@article{4467,
  author = {Pit Pichappan},
  title = {A Review of the Emotion-Induced Music Recommendation Systems},
  journal = {Journal of Digital Information Management},
  year = {2025},
  volume = {23},
  number = {2},
  doi = {https://doi.org/10.6025/jdim/2025/23/2/112-133},
  url = {https://www.dline.info/fpaper/jdim/v23i2/jdimv23i2_3.pdf},
  abstract = {This review discusses the evolution, approaches, methodologies, features, and outcomes of emotion-induced music recommendation systems (MRS) in light of the growing demand for personalised music experiences. Traditional MRS often overlook the emotional context of users, making the integration of emotion recognition a promising enhancement for user satisfaction. The paper examines 32 studies published between 2011 and 2025, detailing how various inputs, such as facial expressions and physiological signals, can inform personalised music recommendations. It highlights the application of advanced machine learning techniques and the challenges that arise, including the cold-start problem and the need for real-time processing capabilities. The review categorises existing systems into content-based filtering, sequential recommendations, and emotion detection using physiological signals.  Additionally, it emphasises the importance of context-aware recommen der systems that factor in user environments. Future research is encouraged to address limitations in accuracy, scalability, and ethical considerations while exploring multimodal approaches for more robust MRS. Ultimately, the review highlights the transformative potential of emotion-based music recommendation systems (MRS) in enhancing user interaction and personalisation with digital music platforms.},
}