Preference prediction is the building block of personalized services,and its implementation at the group level helps enterprises identify their target customers effectively.Existing methods for preference prediction m...Preference prediction is the building block of personalized services,and its implementation at the group level helps enterprises identify their target customers effectively.Existing methods for preference prediction mainly focus on behavioral interactions to extract the associations between groups and products,ignoring the importance of other auxiliary records(e.g.,online reviews and social tags)in association detection.This paper proposes a novel method named GMAT for group preference prediction,aiming to collectively detect the sophisticated association patterns from user generated content(UGC)and behavioral interactions.In doing so,we construct a tripartite graph to collaborate these two types of data,and design a deep-learning algorithm with mutual attention module for generating the contextualized representations of groups and products.Extensive experiments on two real-world datasets show that GMAT is superior to other baselines in terms of group preference prediction.Additionally,GMAT is able to improve prediction accuracy compared with its different variants,further verifying the proposed method’s effectiveness on association pattern detection.展开更多
In this paper, a new decision making approach is proposed for the multi-attribute large group emergency decision-making problem that attribute weights are unknown and expert preference information is expressed by gene...In this paper, a new decision making approach is proposed for the multi-attribute large group emergency decision-making problem that attribute weights are unknown and expert preference information is expressed by generalized interval-valued trapezoidal fuzzy numbers （GITFNs）. Firstly, a degree of similarity formula between GITFNs is presented. Secondly, expert preference information on different alternatives is clustered into several aggregations via the fuzzy clustering method. As the clustering proceeds, an index of group preference consistency is introduced to ensure the clustering effect, and then the group preference information on different alternatives is obtained. Thirdly, the TOPSIS method is used to rank the alternatives. Finally, an example is taken to show the feasibility and effectiveness of this approach. These method can ensure the consistency degree of group preference, thus decision efficiency of emergency response activities can be improved.展开更多
基金supported by National Natural Science Foundation of China(72293561)Research Center for Interactive Technology Industry of Tsinghua University(RCITI2022T002).
文摘Preference prediction is the building block of personalized services,and its implementation at the group level helps enterprises identify their target customers effectively.Existing methods for preference prediction mainly focus on behavioral interactions to extract the associations between groups and products,ignoring the importance of other auxiliary records(e.g.,online reviews and social tags)in association detection.This paper proposes a novel method named GMAT for group preference prediction,aiming to collectively detect the sophisticated association patterns from user generated content(UGC)and behavioral interactions.In doing so,we construct a tripartite graph to collaborate these two types of data,and design a deep-learning algorithm with mutual attention module for generating the contextualized representations of groups and products.Extensive experiments on two real-world datasets show that GMAT is superior to other baselines in terms of group preference prediction.Additionally,GMAT is able to improve prediction accuracy compared with its different variants,further verifying the proposed method’s effectiveness on association pattern detection.
基金supported by a grant from Natural Science Foundation in China(71171202, 71171201,71210003)the Science Foundation for National Innovation Research Group in China(71221061)Key Project for National Natural Science Foundation in China (71431006)
文摘In this paper, a new decision making approach is proposed for the multi-attribute large group emergency decision-making problem that attribute weights are unknown and expert preference information is expressed by generalized interval-valued trapezoidal fuzzy numbers （GITFNs）. Firstly, a degree of similarity formula between GITFNs is presented. Secondly, expert preference information on different alternatives is clustered into several aggregations via the fuzzy clustering method. As the clustering proceeds, an index of group preference consistency is introduced to ensure the clustering effect, and then the group preference information on different alternatives is obtained. Thirdly, the TOPSIS method is used to rank the alternatives. Finally, an example is taken to show the feasibility and effectiveness of this approach. These method can ensure the consistency degree of group preference, thus decision efficiency of emergency response activities can be improved.
