Jianshan Sun
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Jianshan Sun has a total of 77 co-authors. Here are the top co-authors by number of shared publications:
- Yuanchun Jiang
School of Management, Hefei University of Technology, Hefei, China
13 shared publications - Yezheng Liu
School of Management, Hefei University of Technology, Hefei, China
10 shared publications - Kun Yuan
School of Management, Hefei University of Technology, Hefei, China
9 shared publications Yezheng Liu
School of Management, Hefei University of Technology, Hefei, China
4 shared publications- Dongyang Li
School of Management, Hefei University of Technology, Hefei, China
3 shared publications - Jie Cao
Hefei University of Technology
3 shared publications
Latest Publications
- 10 November 2026
- Published by Institute for Operations Research and the Management Sciences (INFORMS) in INFORMS Journal on Computing
Code and Data Repository for Reinforcement Learning-based Graph Downsampling for Social Recommendation
Standalone code for Reinforcement Learning-based Graph Downsampling for Social Recommendation, by Dongyang Li, Jianshan Sun, Xin Li, Chongming Gao, Fuli Feng, and Kun Yuan. This package contains the Douban-Book experiment and is prepared for the IJOC archive. The software is distributed under the MIT License.
- 10 November 2026
- Published by Institute for Operations Research and the Management Sciences (INFORMS) in INFORMS Journal on Computing
Code and Data Repository for Reinforcement Learning-based Graph Downsampling for Social Recommendation
Standalone code for Reinforcement Learning-based Graph Downsampling for Social Recommendation, by Dongyang Li, Jianshan Sun, Xin Li, Chongming Gao, Fuli Feng, and Kun Yuan. This package contains the Douban-Book experiment and is prepared for the IJOC archive. The software is distributed under the MIT License.
- 29 July 2026
- Published by Springer Nature in Information Systems Frontiers
- p. 1-22
A Human-Centric Framework for Fair Job Recommendation Leveraging Generative AI and Data Augmentation
- 29 July 2026
- Published by Springer Nature in Information Systems Frontiers
- p. 1-22
A Human-Centric Framework for Fair Job Recommendation Leveraging Generative AI and Data Augmentation
- 18 July 2026
- Published by Elsevier in Decision Support Systems
- Vol. 209
Designing for persuasion: A theory-driven intent-aware explainable social recommendation system
- 18 July 2026
- Published by Elsevier in Decision Support Systems
- Vol. 209
Designing for persuasion: A theory-driven intent-aware explainable social recommendation system
- Open Access
- 20 April 2026
- Published by Association for Computing Machinery (ACM)
- p. 49-58
MGFRec: Towards Reinforced Reasoning Recommendation with Multiple Groundings and Feedback
- 20 April 2026
- Published by Association for Computing Machinery (ACM)
- p. 49-58
Open AccessMGFRec: Towards Reinforced Reasoning Recommendation with Multiple Groundings and Feedback
- 2 February 2026
- Published by Springer Nature in Scientometrics
- Vol. 131 (2) , 943-969
A deep learning-based model for patent portfolio recommendation leveraging overall and sequential features
- 2 February 2026
- Published by Springer Nature in Scientometrics
- Vol. 131 (2) , 943-969
A deep learning-based model for patent portfolio recommendation leveraging overall and sequential features
- 1 November 2025
- Published by Springer Nature
- p. 709-748
Future Prospects of Big Data in E-commerce
- Open Access
- 9 July 2025
- Published by JMIR Publications Inc. in Journal of Medical Internet Research
- Vol. 27, e66141
Developing a Framework for Online Review-Based Health Care Service Quality Assessment: Text-Mining Study
Background: With the development of online health care platforms, patient reviews have become an important source for assessing medical service quality. However, the critical aspects of quality dimensions in textual reviews remain largely unexplored. Objective: This study aims to establish a comprehensive medical service quality assessment framework by leveraging review data. Such a framework would support large service providers, such as platforms, to assess the quality of many doctors efficiently. Methods: We adopted a text-mining approach with theory-driven topic extraction from online reviews to develop a service quality assessment framework. The framework is based on topic and sentiment classification methods. We conducted an empirical analysis to assess the validity of the framework. Specifically, we examined if patients’ sentiments regarding our extracted dimensions affect demand (number of consultation requests) due to quality signals reflected in these dimensions. Results: We develop a 5-dimensional health care service quality framework (HSQ-5D model). In the empirical study, patient demand is affected by these dimensions, including expertise (coefficient=1.12; P<.001), service delivery process (coefficient=5.60; P<.001), attitude (coefficient=0.82; P<.001), empathy (coefficient=2.65; P<.001), and outcome (coefficient=0.26; P<.001; through patients’ perceived quality from reviews). The 5 dimensions can explain 85.52% of the variance in patient demand, while all information from online reviews can explain 85.67%. The results show the validity and the potential practical value of the proposed HSQ-5D model. Conclusions: This study explores how online reviews can be used to evaluate health care services, offering significant implications for health care management. Theoretically, we extend existing service quality frameworks by integrating text-mining analysis of online reviews, thereby enhancing the understanding of service quality assessment in the digital health context. Practically, the framework can allow health care platforms to identify and reveal doctors’ service quality to reduce patients’ information asymmetry and strengthen patient-provider relationships, ultimately contributing to a more effective and patient-centered health care system.
- 9 July 2025
- Published by JMIR Publications Inc. in Journal of Medical Internet Research
- Vol. 27, e66141
Open AccessDeveloping a Framework for Online Review-Based Health Care Service Quality Assessment: Text-Mining Study
Background: With the development of online health care platforms, patient reviews have become an important source for assessing medical service quality. However, the critical aspects of quality dimensions in textual reviews remain largely unexplored. Objective: This study aims to establish a comprehensive medical service quality assessment framework by leveraging review data. Such a framework would support large service providers, such as platforms, to assess the quality of many doctors efficiently. Methods: We adopted a text-mining approach with theory-driven topic extraction from online reviews to develop a service quality assessment framework. The framework is based on topic and sentiment classification methods. We conducted an empirical analysis to assess the validity of the framework. Specifically, we examined if patients’ sentiments regarding our extracted dimensions affect demand (number of consultation requests) due to quality signals reflected in these dimensions. Results: We develop a 5-dimensional health care service quality framework (HSQ-5D model). In the empirical study, patient demand is affected by these dimensions, including expertise (coefficient=1.12; P<.001), service delivery process (coefficient=5.60; P<.001), attitude (coefficient=0.82; P<.001), empathy (coefficient=2.65; P<.001), and outcome (coefficient=0.26; P<.001; through patients’ perceived quality from reviews). The 5 dimensions can explain 85.52% of the variance in patient demand, while all information from online reviews can explain 85.67%. The results show the validity and the potential practical value of the proposed HSQ-5D model. Conclusions: This study explores how online reviews can be used to evaluate health care services, offering significant implications for health care management. Theoretically, we extend existing service quality frameworks by integrating text-mining analysis of online reviews, thereby enhancing the understanding of service quality assessment in the digital health context. Practically, the framework can allow health care platforms to identify and reveal doctors’ service quality to reduce patients’ information asymmetry and strengthen patient-provider relationships, ultimately contributing to a more effective and patient-centered health care system.
- Open Access
- 9 April 2025
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Information Systems
- Vol. 43 (3) , 1-27
Independent or Social Driven Decision? A Counterfactual Refinement Strategy for Graph-Based Social Recommendation
Social recommendation models have traditionally relied on social homophily to enhance user preference prediction by incorporating information from socially connected friends. However, this approach neglects the diverse nature of social relationships. Some individuals with independent personalities often prioritize their own interests over friends’ advice when making purchase decisions. Conversely, those who seek advice from others are more susceptible to social influence. Moreover, the existing methods tend to overlook redundant and noisy social relationships within the network, hindering their ability to achieve accurate recommendations. In response, this article proposes a novel counterfactual method to understand the causal factors driving purchase behaviors, thereby identifying the influence of users’ friends on their purchase decisions. By answering counterfactual questions about the influence of a friend’s purchase behavior on the user’s choices, we develop a causal model to represent social influence in the network. Our proposed refinement strategy, grounded in causal inference, generates counterfactual purchase behavior and guides the refinement of the social graph. Moreover, we present tailored graph refinement methods at various levels, ensuring fine-grained improvements. Experimental results on benchmark data demonstrate that the application of our strategy to different social recommendation models significantly enhances their predictive performance. The source code has been made available on https://github.com/LDY911/CFRSSR-Code .
- 9 April 2025
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Information Systems
- Vol. 43 (3) , 1-27
Open AccessIndependent or Social Driven Decision? A Counterfactual Refinement Strategy for Graph-Based Social Recommendation
Social recommendation models have traditionally relied on social homophily to enhance user preference prediction by incorporating information from socially connected friends. However, this approach neglects the diverse nature of social relationships. Some individuals with independent personalities often prioritize their own interests over friends’ advice when making purchase decisions. Conversely, those who seek advice from others are more susceptible to social influence. Moreover, the existing methods tend to overlook redundant and noisy social relationships within the network, hindering their ability to achieve accurate recommendations. In response, this article proposes a novel counterfactual method to understand the causal factors driving purchase behaviors, thereby identifying the influence of users’ friends on their purchase decisions. By answering counterfactual questions about the influence of a friend’s purchase behavior on the user’s choices, we develop a causal model to represent social influence in the network. Our proposed refinement strategy, grounded in causal inference, generates counterfactual purchase behavior and guides the refinement of the social graph. Moreover, we present tailored graph refinement methods at various levels, ensuring fine-grained improvements. Experimental results on benchmark data demonstrate that the application of our strategy to different social recommendation models significantly enhances their predictive performance. The source code has been made available on https://github.com/LDY911/CFRSSR-Code .
- 25 January 2025
- Published by Springer Nature in World Wide Web
- Vol. 28 (1) , 1-20
Combining macro and micro: feature-driven dynamic graph learning for social media popularity prediction
- 25 January 2025
- Published by Springer Nature in World Wide Web
- Vol. 28 (1) , 1-20
Combining macro and micro: feature-driven dynamic graph learning for social media popularity prediction
- Open Access
- 18 January 2025
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Information Systems
- Vol. 43 (2) , 1-30
LLM-Enhanced Composed Image Retrieval: An Intent Uncertainty-Aware Linguistic-Visual Dual Channel Matching Model
Composed image retrieval (CoIR) involves a multi-modal query of the reference image and modification text describing the desired changes, allowing users to express image retrieval intents flexibly and effectively. The key of CoIR lies in how to properly reason the search intent from the multi-modal query. Existing work either aligns the composite embedding of the multi-modal query and the target image embedding in the visual domain through late-fusion or converts all images into text descriptions and leverage large language models (LLM) for text semantic reasoning. However, this single-modality reasoning approach fails to comprehensively and interpretably capture the users’ ambiguous and uncertain intents in the multi-modal queries, incurring the inconsistency between retrieved results and ground truth. Besides, the expensive manually annotated datasets limit the further performance improvement of CoIR. To this end, this article proposes an LLM-enhanced Intent Uncertainty-Aware Linguistic-Visual Dual Channel Matching Model (IUDC), which combines the strengths of multi-modal late-fusion and LLMs for CoIR. We first construct an LLM-based triplet augmentation strategy to generate more synthetic training triplets. Based on this, the core of IUDC consists of two matching channels: the semantic matching channel is responsible for intent reasoning on the aspect-level attributes extracted by an LLM, and the visual matching channel accounts for the fine-grained visual matching between multi-modal fusion embedding and target images. Considering the intent uncertainty presented in the multi-modal queries, we introduce Probability Distribution Encoder (PDE) to project the intents as probabilistic distributions in the two matching channels. Consequently, a mutually enhanced module is designed to share knowledge between the visual and semantic representations for better representation learning. Finally, the matching scores of two channels are added to retrieve the target image. Extensive experiments conducted on two real datasets demonstrate the effectiveness and superiority of our model. Notably, with the help of the proposed LLM-based triplet augmentation strategy, our model achieves a new record of state-of-the-art performance among all datasets.
- 18 January 2025
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Information Systems
- Vol. 43 (2) , 1-30
Open AccessLLM-Enhanced Composed Image Retrieval: An Intent Uncertainty-Aware Linguistic-Visual Dual Channel Matching Model
Composed image retrieval (CoIR) involves a multi-modal query of the reference image and modification text describing the desired changes, allowing users to express image retrieval intents flexibly and effectively. The key of CoIR lies in how to properly reason the search intent from the multi-modal query. Existing work either aligns the composite embedding of the multi-modal query and the target image embedding in the visual domain through late-fusion or converts all images into text descriptions and leverage large language models (LLM) for text semantic reasoning. However, this single-modality reasoning approach fails to comprehensively and interpretably capture the users’ ambiguous and uncertain intents in the multi-modal queries, incurring the inconsistency between retrieved results and ground truth. Besides, the expensive manually annotated datasets limit the further performance improvement of CoIR. To this end, this article proposes an LLM-enhanced Intent Uncertainty-Aware Linguistic-Visual Dual Channel Matching Model (IUDC), which combines the strengths of multi-modal late-fusion and LLMs for CoIR. We first construct an LLM-based triplet augmentation strategy to generate more synthetic training triplets. Based on this, the core of IUDC consists of two matching channels: the semantic matching channel is responsible for intent reasoning on the aspect-level attributes extracted by an LLM, and the visual matching channel accounts for the fine-grained visual matching between multi-modal fusion embedding and target images. Considering the intent uncertainty presented in the multi-modal queries, we introduce Probability Distribution Encoder (PDE) to project the intents as probabilistic distributions in the two matching channels. Consequently, a mutually enhanced module is designed to share knowledge between the visual and semantic representations for better representation learning. Finally, the matching scores of two channels are added to retrieve the target image. Extensive experiments conducted on two real datasets demonstrate the effectiveness and superiority of our model. Notably, with the help of the proposed LLM-based triplet augmentation strategy, our model achieves a new record of state-of-the-art performance among all datasets.