Dynamic multiobjective optimization problems (DMOPs) frequently arise in real-world applications, where environments evolve over time. A central challenge in solving DMOPs is the ability to accurately and efficiently track optimal solutions as the environment changes. Existing dynamic multiobjective evolutionary algorithms (DMOEAs) based on single-strategy mechanisms often perform well only under specific environmental conditions, while multistrategy cooperative frameworks tend to suffer from delayed decision-making in rapidly changing, highly uncertain scenarios To address these shortcomings, this article introduces a fuzzy inference-based adaptive multistrategy-DMOEAs (FIAMS-DMOEA). This approach is designed to enhance real-time responsiveness to sudden environmental changes and mitigate decision-making latency. In the proposed method, a randomly dynamic fuzzy system serves as the foundation for population-level adaptability, enabling the algorithm to cope with highly uncertain environmental dynamics. This is further augmented by a multistrategy adaptive response mechanism (MSAR) that improves overall adaptability. By leveraging fuzzy rules, the algorithm can perceive environmental uncertainty in real time and design differentiated migration strategies, thereby establishing a robust foundation for subsequent optimization. The adaptive response mechanism centers on a multistrategy weight update method based on individual dimensional effects, which evaluates individual contributions from a dimension-specific perspective. Extensive experimental results on a suite of 32 benchmark DMOPs demonstrate that FIAMS-DMOEA consistently outperforms five state-of-the-art DMOEAs in overall performance.

ABSTRACT The integration of syntactic and semantic features for aspect‐level sentiment analysis has emerged as a prominent research trend in recent years, typically achieved by combining syntactic dependency trees with graph convolutional networks. However, most existing methods can only extract a single class of syntactic and semantic features. This study identifies sentiment‐supporting words as a means to extract a richer set of syntactic and semantic features. Accordingly, this paper introduces a sentiment support word‐based dependency graph convolutional network (SSW‐RDGCN) model. This model generates matrices by leveraging the dependency relationships and distance relationships between the nodes of the syntactic dependency tree. These matrices are then processed through specific functions to create two new matrices, which, along with the initial features of the sentence, are input into a graph convolutional network. Subsequently, three types of syntactic and semantic features extracted from the sentiment support words are incorporated, and the aspect word features and sentiment support word features are augmented. Experiments conducted on three publicly available datasets demonstrate that the proposed model outperforms the baseline model.

Summary Using imbalanced data in classification affect the accuracy. If the classification is based on imbalanced data directly, the results will have large deviations. A common approach to dealing with imbalanced data is to re‐structure the raw dataset via undersampling method. The undersampling method usually uses random or clustering approaches to trimming the majority class in the dataset, since some data in the majority class makes not contribute to classification model. In this paper a revised undersampling approach is proposed. First, we perform space compression in the vertical direction of the separating hyperplane. Then, a weighted random sampling hybrid ensemble learning method is carried out to make the sampled objects spread more widely near the separating hyperplane. Experiments with 7 under‐sampling methods on 21 imbalanced datasets show that our method has achieved good results.

Aspect-based sentiment classification is currently an important research direction to identify the sentiment expressed by sentences in different aspects. The primary approach for performing aspect-level sentiment analysis involves extracting both grammatical and semantic information. However, analyzing the grammatical connection between aspect words and other words within a review sentence using morphological features like part of speech can be exceedingly complex. This paper proposes the concept of sentiment-supporting words, dividing sentences into aspectual words, sentiment-supporting words and non-sentiment-supporting words, which simplifies the core task of sentiment analysis. Three rules are designed for determining the “sentiment-support words” of the text in different aspects. Subsequently, the application of sentiment-support words in sentiment analysis models is given, and five classical sentiment analysis models are improved accordingly. According to the experimental outcomes on two publicly available datasets, the “sentiment-support words” and corresponding sentiment support rules proposed in this paper are capable of significantly enhancing aspect-based sentiment analysis.

Genetic algorithms (GAs) have been widely applied in Steiner tree optimization problems. However, as the core operation, existing crossover operators for tree-based GAs suffer from producing illegal offspring trees. Therefore, some global link information must be adopted to ensure the connectivity of the offspring, which incurs heavy computation. To address this problem, this article proposes a new crossover mechanism, called leaf crossover (LC), which generates legal offspring by just exchanging partial parent chromosomes, requiring neither the global network link information, encoding/decoding nor repair operations. Our simulation study indicates that GAs with LC outperform GAs with existing crossover mechanisms in terms of not only producing better solutions but also converging faster in networks of varying sizes.

With the development of 5G, the advancement of basic infrastructure has led to considerable development in related research and technology. It also promotes the development of various smart devices and social platforms. More and more people are now using smart devices to post their reviews right after something happens. In order to keep pace with this trend, we propose a method to analyze users’ sentiment by using their text data. When analyzing users’ text data, it is noted that a user’s review may contain many aspects. Traditional text classification methods used by smart devices, however, usually ignore the importance of multiple aspects of a review. Additionally, most algorithms usually ignore the network structure information between the words in a sentence and the sentence itself. To address these issues, we propose a novel dual‐level attention‐based heterogeneous graph convolutional network for aspect‐based sentiment classification which minds more context information through information propagation along with graphs. Particularly, we first propose a flexible HIN (heterogeneous information network) framework to model the user‐generated reviews. This framework can integrate various types of additional information and capture their relationships to alleviate semantic sparsity of some labeled data. This framework can also leverage the full advantage of the hidden network structure information through information propagation along with graphs. Then, we propose a dual‐level attention‐based heterogeneous graph convolutional network (DAHGCN), which includes node‐level and type‐level attentions. The attention mechanisms can analyze the importance of different adjacent nodes and the importance of different types of nodes for the current node. The experimental results on three real‐world datasets demonstrated the effectiveness and reliability of our model.

Predicting and utilizing the evolution trend of hot topics is critical for contingency management and decision-making purposes of government bodies and enterprises. This paper proposes a model named online opinion dynamics (OODs) where any node in a social network has its unique confidence threshold and influence radius. The nodes in the OOD are mainly affected by their neighbors and are also randomly influenced by unfamiliar nodes. In the traditional opinion model, however, each node is affected by all other nodes, including its friends. Furthermore, many traditional opinion evolution approaches are reviewed to see if all nodes (participants) can eventually reach a consensus. On the contrary, OOD is more focused on such details as concluding the overall trend of events and evaluating the support level of each participant through numerical simulation. Experiments show that OOD is superior to the improvement of the original Hegselmann-Krause (HK) model, HK-13 and HK-17, with respect to qualitative predictions of the evolution trend of an event. The quantitative predictions of the HK model cannot be used to make decisions, whereas the results of the OOD model are proved to be acceptable.

This paper investigates how to use diversity introduction methods to enhance the dynamic evolutionary multiobjective optimization algorithms in dealing with dynamic multiobjective optimization problems (DMOPs). Although diversity introduction method is easy used to response to the dynamic change, current diversity introduction methods still have a difficulty in identifying the correct proportion of diversity introduction. To overcome this difficulty, this paper proposes an adaptive diversity introduction (ADI) method. Specifically, the proportion of diversity introduction can be dynamically adjusted rather than being hand designed and fixed in advance. In addition, an adaptive relocation operator is designed to adapt the evolving individuals to the new environmental condition. The effectiveness of the ADI method is validated against various diversity introduction methods upon five DMOPs test problems. The simulation results show that the proposed ADI has better robustness and total performance than other diversity introduction methods.

Marginal Fisher analysis (MFA) is a well-known linear dimensionality reduction method. However, MFA does not utilize the local diversity information of the training data, which will degrade its performance. In order to enhance the discriminant power of MFA, this paper considers introducing local variation quantity to enlarge the distances between local neighborhood embeddings and proposes a flexible and efficient implementation of MFA (F-MFA) within the regularization framework. Therefore, the discriminant structure and diversity of data are preserved in low-dimensional subspace. Computationally, F-MFA is formulated as a trace differential optimization problem which can completely avoids the singularity problem as it exists in MFA. Further, an efficient algorithm is developed for implementing F-MFA via QR-decomposition. Experimental results on four face data sets demonstrate the effectiveness of our approach.

We present a nearest nonlinear subspace classifier that extends ridge regression classification method to kernel version which is called Kernel Ridge Regression Classification (KRRC). Kernel method is usually considered effective in discovering the nonlinear structure of the data manifold. The basic idea of KRRC is to implicitly map the observed data into potentially much higher dimensional feature space by using kernel trick and perform ridge regression classification in feature space. In this new feature space, samples from a single-object class may lie on a linear subspace, such that a new test sample can be represented as a linear combination of class-specific galleries, then the minimum distance between the new test sample and class specific subspace is used for classification. Our experimental studies on synthetic data sets and some UCI benchmark datasets confirm the effectiveness of the proposed method.