JQJindong Qin

Jindong Qin

*This is an algorithmically generated author record based on publicly available information.

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


Jindong Qin has a total of 56 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Targeted service improvement for individualized providers

    by Jindong Qin, Pan Zheng, Xiaojun Wang, Yusen Xia

    Online reviews offer valuable insights for service improvement, especially with the increasing availability of multimodal data (e.g., text and images). However, most existing research has primarily focused on industry- or group-level analyses, often overlooking individual business contexts (e.g., performance and competition), the interaction effects between different service attributes, and the full potential of image information. This study fills these gaps by developing a novel multimodal framework that leverages machine learning and optimization theory to generate targeted service improvement recommendations for individual service providers. The three-stage framework begins with extracting and clustering aspect-opinion pairs from review texts and matching them with corresponding image features. Subsequently, we use a feature distribution smoothing-based Bayesian iterative algorithm to address biases from data imbalance and estimate attribute-level interaction effects. Finally, we construct an interaction effect network, propose a probability-based stepwise optimization algorithm, and integrate image features with large language models to generate specific and actionable recommendations for individual providers. Through a large-scale case study of hotel service improvement, we validate the effectiveness of the proposed framework and demonstrate enhanced predictive accuracy and management insights. A user study with practitioners showed that our method outperformed the best baseline by 19.5 % in practitioner satisfaction.

  • Hesitant Fuzzy Ordered Linguistic Term Sets for Group Decision-Making

    by Yingying Liang, Jindong Qin, Yudao Sun, Witold Pedrycz, Luis Martínez López

    Characterizing uncertainty remains a critical challenge in group decision-making, which has prompted the development of diverse linguistic expressions with flexibility and applicability. However, they predominantly use adaptive linguistic terms coupled with numerical importance degrees, which inherently embed subjective cognitive biases. To address this gap, this study originally introduces hesitant fuzzy ordered linguistic term sets (HFOLTSs), which systematically address dual uncertainties: cognitive ambiguity quantified through multiple linguistic term sets, and importance indeterminacy mitigated by ordered relations. To enhance interpretability and visualization, this study proposes a graphical formalization of HFOLTSs, where hierarchical levels are embedded to reflect the structured nature of ordered relations. In addition, the fundamental operations associated with HFOLTSs, complement, expectation-based comparison, and distance measurement, are established to handle complex linguistic uncertainty. Two aggregation operators, namely, hesitant fuzzy ordered linguistic weighted averaging (HFOLWA) and hesitant fuzzy ordered linguistic ordered weighted averaging (HFOLOWA), are introduced to support group decision-making. To facilitate group consensus, we further devise a mechanism that harmoniously balances consensus efficiency with the willingness of experts. Finally, the proposed method is applied to a contractor selection problem in community renewal, which demonstrates its practicality and effectiveness in managing complex group decision scenarios.


  • Minimum Cost Consensus Model Based on Granular Computing Through Online Reviews for Supporting Group Decision-Making

    by Jindong Qin, Ying Zou, Yingying Liang, Witold Pedrycz

    Recently, the minimum cost consensus model (MCCM) has received considerable attention in group decision-making. However, the prevailing trend in early MCCMs is mainly centered on model-centric approaches, which would produce unit adjustment cost and individual options. With the widespread adoption of information technologies and the availability of extensive datasets, accompanied by the advancement of machine learning, constructing MCCMs based on data-driven and machine learning methods, such as neural network (NN), is more practical and reliable. Additionally, considering the inherent variability in models and data, granular computing (GrC) and GrC-based NN can effectively resolve uncertainty. Therefore, this article presents an MCCM based on GrC and online reviews. First, the granular NN (GNN) is trained with online reviews to obtain decision-makers’ weights and unit adjustment costs based on the user information. Subsequently, through assessing the sentiment polarity of decision-makers’ reviews, their opinions are elicited and dynamically adjusted in the form of intervals. Furthermore, the bilateral granular consensus is defined to characterize the impact of decision-makers’ preferences on consensus from both sides. Finally, group decision-making on movies and television productions on douban.com is conducted using the proposed method. Sensitivity analysis demonstrates the flexibility of our consensus approach, and the comparative analysis shows its effectiveness.


  • Game Behavior-Driven Consensus Models With Maximum Linear-Quadratic Payoffs and Minimum Adjustment

    by Shengli Li, Yuzheng Sang, Rosa M. Rodríguez, Jindong Qin, Cuiping Wei

    Interaction behaviors play a core role in the process of reaching a consensus. In this article, a network game is employed to model the interplay between the behaviors of decision makers (DMs) and Stackelberg game architecture is used to design an interactive mechanism between the DMs and the moderator. An optimization model based on these two games results in a consensus model with maximum linear-quadratic payoffs and minimum adjustment (MPMACM). In the proposed MPMACM, the moderator provides compensation strategies and feedback suggestions to guide the DMs to reach the desired consensus level with minimum adjustment, while the DMs adjust their opinions aiming to obtain their maximum payoffs. We present the equilibrium analysis for the MPMACM, and an adaptive differential evolution algorithm is offered to enact this optimization model. Finally, an example application is conducted to illustrate and justify the performance of the MPMACM.


  • Product Redesign and Innovation Based on Online Reviews: A Multistage Combined Search Method

    by Jindong Qin, Pan Zheng, Xiaojun Wang

    Online reviews published on the e-commerce platform provide a new source of information for designers to develop new products. Past research on new product development (NPD) using user-generated textual data commonly focused solely on extracting and identifying product features to be improved. However, the competitive analysis of product features and more specific improvement strategies have not been explored deeply. This study fully uses the rich semantic attributes of online review texts and proposes a novel online review–driven modeling framework. This new approach can extract fine-grained product features; calculate their importance, performance, and competitiveness; and build a competitiveness network for each feature. As a result, decision making is assisted, and specific product improvement strategies are developed for NPD beyond existing modeling approaches in this domain. Specifically, online reviews are first classified into redesign- and innovation-related themes using a multiple embedding model, and the redesign and innovation product features can be extracted accordingly using a mutual information multilevel feature extraction method. Moreover, the importance and performance of features are calculated, and the competitiveness and competitiveness network of features are obtained through a personalized unidirectional bipartite graph algorithm. Finally, the importance performance competitiveness analysis plot is constructed, and the product improvement strategy is developed via a multistage combined search algorithm. Case studies and comparative experiments show the effectiveness of the proposed method and provide novel business insights for stakeholders, such as product providers, managers, and designers. History: Accepted by Ram Ramesh, Area Editor for Data Science and Machine Learning. Funding: This work was supported by the National Natural Science Foundation of China [Project 72071151] and the Natural Science Foundation of Hubei Province, China [Grant 2023CFB712]. Supplemental Material: The software that supports the findings of this study is available within the paper and its Supplemental Information ( https://pubsonline.informs.org/doi/suppl/10.1287/ijoc.2022.0333 ) as well as from the IJOC GitHub software repository ( https://github.com/INFORMSJoC/2022.0333 ). The complete IJOC Software and Data Repository is available at https://informsjoc.github.io/ .


  • Code and Data Repository Product Redesign and Innovation Based on Online Reviews: A Multistage Combined Search Method

    by Jindong Qin, Pan Zheng, Xiaojun Wang

    Online reviews published on the e-commerce platform provide a new source of information for designers to develop new products. Past research on new product development (NPD) using user-generated textual data commonly focused solely on extracting and identifying product features to be improved. However, the competitive analysis of product features and more specific improvement strategies have not been explored deeply. This study {fully uses} the rich semantic attributes of online review texts and proposes a novel online review--driven modeling framework. This new approach can extract fine-grained product features; calculate their importance, performance, and competitiveness; and build a competitiveness network for each feature. As a result, decision-making is assisted, and specific product improvement strategies are developed for NPD beyond existing modeling approaches in this domain. Specifically, online reviews are first classified into redesign- and innovation-related themes using a multiple embedding model, and the redesign and innovation product features can be extracted accordingly using a mutual information multilevel feature extraction method. Moreover, the importance and performance of features are calculated, and the competitiveness and competitiveness network of features are obtained through a personalized unidirectional bipartite graph algorithm. Finally, the importance—performance—competitiveness analysis plot is constructed, and the product improvement strategy is developed via a multistage combined search algorithm. Case studies and comparative experiments show the effectiveness of the proposed method and provide novel business insights for stakeholders, such as product providers, managers, and designers.


  • Optimizing-Information-Granule-Based Consensus Reaching Model in Large-Scale Group Decision Making

    by Yingying Liang, Witold Pedrycz, Jindong Qin

    In large-scale group decision making (LSGDM), the consensus result is expected to be realized explicitly through reconciling various preferences provided by decision makers based on their personalized viewpoints. A information granule consensus-based decision brings about high flexibility and promising aspects in group decision making. The consensus reaching proposals reported so far paid little attention to the merits of Granular Computing for managing LSGDM problems. This paper concerns an extension of the well-known analytic hierarchy process to the LSGDM scenario using the optimizing information granule-based consensus reaching method. The consensus measurement is first quantified using coverage and specificity to derive the optimal cluster using the Fuzzy C-Means algorithm. Then, based on the optimization model of an information granule leading from numerical to interval representation, a novel construction model of information granule from interval representations to type-2 interval representation is developed, which yields the consistency of the obtained result instead of proceeding with an extra revision. To achieve the desired consensus, a preference modification algorithm is designed to detect the adjusted decision maker and further provide adjustment suggestions following the reference decision maker. Finally, a numeric study illustrates the effectiveness and flexibility of the proposed method.


  • An Efficient Federated Multiview Fuzzy C-Means Clustering Method

    by Xingchen Hu, Jindong Qin, Yinghua Shen, Witold Pedrycz, Xinwang Liu, Jiyuan Liu

    Multi-view clustering has been received considerable attention due to the widespread collection of multi-view data from diverse domains and sources. However, storing multi-view data across multiple devices in many real scenarios poses significant challenges for efficient data analysis. Federated Learning framework enables collaborative machine learning on distributed devices while preserving privacy constraints. Even though there have been intensive algorithms on multi-view fuzzy clustering, federated multi-view fuzzy clustering has not been adequately investigated so far. In this study, we first develop the federated learning mode into multi-view fuzzy clustering and realize the federated optimization procedure, called Federated Multiview Fuzzy C-Means clustering (FedMVFCM). Then, we design an original strategy of consensus prototype learning during federated multi-view fuzzy clustering. It is termed as Federated Multi-view Fuzzy c-means consensus Prototypes Clustering (FedMVFPC). We also further develop the federated alternative optimization algorithm with proven convergence. This study also introduces the notion of clustering prototype communication within the federated learning framework, and integrates the clustering prototypes of different views into a unified optimization formulation. The experimental studies on various benchmark datasets demonstrate that the proposed FedMVFPC method improves the federated clustering performance and efficiency. It achieves comparable or better clustering performance against the existing state-of-the-art multi-view clustering algorithms