融合面部表情和社交网络的音乐情境推荐
Incorporating Facial Expressions and Social Networks for Musical Contextual Recommendations

DOI: 10.12677/CSA.2019.95096, PP. 855-863

Keywords: 面部表情，社交网络，情境推荐，用户情绪，音乐
Facial Expression, Social Network, Situational Recommendation, User Sentiment, Music

Full-Text   Cite this paper   Add to My Lib

Abstract:

在数字音乐快速发展的同时，人们也从音乐匮乏的时代走向音乐过载的时代，越来越多的用户在使用数字音乐时，希望从种类繁多的音乐中得到其当前喜欢的推荐。不同于其他商品推荐，音乐的消费使用与用户的情绪高度关联。针对这些问题，提出了一种融合面部表情和社交网络的音乐推荐方法。该方法利用社交网络历史行为分析建立用户知识模型，再利用目前的面部识别技术，结合用户的面部表情去判断用户当前的情绪。在现有的音乐推荐方法基础上，加入或过滤出情绪分类以及与用户情绪符合的推荐结果。实验结果证明了情绪因素会对音乐偏好产生影响，提出的融合面部表情和社交网络的音乐情境推荐方法，比其他不考虑用户情绪单单基于内容推荐或者协同过滤推荐的推荐方法略好且稳定，具有较好的实际应用效果。
At the same time as the rapid development of digital music, people are moving from the era of lack of music to the era of music overload. More and more users are hoping to get their current favorite recommendations from a wide variety of music when using digital music. Unlike other product recommendations, the consumption of music is highly correlated with the user’s mood. In response to these problems, a music recommendation method combining facial expressions and social networks is proposed. The method uses social network historical behavior analysis to establish a user knowledge model, and then uses the current facial recognition technology to combine the user’s facial expression to determine the user’s current mood. Based on the existing music recommendation method, the emotion classification and the recommendation result in accordance with the user’s emotion are added or filtered. The experimental results show that emotional factors have an impact on music preferences. The proposed music context recommendation method combining facial expressions and social networks is slightly better and more stable than other recommendation methods based on content recommendation or collaborative filtering. It has a better practical application result.

References

[1]	郭博林. 基于大数据分析的音乐个性化推荐系统应用研究[D]: [硕士学位论文]. 成都: 电子科技大学, 2018.
[2]	于岚. 基于协同过滤的个性化推荐系统研究[D]: [硕士学位论文]. 西安: 西安电子科技大学, 2017.
[3]	陈唯. 基于用户情境的实时兴趣模型研究及应用[D]: [硕士学位论文]. 成都: 成都理工大学, 2017.
[4]	康赵楠. 基于本体建模和情境感知的音乐推荐方法研究[D]: [硕士学位论文]. 宁波: 宁波大学, 2017.
[5]	王小欢. 基于情境感知的网络音乐个性推荐研究[D]: [硕士学位论文]. 北京: 北京交通大学, 2017.
[6]	Shin, I.-H., Cha, J., Cheon, G.W., Lee, C., Lee, S.Y., Yoon, H.-J. and Kim, H.C. (2014) Automatic Stress-Relieving Music Recommendation Sys-tem Based on Photoplethysmography-Derived Heart Rate Variability Analysis. 36th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, Chicago, 26-30 August 2014, 6402-6405.
[7]	Deger, A., Yusuf, Y. and Mustafa, E.K. (2018) Emotion Based Music Recommendation System Using Wearable Physiological Sensors. IEEE Transactions on Consumer Electronics, 64, 196-203.
[8]	Shan, M.K., Kuo, F.F., Chiang, M.F., et al. (2009) Emotion-Based Music Recommendation by Affininty Discovery from Film Music. Expert Systems with Applications, 36, 7666-7674. https://doi.org/10.1016/j.eswa.2008.09.042
[9]	Yoon, K., Lee, J. and Kim, M.U. (2012) Music Rec-ommendation System Using Emotion Triggering Low-Level Features. IEEE Transactions on Consumer Electronics, 58, 612-618. https://doi.org/10.1109/TCE.2012.6227467
[10]	Sunitha, M. and Adilakshmi, T. (2018) Music Recom-mendation System with User-Based and Item-Based Collaborative Filtering Technique. In: Perez, G.M.E., Mishra, K.K., Tiwari, S. and Trivedi, M.C., Eds., Networking Communication and Data Knowledge Engineering, Springer, Singapore, 267-278. https://doi.org/10.1007/978-981-10-4585-1_22
[11]	Yepes, F.A., López, V.F., Pérez-Marcos, J., et al. (2018) Listen to This: Music Recommendation Based on One-Class Support Vector Machine. International Conference on Hybrid Artificial Intelligence Systems, Oviedo, 20-22 June 2018, 467-478. https://doi.org/10.1007/978-3-319-92639-1_39
[12]	Chen, H.C. and Chen, A.L.P. (2001) A Music Recommenda-tion System Based on Music Data Grouping and User Interests. 10th International Conference on Information & Knowledge Management, Atlanta, 5-10 October 2001, 231-238. https://doi.org/10.1145/502585.502625
[13]	Bu, J., Tan, S., Chen, C., et al. (2010) Music Recommendation by Unified Hypergraph: Combining Social Media Information and Music Content. ACM International Conference on Mul-timedia, Firenze, 25-29 October 2010, 391-400. https://doi.org/10.1145/1873951.1874005
[14]	Wang, D., Deng, S. and Xu, G. (2017) Sequence-Based Con-text-Aware Music Recommendation. Information Retrieval Journal, 21, 230-252.
[15]	Lee, J., Lee, K., Park, J., et al. (2018) Deep Content-User Embedding Model for Music Recommendation.
[16]	张瑞旸. 基于场景变化的实时音乐推荐系统[J]. 通讯世界, 2018(9): 2.
[17]	李瑞敏. 基于社会化网络的个性化音乐推荐算法研究[D]: [硕士学位论文]. 大连: 大连理工大学, 2013.
[18]	邓腾飞. 个性化音乐推荐系统的研究[D]: [硕士学位论文]. 广州: 华南理工大学, 2018.
[19]	琚春华, 黄治移, 鲍福光. 融入音乐子人格特质和社交网络行为分析的音乐推荐方法[J]. 电信科学, 2015, 31(10): 122-130.
[20]	文豪. 基于张量分解并融合上下文的推荐算法研究与实现[D]: [硕士学位论文]. 北京: 北京邮电大学, 2018.

Full-Text