Article: MFA: Web API recommendation based on service multiple feature aggregation Journal: International Journal of Computational Science and Engineering (IJCSE) 2025 Vol.28 No.3 pp.314 - 328 Abstract: As the number of web services continues to increase, it has become a challenging problem to provide developers with accurate and efficient web services that meet Mashup requirements. To solve this problem, various methods have been proposed to recommend APIs to match the needs of Mashups, and have achieved great success. However, due to the uneven quality of service descriptions, there are some challenges in feature extraction, utilisation of service meta-information, and textual requirements understanding. Therefore, we propose a Web API recommendation method (FMA) based on service multiple feature aggregation. FMA uses the attention mechanism model to mine the semantic features of similar services and enhance the features of Mashup services and Web API services. The service category is used as the basis for constructing the graph network, and multiple service features are mined and integrated through the hierarchical feature aggregation algorithm of the graph convolution network to further enhance the service features, thereby significantly improving the Web API recommendation effect. We conduct extensive experiments on a large-scale real-world dataset called ProgrammableWeb, and the results show that FMA outperforms existing baseline methods on multiple evaluation metrics. Inderscience Publishers - linking academia, business and industry through research

Title: MFA: Web API recommendation based on service multiple feature aggregation

Authors: Guobing Zou; Chunhua Zeng; Yue Zhu; Pengtao Li; Song Yang; Shengxiang Hu

Addresses: School of Computer Engineering and Science, Shanghai University, Shanghai, China ' School of Computer Engineering and Science, Shanghai University, Shanghai, China ' School of Computer Engineering and Science, Shanghai University, Shanghai, China ' School of Computer Engineering and Science, Shanghai University, Shanghai, China ' School of Computer Engineering and Science, Shanghai University, Shanghai, China ' School of Computer Engineering and Science, Shanghai University, Shanghai, China

Abstract: As the number of web services continues to increase, it has become a challenging problem to provide developers with accurate and efficient web services that meet Mashup requirements. To solve this problem, various methods have been proposed to recommend APIs to match the needs of Mashups, and have achieved great success. However, due to the uneven quality of service descriptions, there are some challenges in feature extraction, utilisation of service meta-information, and textual requirements understanding. Therefore, we propose a Web API recommendation method (FMA) based on service multiple feature aggregation. FMA uses the attention mechanism model to mine the semantic features of similar services and enhance the features of Mashup services and Web API services. The service category is used as the basis for constructing the graph network, and multiple service features are mined and integrated through the hierarchical feature aggregation algorithm of the graph convolution network to further enhance the service features, thereby significantly improving the Web API recommendation effect. We conduct extensive experiments on a large-scale real-world dataset called ProgrammableWeb, and the results show that FMA outperforms existing baseline methods on multiple evaluation metrics.

Keywords: Web API; Mashup service; API recommendation; multiple feature aggregation; attention mechanism.

DOI: 10.1504/IJCSE.2025.146072

International Journal of Computational Science and Engineering, 2025 Vol.28 No.3, pp.314 - 328

Received: 27 Apr 2024
Accepted: 31 May 2024
Published online: 06 May 2025 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article

Title: MFA: Web API recommendation based on service multiple feature aggregation

Keep up-to-date