Category-Aware API Clustering and Distributed Recommendation for Automatic Mashup Creation
Category-Aware API Clustering and Distributed Recommendation for Automatic Mashup Creation
复制标题
DOI：
10.1109/tsc.2014.2379251
复制
发表时间：
2015-09
影响因子：
8.1
通讯作者：
Bofei Xia;Yushun Fan;Wei Tan;Keman Huang;Jia Zhang;Cheng Wu
中科院分区：
文献类型：
--
作者：
Bofei Xia;Yushun Fan;Wei Tan;Keman Huang;Jia Zhang;Cheng Wu
Mashup已经成为一种很有前途的方式，允许开发人员组合现有的API（服务）来创建新的或增值的服务。随着Internet上发布的服务数量的迅速增加，用于自动mashup创建的服务推荐获得了很大的动力。由于mashup本质上需要具有不同功能的服务，因此推荐结果应该包含来自不同类别的服务。然而，大多数现有的推荐方法只在一个单一的列表中的所有候选服务的排名，这有两个缺陷。首先，不考虑服务属于哪个类别而对服务进行排名可能会导致无意义的服务排名并影响推荐准确性。其次，mashup开发人员并不总是清楚他们需要哪些服务类别，以及哪些类别中的服务在mashup创建中更好地协作。如果没有明确地推荐哪些服务类别与mashup创建相关，mashup开发人员仍然很难在混合排名列表中选择合适的服务，这降低了推荐的用户友好性。为了克服这些不足，提出了一种新的类别感知的服务聚类和分布式推荐方法自动混搭创建。首先，提出了一种基于主题模型的Kmeans变体（vKmeans）方法，用于增强服务分类，为推荐提供依据。其次，在vKmeans的基础上，结合机器学习和协同过滤技术，提出了一个服务类别相关性排序（SCRR）模型，用于分解mashup需求，并显式预测相关服务类别。最后，一个类别感知的分布式服务推荐（CDSR）模型，这是基于分布式机器学习框架，预测服务的排名顺序在每个类别。在真实数据集上的实验证明，该方法不仅在推荐准确率上有了显著的提高，而且提高了推荐结果的多样性。
Mashup has emeraged as a promising way to allow developers to compose existed APIs (services) to create new or value-added services. With the rapid increasing number of services published on the Internet, service recommendation for automatic mashup creation gains a lot of momentum. Since mashup inherently requires services with different functions, the recommendation result should contain services from various categories. However, most existing recommendation approaches only rank all candidate services in a single list, which has two deficiencies. First, ranking services without considering to which categories they belong may lead to meaningless service ranking and affect the recommendation accuracy. Second, mashup developers are not always clear about which service categories they need and services in which categories cooperate better for mashup creation. Without explicitly recommending which service categories are relevant for mashup creation, it remains difficult for mashup developers to select proper services in a mixed ranking list, which lower the user friendliness of recommendation. To overcome these deficiencies, a novel category-aware service clustering and distributed recommending method is proposed for automatic mashup creation. First, a Kmeans variant(vKmeans) method based on topic model Latent Dirichlet Allocation is introduced for enhancing service categorization and providing a basis for recommendation. Second, on top of vKmeans, a service category relevance ranking (SCRR) model, which combines machine learning and collaborative filtering, is developed to decompose mashup requirements and explicitly predict relevant service categories. Finally, a category-aware distributed service recommendation (CDSR) model, which is based on a distributed machine learning framework, is developed for predicting service ranking order within each category. Experiments on a real-world dataset have proved that the proposed approach not only gains significant improvement at precision rate but also enhances the diversity of recommendation results.