Data-driven Personalized Family Music Therapy: a Reinforcement Learning Recommendation Model Based on Family Member Behavior and Feedback
Main Article Content
Abstract
This study proposes a data-driven personalized family music therapy recommendation framework to address the limitations of conventional recommendation systems in modeling emotional interactions among multiple family members. The framework employs a reinforcement learning approach tailored to family environments, where emotional states evolve through continuous interpersonal interactions and feedback. A relationship-aware family state representation is developed by integrating behavioral observations and physiological responses, enabling the modeling of both individual emotional states and emotional contagion among family members. To support adaptive intervention, the action space incorporates music selection, spatial delivery strategies, and intentional silence decisions, allowing the system to balance active intervention with natural emotional self-regulation. In addition, a multi-channel reward mechanism is designed by combining physiological recovery, behavioral relaxation, and environmental stability indicators, while a temporal credit assignment strategy addresses delayed therapeutic effects. Experimental evaluation on a multimodal dataset covering four representative family stress scenarios demonstrates that the proposed framework achieves 89.7% accuracy in family emotion representation, 86.3% consistency with expert intervention judgments, and an 82.3% positive emotion conversion rate after continuous intervention. These findings suggest that reinforcement learning can provide an effective foundation for transforming music recommendation systems from individual entertainment tools into proactive family emotional support systems.
Downloads
Article Details
This work is licensed under a Creative Commons Attribution 4.0 International License.
Authors who publish with this journal agree to the following terms:
- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See The Effect of Open Access).
References
Z. Liu, W. Xu, W. Zhang, and Q. Jiang, “An emotion-based personalized music recommendation framework for emotion improvement,” Information Processing & Management, vol. 60, no. 3, pp. 103256–103264, 2023, doi: https://doi.org/10.1016/j.ipm.2022.103256.
R. De Prisco, A. Guarino, D. Malandrino, and R. Zaccagnino, “Induced emotion-based music recommendation through reinforcement learning,” Applied Sciences, vol. 12, no. 21, pp. 11209–11215, 2022, doi: https://doi.org/10.3390/app122111209.
S. I. Baek and Y. K. Lee, “A Continuous Music Recommendation Method Considering Emotional Change,” Applied Sciences, vol. 15, no. 13, pp. 7222–7229, 2025, doi: https://doi.org/10.3390/app15137222.
M. Carvalho, N. Cera, and S. Silva, “The "ifs" and "hows" of the role of music on the implementation of emotional regulation strategies,” Behavioral Sciences, vol. 12, no. 6, pp. 199–206, 2022, doi: https://doi.org/10.3390/bs12060199.
M. Stratigi, E. Pitoura, and K. Stefanidis, “SQUIRREL: A framework for sequential group recommendations through reinforcement learning,” Information Systems, vol. 112, no. 1, pp. 102128–102134, 2023, doi: https://doi.org/10.1016/j.is.2022.102128.
K. Howland, K. Edvardsson, H. Lees, and L. Hooker, “Telehealth use in the well-child health setting. A systematic review of acceptability and effectiveness for families and practitioners,” International journal of nursing studies advances, vol. 8, no. 1, pp. 100277–106282, 2025, doi: https://doi.org/10.1016/j.ijnsa.2024.100277.
V. Peters, J. Bissonnette, D. Nadeau, A. Gauthier-Légaré, and M. A. Noël, “The impact of musicking on emotion regulation: A systematic review and meta-analysis,” Psychology of Music, vol. 52, no. 5, pp. 548–568, 2024, doi: https://doi.org/10.1177/03057356231212362.
B. Paley and N. J. Hajal, “Conceptualizing emotion regulation and coreg-ulation as family-level phenomena,” Clinical child and family psychology review, vol. 25, no. 1, pp. 19–43, 2022, doi: https://doi.org/10.1007/s10567-022-00378-4.
A. Tran, K. H. Greenaway, J. Kostopoulos, S. T. O’Brien, and E. K. Kalokerinos, “Mapping interpersonal emotion regulation in everyday life,” Affective Science, vol. 4, no. 4, pp. 672–683, 2023, doi: https://doi.org/10.1007/s42761-023-00223-z.
S. S. Yap, F. T. Ramseyer, J. Fachner, C. Maidhof, W. Tschacher, and G. Tucek, “Dyadic nonverbal synchrony during pre and post music therapy interventions and its relationship to self-reported therapy readiness,” Frontiers in human neuroscience, vol. 16, no. 1, pp. 912729–912734, 2022, doi: https://doi.org/10.3389/fnhum.2022.912729.
C. Stolterfoth and E. Pfeifer, “Music therapy and silence–Silence in music therapy. A systematic review,” The Arts in Psychotherapy, vol. 93, no. 1, pp. 102286–102293, 2025, doi: https://doi.org/10.1016/j.aip.2025.102286.
Y. Rong, N. Chen, J. Dong, Q. Li, X. Yue, L. Hu, et al., “Expectations of immediate and delayed reward differentially affect cognitive task performance,” NeuroImage, vol. 262, no. 1, pp. 119582–119587, 2022, doi: https://doi.org/10.1016/j.neuroimage.2022.119582.
A. W. Awan, S. M. Usman, S. Khalid, A. Anwar, R. Alroobaea, S. Hussain, et al., “An ensemble learning method for emotion charting using multimodal physiological signals,” Sensors, vol. 22, no. 23, pp. 9480– 9488, 2022, doi: https://doi.org/10.3390/s22239480.
X. Hu, F. Li, and R. Liu, “Detecting music-induced emotion based on acoustic analysis and physiological sensing: A multimodal approach,” Applied Sciences, vol. 12, no. 18, pp. 9354–9361, 2022, doi: https://doi.org/10.3390/app12189354.
P. Pichappan, “A Review of the Emotion-Induced Music Recommendation Systems,” Journal of Digital Information Management, vol. 23, no. 2, pp. 112–133, 2025, doi: https://doi.org/10.6025/jdim/2025/23/2/112-133.
X. Han, F. Chen, and J. Ban, “A GAI-based multi-scale convolution and attention mechanism model for music emotion recognition and recommendation from physiological data,” Applied Soft Computing, vol. 164, no. 1, pp. 112034–112041, 2024, doi: https://doi.org/10.1016/j.asoc.2024.112034.
Z. Ahmad and N. Khan, “A survey on physiological signal-based emotion recognition,” Bioengineering, vol. 9, no. 11, pp. 688–693, 2022, doi: https://doi.org/10.3390/bioengineering9110688.
A. Wong, T. Bäck, A. V. Kononova, and A. Plaat, “Deep multiagent reinforcement learning: challenges and directions,” Artificial Intelligence Review, vol. 56, no. 6, pp. 5023–5056, 2023, doi: https://doi.org/10.1007/s10462-022-10299-x.
Y. Miyashita and T. Sugawara, “Two-stage reward allocation with decay for multi-agent coordinated behavior for sequential cooperative task by using deep reinforcement learning,” Autonomous Intelligent Systems, vol. 2, no. 1, pp. 10–17, 2022, doi: https://doi.org/10.1007/s43684-022-00029-z.
B. Xiao, H. K. Lam, X. Su, Z. Wang, F. P. W. Lo, S. Chen, et al., “Sampled-data control through model-free reinforcement learning with effective experience replay,” Journal of Automation and Intelligence, vol. 2, no. 1, pp. 20–30, 2023, doi: https://doi.org/10.1016/j.jai.2023.100018.
X. Lou, Q. Yin, J. Zhang, C. Yu, Z. He, N. Cheng, et al., “Offline reinforcement learning with representations for actions,” Information Sciences, vol. 610, no. 1, pp. 746–758, 2022, doi: https://doi.org/10.1016/j.ins.2022.08. 019.
I. Gordon, A. Tomashin, and O. Mayo, “A theory of flexible multimodal synchrony,” Psychological review, vol. 132, no. 3, pp. 680–687, 2025, doi: https://doi.org/10.1037/rev0000495.
S. Delleli, I. Ouergui, C. G. Ballmann, H. Messaoudi, K. Trabelsi, L. P. Ardigo, et al., “The effects of pre-task music on exercise performance and associated psycho-physiological responses: a systematic review with multilevel meta-analysis of controlled studies,” Frontiers in Psychology, vol. 14, no. 1, pp. 1293783–1293791, 2023, doi: https://doi.org/10.3389/fpsyg.2023.1293783.
R. Chen and Y. Tan, “Credit assignment with predictive contribution measurement in multi-agent reinforcement learning,” Neural Networks, vol. 164, no. 1, pp. 681–690, 2023, doi: https://doi.org/10.1016/j.neunet.2023.05.021.
D. Wang, J. Wang, L. Hu, and M. Zhao, “Event-based online learning control design with eligibility trace for discrete-time unknown nonlinear systems,” Engineering Applications of Artificial Intelligence, vol. 123, no. 1, pp. 106240–106244, 2023, doi: https://doi.org/10.1016/j.engappai.2023.106240.
A. Israelsson, A. Seiger, and P. Laukka, “Blended emotions can be accurately recognized from dynamic facial and vocal expressions,” Journal of Nonverbal Behavior, vol. 47, no. 3, pp. 267–284, 2023, doi: https://doi.org/10.1007/s10919-023-00426-9.
J. Luo, G. Zhang, Y. Su, Y. Lu, Y. Pang, Y. Wang, et al., “Quantitative analysis of heart rate variability parameter and mental stress index,” Frontiers in Cardiovascular Medicine, vol. 9, no. 1, pp. 930745–930452, 2022, doi: https://doi.org/10.3389/fcvm.2022.930745.
L. Gong, W. Chen, M. Li, and T. Zhang, “Emotion recognition from multiple physiological signals using intra-and inter-modality attention fusion network,” Digital Signal Processing, vol. 144, no. 1, pp. 104278– 104285, 2024, doi: https://doi.org/10.1016/j.dsp.2023.104278.
E. Ghaleb, J. Niehues, and S. Asteriadis, “Joint modelling of audio-visual cues using attention mechanisms for emotion recognition,” Multimedia Tools and Applications, vol. 82, no. 8, pp. 11239–11264, 2023, doi: https://doi.org/10.1007/s11042-022-13557-w.
S. L. Jacobsen, G. Gattino, U. Holck, and J. Ø. Bøtker, “Music, families and interaction (MUFASA): a protocol article for an RCT study,” BMC psychology, vol. 10, no. 1, pp. 252–259, 2022, doi: https://doi.org/10.1186/s40359-022-00957-8.
Y. Shibata, A. Yoshimoto, K. Yamashiro, Y. Ikegaya, and N. Matsumoto, “Delayed reinforcement hinders subsequent extinction,” Biochemical and biophysical research communications, vol. 591, no. 1, pp. 20–25, 2022, doi: https://doi.org/10.1016/j.bbrc.2021.12.101.
B. Flater, A. Brean, and D. S. Quintana, “Music therapy and vagally mediated heart rate variability: A systematic review and narrative synthesis,” International Journal of Psychophysiology, vol. 219, no. 1, pp. 113288– 113294, 2026, doi: https://doi.org/10.1016/j.ijpsycho.2025.113288.
A. Warmbrodt, R. Timmers, and R. Kirk, “The emotion trajectory of self-selected jazz music with lyrics: A psychophysiological perspective,” Psychology of Music, vol. 50, no. 3, pp. 756–778, 2022, doi: https://doi.org/10.1177/03057356211024336.
Q. Wang, C. Zhang, and B. Hu, “Dynamic programming with meta-reinforcement learning: a novel approach for multi-objective optimization,” Complex & Intelligent Systems, vol. 10, no. 4, pp. 5743–5758, 2024, doi: https://doi.org/10.1007/s40747-024-01469-1.
J. Tang, Z. Ma, K. Gan, J. Zhang, and Z. Yin, “Hierarchical multimodal-fusion of physiological signals for emotion recognition with scenario adaption and contrastive alignment,” Information Fusion, vol. 103, no. 1, pp. 102129–102136, 2024, doi: https://doi.org/10.1016/j.inffus.2023.102129.