Yang, XinLi, YujieLi, QiukeLiu, Dun...
16页查看更多>>摘要：In dynamic and open environments, the traditional static sentiment analysis or opinion mining model is unsuitable for continuous computation and classification of human opinions, sentiments and emotions when training and testing data increase over time. Based on multi-granularity computing with pertinent data and parameters, this study conducted a temporal-spatial three-way multi-granularity learning framework for dynamic text sentiment classification to continually address dynamic data uncertainty. It dynamically updated the proposed model with the evolving text using a sequential three-way sentiment classification. Under a temporal-spatial multi-granularity structure, this model gradually tackled uncertain samples in the boundary region according to the monotonous variation of coarser-to-finer granularity. Subsequently, this study combined a novel dynamic sentiment classification model with balancing the performances and costs by considering four benchmark models: fastText, TextCNN, TextRNN, and TextRCNN. Finally, the comparative results of experiments on three public datasets are reported to verify the efficiency of the proposed models. (c) 2022 Elsevier Inc. All rights reserved.
原文链接:
NSTL
Elsevier
Liu, SannyuyaYu, JianweiLi, QingLiang, Ruxia...
21页查看更多>>摘要：Knowledge tracing (KT) has become an increasingly relevant problem in intelligent education services, which estimates and traces the degree of learner's mastery of concepts based on students' responses to learning resources. The existing mainstream KT models, only attribute learners' feedback to the degree of knowledge mastery and leave the influence of mental ability factors out of consideration. Although ability is an essential component of the problem-solving process, these knowledge-centered models cause a contradiction between data fitting and rationalization of the model decision-making process, making it difficult to achieve high precision and readability simultaneously.In this paper, an innovative KT model, ability boosted knowledge tracing (ABKT)(1) is pro-posed, which introduces the ability factor into learning feedback attribution to enable the model to analyze the learning process from two perspectives, knowledge and ability, simul-taneously. Based on constructive learning theory, continuous matrix factorization (CMF) model is proposed to simulate the knowledge internalization process, following the initiative growth and stationarity principles. In addition, the linear graph latent ability (LGLA) model is proposed to construct learner and item latent ability features, from graph-structured learner interaction data. Then, the knowledge and ability dual-tracing framework is constructed to integrate the knowledge and ability modules. Experimental results on four public databases indicate that the proposed methods perform better than state-of-the-art knowledge tracing algorithms in terms of prediction accuracy in quantitative assessments, displaying some advantages in model interpretability and intelligibility.(c) 2022 Elsevier Inc. All rights reserved.
原文链接:- NSTL
- Elsevier
Ling, GuangLiu, XinzhiGuan, Zhi-HongGe, Ming-Feng...
20页查看更多>>摘要：This paper investigates the input-to-state stability (ISS) and integral input-to-state stability (iISS) of switched stochastic nonlinear systems with time delays and random impulses. Different from the existing researches on ISS and iISS, random impulses with both high intensity and density are taken into account. More practically, these impulses are of different stochastic characteristics with respect to different subsystems, and may also occur in coincidence with the subsystem switching instants. The upper bound of the time derivative operator of Lyapunov function is assumed to be time-varying and mode dependent, and some sufficient conditions for the ISS and iISS properties of this presented switched stochastic nonlinear systems are established by employing LyapunovRazumikhin technique and comparison principle. Finally, several numerical examples are adopted to verify the theoretical analysis.(c) 2022 Elsevier Inc. All rights reserved.
原文链接:- NSTL
- Elsevier
