% and a Sharpe ratio improvement of 31.5%, while reducing maximum drawdown by 18.2%. Dominance metrics effectively curtailed risk exposure during uncertainty, while Arousal signals minimized overtrading in disordered markets. These results validate the necessity of multidimensional sentiment modeling and highlight PAD theory’s utility in bridging behavioral biases with algorithmic rigor. The framework offers a systematic solution for institutional investors to exploit sentiment-driven inefficiencies while maintaining cross-asset robustness.

Keywords

Sentiment Analysis; Pleasure-Arousal-Dominance (PAD) Model; Machine Learning; Quantitative Trading; Multi-Asset Futures; Sentiment-Enhanced Strategies; Risk Management

References

[1]D. Aggarwal, “Defining and measuring market sentiments: a review of the literature,” vol. 14, no. 2, pp. 270–288, publisher: Emerald Publishing Limited. [Online]. Available: https://doi.org/10.1108/ QRFM-03-2018-0033. [2]W. Wang, C. Su, and D. Duxbury, “Investor sentiment and stock returns: Global evidence,” vol. 63, pp. 365–391. [Online]. Available: https://www.sciencedirect.com/science/article/pii/ S092753982100058X. [3]Z. Gric, J. Bajz´ık, and O. Badura, “Does sentiment affect stock returns? A meta-analysis across survey-based measures,” vol. 89, p. 102773, 2023. [Online]. Available: https://www.sciencedirect. com/science/article/pii/S1057521923002892. [4]H. Zhang, F. Hua, C. Xu, J. Guo, H. Kong, and R. Zuo, “Unveiling the potential of sentiment: Can large language models predict chinese stock price movements?” 2023. [Online]. Available: http://arxiv. org/abs/2306.14222. [5]A. Ye, J. Xu, Y. Wang, Y. Yu, D. Yan, R. Chen, B. Dong, V. Chaudhary, and S. Xu, “Learning the market: Sentiment-based ensemble trading agents.” 2024. [Online]. Available: http://arxiv.org/abs/ 2402.01441. [6]Y.-J. Hsu, Y.-C. Lu, and J. J. Yang, “News sentiment and stock market volatility,” vol. 57, no. 3, pp. 1093–1122, 2021. [Online]. Available: https://doi.org/10.1007/s11156-021-00971-8. [7]C. Mbanga, A. F. Darrat, and J. C. Park, “Investor sentiment and aggregate stock returns: The role of investor attention,” vol. 53, no. 2, pp. 397–428, 2019. [Online]. Available: https://doi.org/10.1007/ s11156-018-0753-2. [8]J. W. Goodell, S. Kumar, P. Rao, and S. Verma, “Emotions and stock market anomalies: A systematic review,” vol. 37, p. 100722, 2023. [Online]. Available: https://www.sciencedirect. com/science/article/pii/S2214635022000557. [9]P. Liu, “Quantitative trading: An introduction,” in Quantitative Trading Strategies Using Python: Technical Analysis, Statistical Testing, and Machine Learning, P. Liu, Ed., Apress, pp. 1–33, 2023. [Online]. Available: https://doi.org/10.1007/978-1-4842-9675-2_1. [10]B. Huang, Y. Huan, L. D. Xu, L. Zheng, and Z. Zou, “Automated trading systems: Statistical and machine learning methods and hard- ware implementation: A survey,” vol. 13, no. 1, pp. 132–144, 2019. [Online]. Available: https://www.tandfonline.com/doi/full/10. 1080/17517575.2018.1493145. [11]H. Wu and D. Levinson, “The ensemble approach to fore- casting: A review and synthesis,” vol. 132, p. 103357, 2021. [Online]. Available: https://www.sciencedirect.com/science/ article/pii/S0968090X21003594. [12]R. Sakariyahu, R. Lawal, O. Oyekola, O. E. Dosumu, and R. Adi- gun, “Natural disasters, investor sentiments and stock market reactions: Evidence from Turkey–Syria earthquakes,” vol. 228, p. 111153, 2023. [Online]. Available: https://www.sciencedirect. com/science/article/pii/S0165176523001787. [13]M. BourdeauBrien and L. Kryzanowski, “The impact of natural dis- asters on the stock returns and volatilities of local firms,” vol. 63, pp. 259–270, 2017. [Online]. Available: https://www.sciencedirect. com/science/article/pii/S1062976916300278. [14]M. Kim, “Adaptive trading system integrating machine learn- ing and back-testing: Korean bond market case,” vol. 176, p. 114767, 2021. [Online]. Available: https://www.sciencedirect. com/science/article/pii/S0957417421002086. [15]T. Th´eate and D. Ernst, “An application of deep reinforcement learning to algorithmic trading,” vol. 173, p. 114632, 2021. [Online]. Available: https://www.sciencedirect.com/science/ article/pii/S0957417421000737. [16]I. Goldstein, C. S. Spatt, and M. Ye, “Big data in finance,” vol. 34, no. 7, pp. 3213—3225, 2021. [Online]. Available: https://doi.org/10. 1093/rfs/hhab038. [17]K. Du, F. Xing, R. Mao, and E. Cambria, “Financial sentiment analysis: Techniques and applications,” vol. 56, no. 9, pp. 220:1—220:42. [Online]. Available: https://dl.acm.org/doi/10.1145/3649451. [18]F. Chi, B.-H. Hwang, and Y. Zheng, “The use and usefulness of big data in finance: evidence from financial analysts,” publisher: INFORMS. [Online]. Available: https://pubsonline.informs.org/doi/full/ 10.1287/mnsc.2022.02659. [19]X.-Y. Liu, Z. Xia, H. Yang, J. Gao, D. Zha, M. Zhu, C. D. Wang, Z. Wang, and J. Guo, “Dynamic datasets and market environments for financial reinforcement learning,” vol. 113, no. 5, pp. 2795—2839. [On- line]. Available: https://doi.org/10.1007/s10994-023-06511-w. [20]F. Chi, B.-H. Hwang, and Y. Zheng, “The use and usefulness of big data in finance: evidence from financial analysts,” publisher: INFORMS. [Online]. Available: https://pubsonline.informs.org/doi/full/ 10.1287/mnsc.2022.02659. [21]H. Han, Z. Li, and Z. Li, “Using machine learning methods to predict consumer confidence from search engine data,” vol. 15, no. 4, p. 3100, number: 4 Publisher: Multidisciplinary Digital Publishing Institute. [Online]. Available: https://www-mdpi-com-s.vpn.cumtb.edu.cn:8118/20711050/15/4/3100. [22]W. Li, C. Hu, and Y. Luo, “A deep learning approach with extensive sentiment analysis for quantitative investment,” vol. 12, no. 18, p. 3960. [Online]. Available: https://www.mdpi.com/2079-9292/12/18/3960. [23]C.-H. Chen, W.-H. Lai, S.-T. Hung, and T.-P. Hong, “An advanced optimization approach for long-short pairs trading strategy based on correlation coefficients and bollinger bands,” vol. 12, no. 3, p. 1052.[Online]. Available: https://www.mdpi.com/20763417/12/3/1052. [24]X. Gao, M. Qiu, and Z. He, “Big data analysis with momentum strategy on data-driven trading,” in 2021 IEEE Intl Conf on Parallel & Distributed Processing with Applications, Big Data & Cloud Computing, Sustainable Computing & Communications, Social Computing & Networking (ISPA/BDCloud/SocialCom/SustainCom),IEEE, pp. 1328—1335. [Online]. Available: https://ieeexplore.ieee.org/ document/9644769/. [25]H. Pan, “Chinese value investing theory and quantitative technology,” in 2021 IEEE 19th International Conference on Industrial Informatics (INDIN), IEEE, pp. 1—6. [Online]. Available: https://ieeexplore.ieee.org/document/9557552/. [26]B. Li, S. C. H. Hoi, P. Zhao, and V. Gopalkrishnan, “Confidence weighted mean reversion strategy for online portfolio selection,” vol. 7, no. 1, pp. 1—38. [Online]. Available: https://dl.acm.org/doi/10.1145/2435209.2435213. [27]C. Zhou, Y. Huang, K. Cui, and X. Lu, “R-DDQN: Optimizing algorithmic trading strategies using a reward network in a double DQN,” vol. 12, no. 11, p. 1621. [Online]. Available: https://www.mdpi.com/2227-7390/12/11/1621. [28]D. Xia and J. Shi, “Individual investors’ online voice and corporate environmental information disclosure,” vol. 62, p. 105262. [Online]. Available: https://linkinghub.elsevier.com/retrieve/ pii/S1544612324002927. [29]I. Yousaf and L. Yarovaya, “The relationship between trading volume, volatility and returns of non-fungible tokens: evidence from a quantile approach,” vol. 50, p. 103175. [Online]. Available: https: //linkinghub.elsevier.com/retrieve/pii/S1544612322003889. [30]A. Thavaneswaran, Y. Liang, Z. Zhu, and R. K. Thulasiram, “Novel data-driven fuzzy algorithmic volatility forecasting models with applications to algorithmic trading,” in 2020 IEEE International Conference on Fuzzy Systems (FUZZ-IEEE), IEEE, pp. 1—8. [Online]. Available: https://ieeexplore.ieee.org/document/9177735/. [31]S. Song, F. Tian, and H. Li, “An intraday-return-based value- at-risk model driven by dynamic conditional score with censored generalized pareto distribution,” vol. 74, p. 101314, 2021. [Online]. Available: https://linkinghub.elsevier.com/retrieve/ pii/S1049007821000439. [32]J. Miffre, “Long-short commodity investing: A review of the literature,” vol. 1, no. 1, pp. 3—13, 2016. [Online]. Available: https: //linkinghub.elsevier.com/retrieve/pii/S2405851315301094. [33]V. Campos, B. Jou, and X. Gir´oi Nieto, “From pixels to sentiment: Fine-tuning CNNs for visual sentiment prediction,” vol. 65, pp. 15— 22, 2017. [Online]. Available: https://linkinghub.elsevier.com/retrieve/pii/S0262885617300355. [34]I. Chaturvedi, R. Satapathy, S. Cavallari, and E. Cambria, “Fuzzy commonsense reasoning for multimodal sentiment analysis,” vol. 125, pp. 264—270, 2019. [Online]. Available: https://linkinghub.elsevier. com/retrieve/pii/S0167865519301394. [35] F. Huang, S. Zhang, J. Zhang, and G. Yu, “Multimodal learning for topic sentiment analysis in microblogging,” vol.253, pp. 144—153, 2017. [Online]. Available: https://linkinghub.elsevier.com/retrieve/ pii/S0925231217304393. [36]J. Serrano-Guerrero, J. A. Olivas, F. P. Romero, and E. HerreraViedma, “Sentiment analysis: A review and comparative analysis of web services,” vol. 311, pp. 18—38, 2015. [Online]. Available:https://linkinghub.elsevier.com/retrieve/pii/S0020025515002054. [37]M. Soleymani, D. Garcia, B. Jou, B. Schuller, S.-F. Chang, and M. Pan- tic, “A survey of multimodal sentiment analysis,” vol. 65, pp.3—14, 2017. [Online]. Available: https://linkinghub.elsevier.com/ retrieve/pii/S0262885617301191. [38]A. Kumar, K. Srinivasan, W.-H. Cheng, and A. Y. Zomaya, “Hybrid context enriched deep learning model for fine-grained sentiment analysis in textual and visual semiotic modality social data,” vol. 57, no. 1, p. 102141, 2020. [Online]. Available: https://linkinghub.elsevier. com/retrieve/pii/S0306457319306934. [39]D. Chen, W. Su, P. Wu, and B. Hua, “Joint multimodal sentiment analysis based on information relevance,” vol. 60, no. 2, p. 103193, 2023. [Online]. Available: https://linkinghub.elsevier.com/retrieve/ pii/S0306457322002941. [40]A. Gandhi, K. Adhvaryu, S. Poria, E. Cambria, and A. Hussain, “Multimodal sentiment analysis: A systematic review of history, datasets, multimodal fusion methods, applications, challenges and future directions,” vol. 91, pp. 424—444, 2023. [Online]. Available: https: //linkinghub.elsevier.com/retrieve/pii/S1566253522001634. [41]D. Wang, X. Guo, Y. Tian, J. Liu, L. He, and X. Luo, “TETFN: A text enhanced transformer fusion network for multimodal sentiment analysis,” vol.136, p. 109259, 2023. [Online]. Available: https://linkinghub.elsevier.com/retrieve/pii/S0031320322007385. [42]A. B. Prasetijo, T. A. Saputro, I. P. Windasari, and Y. E. Windarto, “Buy/sell signal detection in stock trading with bollinger bands and parabolic SAR: With web application for proofing trading strategy,” in 2017 4th International Conference on Information Technology, Computer, and Electrical Engineering (ICITACEE), IEEE, pp. 41—44, 2017. [Online]. Available: http://ieeexplore.ieee.org/document/8257672/. [43][43] M.-E. Wu, T.-C. Chen, C.-P. Chung, G.-R. Li, D.-W. Chi- ang, and D.-Y. Yang, “PASS: Portfolio analysis of selecting strategies on quantitative trading via NSGA-II,” pp. 1—28, 2024. [Online]. Available: https://www.tandfonline.com/doi/full/10. 1080/0305215X.2024.2418342 [44]W. Zhang, S. Li, Z. Guo, and Y. Yang, “A hybrid forecasting model based on deep learning feature extraction and statistical arbitrage methods for stock trading strategies,” vol. 42, no. 7, pp. 1729—1749, 2023. [Online]. Available: https://onlinelibrary.wiley.com/doi/10.1002/for.2978. [45]G. C. Calafiore, L. Poletti, and A. Preziosi, “MatTrader: An automated trading and financial data analysis framework for matlab and java,” in 2016 IEEE 55th Conference on Decision and Control (CDC), IEEE, pp. 7561—7566, 2016. [Online]. Available: http://ieeexplore.ieee. org/document/7799437/.