Recommendation system based on user emotions in e-markerting
Article Sidebar
Main Article Content
DOI:
https://doi.org/10.17979/redma.2025.29.2.12767Abstract
This work proposes a strategy for integrating an emotion recognition system into an e-marketing recommendation system. The system uses the mobile device’s camera (with the user’s authorization) to capture facial images and, via the Mini‑Xception neural network, identifies emotions. The hybrid recommendation system combines a content-based approach, which uses TF-IDF and cosine similarity, with one based on popularity. A temporal decay scheme is applied to weight more recent emotional detections, and the emotional level is normalized to facilitate comparison across users. The results show 92% accuracy in emotion recognition. The recommendation system outputs a list of products tailored to the emotion levels computed during the session.
Keywords:
Article Details
References
Afoudi, Y., Lazaar, M., and Al Achhab, M. (2021). Hybrid recommendation system combined content-based filtering and collaborative prediction using artificial neural network. Simulation Modelling Practice and Theory, 113, Article 102375.
https://doi.org/10.1016/j.simpat.2021.102375
Arriaga, O., Valdenegro-Toro, M., and Plöger, P. (2017). Real-time convolutional neural networks for emotion and gender classification. arXiv. https://doi.org/10.48550/arXiv.1710.07557
Bagherzadeh, S., Norouzi, M. R., Hampa, S. B., Ghasri, A., Kouroshi, P. T., Hosseininasab, S., ... and Nasrabadi, A. M. (2024). A subject-independent portable emotion recognition system using synchrosqueezing wavelet transform maps of EEG signals and ResNet-18. Biomedical Signal Processing and Control, 90, Article: 105875. https://doi.org/10.1016/j.bspc.2023.105875
Bandyopadhyay, S., Thakur, S. S., and Mandal, J. K. (2021, November). Online recommendation system using human facial expression based emotion detection: a proposed method. In En Mandal, J.K., Buyya, R. y De, D. (Eds) Proceedings of International Conference on Advanced Computing Applications: ICACA 2021 (pp. 459-468). Springer Singapore. https://doi.org/10.1007/978-981-16-5207-3_38
Ekman, P. (1992). An argument for basic emotions. Cognition & Emotion, 6(3-4), 169-200. https://doi.org/10.1080/02699939208411068
Fernandez, A. G., y Ygnacio, M. A. C. (2023). Una revisión de métodos, técnicas y algoritmos para sistemas de recomendación de productos tecnológicos. Interfases, (18), 255-280. https://doi.org/10.26439/interfases2023.n018.6357
Luque-Ortiz, S. (2021). Estrategias de marketing digital utilizadas por empresas del retail deportivo. Revista CEA, 7(13). https://doi.org/10.22430/24223182.1650
Manimaran, S., Saranya, S. R., Selvam, N., and Sherine, S. B. (2025). Emotion-Based Music Recommendation System Using Facial Expression Recognition. American Journal of Engineering, Mechanics and Architecture (2993-2637), 3(3), 174-190. https://grnjournal.us/index.php/AJEMA/article/view/7186
Peeters, R., Der, R. C., and Bizer, C. (2023). WDC Products: a multi-dimensional entity matching benchmark. https://webdatacommons.org/largescaleproductcorpus/wdc-products/.
Rivero A., D. (2023). Sistemas de recomendación: enfoque y técnicas. En D. Rivero A., F. Rivas E., y S. Arciniegas A. (Eds). Gestión, infraestructura y aplicaciones en sistemas de tecnología de información (pp. 53-77). Centro de Publicaciones PUCE.
Ruan, T., Liu, Q., and Chang, Y. (2025). Digital media recommendation system design based on user behavior analysis and emotional feature extraction. PLoS One 20 (5), Article e0322768. https://doi.org/10.1371/journal.pone.0322768
Singh, K. K., and Dembla, P. (2023). A study on emotion analysis and music recommendation using transfer learning. Journal of Computer Science, 19 (06), 707-726. https://doi.org/10.3844/jcssp.2023.707.726
Sreekala, K. (2020). Popularity based recommendation system. International Journal of Engineering and Advanced Technology (IJEAT), 9 (3), 1561-1566. https://doi.org/10.35940/ijeat.B4660.029320
Tewari, A. S. (2020). Generating items recommendations by fusing content and user-item based collaborative filtering. Procedia Computer Science, 167, 934-1940. https://doi.org/10.1016/j.procs.2020.03.215
Tkalcic, M., Kosir, A., and Tasic, J. (2011). Affective recommender systems: the role of emotions in recommender systems. The RecSys 2011 Workshops-Decisions@ RecSys 2011 and UCERSTI-2: human decision making in recommender systems; user-centric evaluation of recommender systems and their interfaces-2, 811, 9-13.
Won, H. M., Heo, Y. S., and Kwak, N. (2023). Image recommendation system based on environmental and human face information. Sensors, 23 (11), Article 5304. https://doi.org/10.3390/s23115304