基于社会化媒体情境的多维协同智能推荐

针对传统协同智能推荐技术的冷启动、数据稀缺性问题,为提高推荐算法的效率和准确性,提出一种基于社会化媒体情境的多维智能推荐算法模型。该模型将目标用户的属性特征、行为特征考虑到社会化媒体情境信息中,并动态实时捕捉用户在不同社会化媒体情境下的偏好倾向,利用联机分析处理(OLAP)技术对多维数据进行处理。该模型将用户间的社会化关系和所处的政治经济环境视为衡量用户相似的重要指标,同时使用皮尔森系数和云模型来计算用户间各特征的相似度,并以此为推荐基础向用户呈现更个性化和定制化的推荐结果。实验结果表明,该模型的推荐结果的平均绝对误差明显小于传统的协同智能推荐和单纯的基于云模型推荐技术。

Multidimensional collaborative intelligence recommendation based on social media context

In allusion to the problem of cold start technology and data scarcity in the traditional collaborative intelligence recommendation technology, in order to improve the efficiency and accuracy of recommendation algorithm, multidimensional collaborative intelligence recommendation based on social media context was proposed. In this model, the feature attributes and behavioral characteristics of the target users were considered into the information of social media context, users' interests in different social media context were dynamically captured in real-time, and OnLine Analytical Processing (OLAP) technology was used to process multidimensional data. The social relationship between users and the political and economic environment were regarded as an important indicator, then, the similarity between users were calculated using Pearson coefficient and cloud model, to get personalized and customized recommendation results. The experimental results show that the average absolute error of the model is significantly less than traditional collaborative intelligent recommendation and simple recommendation technology based on cloud model.