During software development, developers often need appropriate but unfamiliar APIs to implement a specific functionality. Under such circumstances, developers tend to leverage search tools to seek for the relevant APIs. However, there are always semantic gaps between query words and APIs, which negatively affects the performance of these tools. In this study, we introduce Glo-APIRec, a method that combines global semantics with local context to estimate the semantic relevance between query words and APIs to recommend APIs. In this method, the Transformer model is employed to obtain global semantics, while the Word2Vec model is utilized to capture local context using a fixed-size window. First, Glo-APIRec collects millions of Java projects from GitHub to construct the corpus. Afterward, a set of tuples consisting of words and APIs is built by extracting comments and API sequences from the source code files. Finally, Transformer is employed to capture long distance semantics about API sequences and code comments. Meanwhile, Word2Vec is used to generate word vectors to capture the local context by introducing the random shuffling strategy to break the positions of words and APIs in the tuples. We evaluate the performance of Glo-APIRec with 30 sentence-level queries. Experimental results show that Glo-APIRec can achieve 0.600 in terms of SuccessRate for top-1 recommendation and 0.900 for top-10 recommendation. When recommending 10 APIs, Glo-APIRec can achieve 0.480, 0.703 and 0.717 in terms of precision, Mean Reciprocal Rank ([Formula: see text]) and Normalized Discounted Cumulative Gain ([Formula: see text]), and outperforms the state-of-the-art method by 26.2%, 31.7% and 27.9%, respectively.

ABSTRACT Introduction Microservices architecture is one of the most popular design approaches in software development. The granularity smell of microservices is a topic of great interest, which often leads to a degradation in the quality of the microservices architecture, so it needs to be eliminated through architecture refactoring. Existing research on architecture refactoring to address granularity smells in microservices is limited, with a lack of consideration for the semantic information of business logic, and suggestions for microservice refactoring rely too much on manual experience and lack standardized descriptions. Objectives This paper aims to provide a novel approach for refactoring granularity smells in microservice architectures, addressing the existing shortcomings in considering semantic information of microservice business logic, the reliance on empirical experience for refactoring suggestions, and the lack of standardized suggestions for refactoring. Methods This paper introduces a novel method for refactoring granularity smells in microservices architecture based on business topic clusters, named ASRMG. This method extracts business topic clusters from the business logic code of interfaces, thereby defining the cohesion and coupling semantics of the system. It then employs an enhanced genetic algorithm for refactoring the microservices system, using a refactoring pattern database to automate the generation of fine‐grained refactoring suggestions. Results Experiments conducted on five open‐source microservices systems of varying scales and domains achieved a 99.24% elimination rate of granularity smells, with cohesion metrics improving by an average of 60.19% and coupling metrics reducing by an average of 15.32%, indicating a significant enhancement in the quality of microservice architecture. Conclusion This paper introduces a novel method for refactoring and evaluating microservice systems, named ASRMG. ASRMG extracts business topic clusters from the code of microservice systems and refines the evaluation method for refactored microservice, and proposes an automated method for generating refactoring suggestions for granularity smells, enhancing the efficiency and quality of architecture smell refactoring.

With the explosion in the number of mobile applications (apps), it becomes increasingly difficult to find a suitable app that aligns with user’s needs and preferences. Recommender systems help simplify this process as they have done in the field of e-commerce. However traditional recommendation methods suffer from poor performance, if their designs are not well tailored to the specific characteristics of mobile application. In fact, when recommending apps, their categories play a sensitive role. Meanwhile, recently emerged deep learning-based methods come with high computational costs, limiting their applicability in the lightweight mobile scenarios. To address these issues, in this paper, we propose a heterogeneous graph collaborative filtering approach applied to app recommendations. Firstly, we propose a review processing method that can effectively capture the features of users, apps and categories through reviews and likes. Then, we build a heterogeneous graph containing multiple nodes such as users, apps and categories, and further learn the latent features and complex relationships of nodes through lightweight graph convolution operations. Finally, we predict the apps for users by node embeddings. The extensive experimental results based on real dataset demonstrate the proposed model has achieved significant improvement in recommendation performance compared with the baselines.