基于情感识别方法的推荐系统(英文)

RSER:A Recommender System Based on Emotion Recognition Methods

随着电子商务的高速发展,推荐系统已成为广大客户选择合意商品的重要工具。目前应用的电子商务推荐方法,依赖于客户的购物素养;而客户在购物中,更重要的影响因素是人的情感。针对这种情况,提出了一种新型的、基于客户情感的推荐系统;给出了该系统的模型、数据结构等。该系统的核心是商品和情感二维叠加空间。实验证明,该系统具有较高的推荐精度和检索速度。

With the growth of E-commerce, the development of recommender systems is helpful for users to select desirable products from all kinds of them. The existing e-commerce recommender approaches are based on a user＇s preference on music. However, sometimes, it might better meet users＇ requirement to recommend products according to emotions. In order to deal with them, a novel framework model for emotion-based e-com- merce recommender systems is proposed. The core of the recommender system is the construction of the product vs customer emotion model by two-dimensional overlap spaces, which plays an important role in conveying emo- tions in products. Then the product feature extraction and propose some related matching algorithms for the con- struction of product vs customer emotion model is researched. The system model, data structures and so on are given in our paper. At last, experimental and analytical result shows the proposed emotion-based music recom- mendation achieves higher accuracy and faster retrieval speed.