Xiangping Zhang
Xiangping Zhang has a total of 11 co-authors. Here are the top co-authors by number of shared publications:
Jianxun Liu
School of Computer Science and Engineering, Hunan University of Science and Technology, Xiangtan, China
4 shared publications- Jianxun Liu
Key Lab. for Services Computing and Novel Software Technology Hunan University of Science and Technology Xiangtan China
2 shared publications Min Shi
Harvard Ophthalmology AI Lab Harvard Medical School Boston Massachusetts USA
2 shared publications- Buqing Cao
Hunan University of Science and Technology
1 shared publication Haize Hu
School of Computer Science and Engineering, Hunan University of Science and Technology, Xiangtan, China
1 shared publication- Min Shi
School of Computing and Informatics, University of Louisiana at Lafayette, Lafayette, LA, USA
1 shared publication
Latest Publications
- 28 March 2026
- Published by World Scientific Pub Co Pte Ltd in International Journal of Software Engineering and Knowledge Engineering
- Vol. 36 (13) , 1901-1926
Estimating the Degree of User Contribution in App from User Feedback and Developers Update Logs
Apps have become an inseparable part of people’s daily lives. However, in the extremely fierce market competition, apps lacking recognition among users are susceptible to elimination. Therefore, developers must quickly and accurately capture, understand and adopt the general user requirements to effectively strategize and promote their apps’ organized and healthy evolution. In this study, we refer to the proportion of general user requirements adopted by developers during app evolution as the degree of user contribution, assisting app developers or software engineering researchers in measuring or gaining insight into the evolution of their apps. In this paper, we propose a quantitative analysis approach based on temporal association perception. The main idea is to consider valid user reviews as user requirements and app update logs as developer responses. We then mine and analyze the pairwise and temporal relationships that exist between the two through textual computation, thus quantifying the user contribution from them. To train and evaluate the approach proposed in this paper, and get the proportion of user requirements adopted by developers in the actual development process, we collect 2489 app update logs and 42,37,031 user reviews of 5 apps from Apple App Store and also conduct a questionnaire survey with app developers in mainland China. Experimental results demonstrate the effectiveness of the approach, and the quantified user contributions for the 5 apps in this study ranged from 16.6% to 43.2%. Moreover, according to feedback from developers, the degree of user contribution quantified in this paper is consistent with the developer’s development experience at an aggregate level. The approach proposed in this paper, and the empirical research conducted, provide a new perspective for app developers and software engineering researchers to assess the evolution of apps.
- 28 March 2026
- Published by World Scientific Pub Co Pte Ltd in International Journal of Software Engineering and Knowledge Engineering
- Vol. 36 (13) , 1901-1926
Estimating the Degree of User Contribution in App from User Feedback and Developers Update Logs
Apps have become an inseparable part of people’s daily lives. However, in the extremely fierce market competition, apps lacking recognition among users are susceptible to elimination. Therefore, developers must quickly and accurately capture, understand and adopt the general user requirements to effectively strategize and promote their apps’ organized and healthy evolution. In this study, we refer to the proportion of general user requirements adopted by developers during app evolution as the degree of user contribution, assisting app developers or software engineering researchers in measuring or gaining insight into the evolution of their apps. In this paper, we propose a quantitative analysis approach based on temporal association perception. The main idea is to consider valid user reviews as user requirements and app update logs as developer responses. We then mine and analyze the pairwise and temporal relationships that exist between the two through textual computation, thus quantifying the user contribution from them. To train and evaluate the approach proposed in this paper, and get the proportion of user requirements adopted by developers in the actual development process, we collect 2489 app update logs and 42,37,031 user reviews of 5 apps from Apple App Store and also conduct a questionnaire survey with app developers in mainland China. Experimental results demonstrate the effectiveness of the approach, and the quantified user contributions for the 5 apps in this study ranged from 16.6% to 43.2%. Moreover, according to feedback from developers, the degree of user contribution quantified in this paper is consistent with the developer’s development experience at an aggregate level. The approach proposed in this paper, and the empirical research conducted, provide a new perspective for app developers and software engineering researchers to assess the evolution of apps.
- 14 February 2025
- Published by Springer Nature in Applied Intelligence
- Vol. 55 (7) , 1-17
A code completion approach combining pointer network and Transformer-XL network
- 14 February 2025
- Published by Springer Nature in Applied Intelligence
- Vol. 55 (7) , 1-17
A code completion approach combining pointer network and Transformer-XL network
- 7 February 2024
- Published by Wiley in Journal of Software: Evolution and Process
- Vol. 36 (7)
GRRLN: Gated Recurrent Residual Learning Networks for code clone detection
Code clone detection is a critical problem in software development and maintenance domains. It aims to identify functionally identical or similar code fragments within an application. Existing works formulate the code clone detection task as a binary classification problem which predicts a code pair as a clone or not based on a pre‐defined threshold. In reality, there are various types of code clone subject to the degree of how a pair of code fragments are similar to each other. To investigate the effect of different code clone detection manners on the clone detection result, we propose Gated Recurrent Residual Learning Networks (GRRLN), a novel neural network model for code clone detection. To train GRRLN, we first represent each code fragment as a statement‐level tree sequence derived from the whole abstract syntax tree (AST). Then, a gated recurrent neural network with residual connections is adopted to fully extract the semantics of all individual statement trees together with their dependency relationships across the input statement sequence. Finally, the output representations of code fragments by GRRLN are used for similarity calculation and clone detection. We evaluate GRRLN using two real‐world datasets for code clone detection and clone type classification. Experiments show that GRRLN achieves promising and compelling results and meanwhile needs significantly less time and memory consumption compared with the state‐of‐the‐art methods.
- 7 February 2024
- Published by Wiley in Journal of Software: Evolution and Process
- Vol. 36 (7)
GRRLN: Gated Recurrent Residual Learning Networks for code clone detection
Code clone detection is a critical problem in software development and maintenance domains. It aims to identify functionally identical or similar code fragments within an application. Existing works formulate the code clone detection task as a binary classification problem which predicts a code pair as a clone or not based on a pre‐defined threshold. In reality, there are various types of code clone subject to the degree of how a pair of code fragments are similar to each other. To investigate the effect of different code clone detection manners on the clone detection result, we propose Gated Recurrent Residual Learning Networks (GRRLN), a novel neural network model for code clone detection. To train GRRLN, we first represent each code fragment as a statement‐level tree sequence derived from the whole abstract syntax tree (AST). Then, a gated recurrent neural network with residual connections is adopted to fully extract the semantics of all individual statement trees together with their dependency relationships across the input statement sequence. Finally, the output representations of code fragments by GRRLN are used for similarity calculation and clone detection. We evaluate GRRLN using two real‐world datasets for code clone detection and clone type classification. Experiments show that GRRLN achieves promising and compelling results and meanwhile needs significantly less time and memory consumption compared with the state‐of‐the‐art methods.
- Open Access
Estimation of the User Contribution Rate by Leveraging Time Sequence in Pairwise Matching function-point between Users Feedback and App Updating Log
Mobile applications have become an inseparable part of people's daily life. Nonetheless, the market competition is extremely fierce, and apps lacking recognition among most users are susceptible to market elimination. To this end, developers must swiftly and accurately apprehend the requirements of the wider user base to effectively strategize and promote their apps' orderly and healthy evolution. The rate at which general user requirements are adopted by developers, or user contribution, is a very valuable metric that can be an important tool for app developers or software engineering researchers to measure or gain insight into the evolution of app requirements and predict the evolution of app software. Regrettably, the landscape lacks refined quantitative analysis approaches and tools for this pivotal indicator. To address this problem, this paper exploratively proposes a quantitative analysis approach based on the temporal correlation perception that exists in the app update log and user reviews, which provides a feasible solution for quantitatively obtaining the user contribution. The main idea of this scheme is to consider valid user reviews as user requirements and app update logs as developer responses, and to mine and analyze the pairwise and chronological relationships existing between the two by text computing, thus constructing a feasible approach for quantitatively calculating user contribution. To demonstrate the feasibility of the approach, this paper collects data from four Chinese apps in the App Store in mainland China and one English app in the U.S. region, including 2,178 update logs and 4,236,417 user reviews, and from the results of the experiment, it was found that 16.6%-43.2% of the feature of these apps would be related to the drive from the online popular user requirements.
Open AccessEstimation of the User Contribution Rate by Leveraging Time Sequence in Pairwise Matching function-point between Users Feedback and App Updating Log
Mobile applications have become an inseparable part of people's daily life. Nonetheless, the market competition is extremely fierce, and apps lacking recognition among most users are susceptible to market elimination. To this end, developers must swiftly and accurately apprehend the requirements of the wider user base to effectively strategize and promote their apps' orderly and healthy evolution. The rate at which general user requirements are adopted by developers, or user contribution, is a very valuable metric that can be an important tool for app developers or software engineering researchers to measure or gain insight into the evolution of app requirements and predict the evolution of app software. Regrettably, the landscape lacks refined quantitative analysis approaches and tools for this pivotal indicator. To address this problem, this paper exploratively proposes a quantitative analysis approach based on the temporal correlation perception that exists in the app update log and user reviews, which provides a feasible solution for quantitatively obtaining the user contribution. The main idea of this scheme is to consider valid user reviews as user requirements and app update logs as developer responses, and to mine and analyze the pairwise and chronological relationships existing between the two by text computing, thus constructing a feasible approach for quantitatively calculating user contribution. To demonstrate the feasibility of the approach, this paper collects data from four Chinese apps in the App Store in mainland China and one English app in the U.S. region, including 2,178 update logs and 4,236,417 user reviews, and from the results of the experiment, it was found that 16.6%-43.2% of the feature of these apps would be related to the drive from the online popular user requirements.
- 26 July 2023
- Published by Elsevier in Journal of Parallel and Distributed Computing
- Vol. 181
A parallel deep learning-based code clone detection model
- 26 July 2023
- Published by Elsevier in Journal of Parallel and Distributed Computing
- Vol. 181
A parallel deep learning-based code clone detection model
- 1 September 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 34-43
Word Embedding-based Web Service Representations for Classification and Clustering
Web services classification and clustering rely on discriminative representations of service functional semantics. Most existing topic-based methods for Web service representation simply leverage word co-occurrence relations, which may cause sub-optimal results for some specific-tasks due to the sparse features in the short service descriptions. Despite sparse and discrete word statistical features, other information such as word-topic and word-tag relationships can be utilized to accurately represent Web services. In this paper, we propose a novel word embedding-based approach for representing Web services. First, we use Word2vec to generate word embeddings from service descriptions. Then, the word-topic and word-tag relationships are preserved for Web service representation generation via the topic-weighted and tag-weighted word embedding stages based on Gaussian Mixture Model and Bayesian rule, respectively. Experiments and validations on the real-world dataset demonstrate that our method outperforms the state of the arts by a wide margin on service classification and clustering.
- 1 September 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 34-43
Word Embedding-based Web Service Representations for Classification and Clustering
Web services classification and clustering rely on discriminative representations of service functional semantics. Most existing topic-based methods for Web service representation simply leverage word co-occurrence relations, which may cause sub-optimal results for some specific-tasks due to the sparse features in the short service descriptions. Despite sparse and discrete word statistical features, other information such as word-topic and word-tag relationships can be utilized to accurately represent Web services. In this paper, we propose a novel word embedding-based approach for representing Web services. First, we use Word2vec to generate word embeddings from service descriptions. Then, the word-topic and word-tag relationships are preserved for Web service representation generation via the topic-weighted and tag-weighted word embedding stages based on Gaussian Mixture Model and Bayesian rule, respectively. Experiments and validations on the real-world dataset demonstrate that our method outperforms the state of the arts by a wide margin on service classification and clustering.