Semantic Associations Research Articles

Sentiment Classification from Social Media Data with Gaussian Conditional Rule-Based Deep Convolutional Neural Network

Social media platforms share several emotions in the form of text, audio, and images, where the text-shared data are less convincing to understand the emotions. The classification of the sentiments should be accurate to achieve a better understanding of the values in the commercial industry. Twitter has proven to be an effective instrument for text-based sentiment analysis when compared to other traditional assessments like surveys and stock market performance records. Though the existing research on sentiment analysis achieved good results of performance, the techniques had drawbacks such as long-term sentence prediction, less robustness, high computational resources, lack of complementary feature extraction, and so on. In this research, the Gaussian conditional rule-based deep convolutional neural network (DCNN) (Gaussian conditional rule-based DCNN) is proposed to tackle the limitation of the existing techniques, where the Gaussian distribution is applied for the selection of the kernel filters in the formation of the feature maps, and the classifier parameters are adaptively trained using the proposed adaptive nature optimizer (ANO). Through the integration of the conditionality of the random forest algorithm into the developed architecture, the model attains the potential to adapt the processing concerning the supplementary contextual information or features. Utilizing the prominent word embedding approach maximizes the input quality, converts words into continuous vector representations in a high-dimensional space, and captures both syntactic and semantic associations between words. In addition, the Graph embedding preserves some of the graph’s structural characteristics and effectively captures the syntactic dependencies, co-occurrences, semantic similarities, as well as pertinent linguistic correlations among the texts. Specifically, the proposed ANO algorithm and the conditional rule exploited in the model provide stable as well as robust performance in the classification of sentiments. The experimental results demonstrate that the Gaussian conditional rule-based DCNN model achieves 98.36 %, 98.80%, and 97.44% for accuracy, specificity, and sensitivity, respectively.

Knowledge management for product innovation design based on dual-layer concept network

Creative design has become the core of competitiveness for enterprises, and the design process is an activity based on multi-domain knowledge. Designers need to have a lot of interdisciplinary knowledge in this activity, and there may be a burden on understanding. To alleviate understanding burden and promote knowledge integration, a dual-layer concept network is established based on complex networks. Knowledge association in the network originates from the perspective of innovation and product design, facilitating in providing designers with creative and content-related knowledge. This paper takes function, invention principle and scientific principle as the label to build a creative attribute network, and uses the semantic similarity between knowledge texts to build a semantic association network. Combining creative attributes and content semantics of knowledge, a novel knowledge management and browsing method based on a dual-layer concept network is proposed. Meanwhile, due to the ambiguity and uncertainty of design activity and knowledge demand, designers repeatedly query knowledge based on a dual-layer concept network. During this process, designers’ think of diverges and associates, which inspire them to integrate knowledge and generate creative ideas. Finally, this paper takes the problem of vibrating screens as an example to verify the practicability and effectiveness of this method. The methodology is expected to be served as an essential supporting tool for sparking innovation.

Semantic and phonological associative norms of 145 French words for children aged 5–9 years: Free associations and forced-choice task

This study aimed to establish normative data for 145 words using phonological and semantic association tasks with 242 French schoolchildren, ranging from ages 5 (Grande Section) to 8 (Cours Elémentaire 2), providing a fundamental resource for future research and educational planning. The participants were engaged in two primary tasks: a free association task, entailing image recognition followed by phonological or semantic word association and a forced-choice task, involving choosing semantically or phonologically related images from options. Overall, there were more associations produced for semantic associations than phonological ones; however, there was a greater variety of phonological associations than semantic ones. We found that 5-year-old children performed better in semantic tasks by choosing expected associates compared to phonological tasks. However, this difference was not present in older children. This suggests that phonological networks develop more gradually than semantic ones, with phonological awareness continuing to improve with age while semantic stability is reached earlier. The established norms offer a framework for educators, clinicians, and researchers in understanding and assessing the semantic and phonological associative strategy of children in early educational settings within the French context.

Functional Brain Networks Underlying Autobiographical Event Simulation: An Update.

fMRI studies typically explore changes in the BOLD signal underlying discrete cognitive processes that occur over milliseconds to a few seconds. However, autobiographical cognition is a protracted process and requires fMRI tasks with longer trials to capture the temporal dynamics of the underlying brain networks. In the current study, we provided an updated analysis of the fMRI data obtained from a published autobiographical event simulation study, with a slow event-related design (34-sec trials), that involved participants recalling past, imagining past, and imagining future autobiographical events, as well as completing a semantic association control task. Our updated analysis using Constrained Principal Component Analysis for fMRI retrieved two networks reported in the original study: (1) the default mode network, which activated during the autobiographical event simulation conditions but deactivated during the control condition, and (2) the multiple demand network, which activated early in all conditions during the construction of the required representations (i.e., autobiographical events or semantic associates). Two novel networks also emerged: (1) the Response Network, which activated during the scale-rating phase, and (2) the Maintaining Internal Attention Network, which, while active in all conditions during the elaboration of details associated with the simulated events, was more strongly engaged during the imagination and semantic association control conditions. Our findings suggest that the default mode network does not support autobiographical simulation alone, but it co-activates with the multiple demand network and Maintaining Internal Attention Network, with the timing of activations depending on evolving task demands during the simulation process.

Neural correlates of auditory comprehension and integration of sanskrit verse: a functional MRI study.

In this investigation, we delve into the neural underpinnings of auditory processing of Sanskrit verse comprehension, an area not previously explored by neuroscientific research. Our study examines a diverse group of 44 bilingual individuals, including both proficient and non-proficient Sanskrit speakers, to uncover the intricate neural patterns involved in processing verses of this ancient language. Employing an integrated neuroimaging approach that combines functional connectivity-multivariate pattern analysis (fc-MVPA), voxel-based univariate analysis, seed-based connectivity analysis, and the use of sparse fMRI techniques to minimize the interference of scanner noise, we highlight the brain's adaptability and ability to integrate multiple types of information. Our findings from fc-MVPA reveal distinct connectivity patterns in proficient Sanskrit speakers, particularly involving the bilateral inferior temporal, left middle temporal, bilateral orbitofrontal, and bilateral occipital pole. Voxel-based univariate analysis showed significant activation in the right middle frontal gyrus, bilateral caudate nuclei, bilateral middle occipital gyri, left lingual gyrus, bilateral inferior parietal lobules, and bilateral inferior frontal gyri. Seed-based connectivity analysis further emphasizes the interconnected nature of the neural networks involved in language processing, demonstrating how these regions collaborate to support complex linguistic tasks. This research reveals how the brain processes the complex syntactic and semantic elements of Sanskrit verse. Findings indicate that proficient speakers effectively navigate intricate syntactic structures and semantic associations, engaging multiple brain regions in coordination. By examining the cognitive mechanisms underlying Sanskrit verse comprehension, which shares rhythmic and structural features with music and poetry, this study highlights the neural connections between language, culture, and cognition.

Ontology-based construction of embroidery intangible cultural heritage knowledge graph: A case study of Qingyang sachets.

The fine-grained mining and construction of semantic associations within multimodal intangible cultural heritage (ICH) resources are crucial for deepening our understanding of their knowledge content and ensuring their systematic protection and transmission in the digital and intelligent era. This paper addresses the urgent need for the digital preservation and transmission of ICH resources. Following a review of current research on Qingyang sachets and ICH, the study introduces an ontology-based approach to constructing a semantic description model for the multimodal digital resources related to Qingyang sachets. By acquiring and processing multimodal resources concerning the craftsmanship and associated customs of Qingyang sachets, the study reorganizes the corresponding textual and visual knowledge. Utilizing knowledge graphs, the research explores multidimensional pathways for delivering knowledge services related to the multimodal digital resources of Qingyang sachets. Empirical research confirms the applicability and feasibility of the proposed semantic association scheme for multimodal ICH digital resources. The findings provide valuable insights for multidimensional organization and integration across scenarios, time periods, and resources within the ICH domain, offering a reference for digital solutions aimed at the systematic protection of ICH.

Anomaly Detection on Interleaved Log Data with Semantic Association Mining on Log-Entity Graph

Anomaly Detection on Interleaved Log Data with Semantic Association Mining on Log-Entity Graph

Semantic Relations in Abu Talib’s Poetry (PBUH): A Textual Study

Investigating texts and their semantic links is an essential aspect of linguistics. Words integrate to form a refined meaning shaped by cultural or social context. Semantic ties are crucial moral connections that unify the text and enhance comprehension during communication. These relationships are crucial for structuring events within the text and connecting its sequences, ensuring coherence and harmony. These linkages provide a crucial focal point of textual studies that seeks to elucidate the characteristics of the text. Few texts strive for effective communication without them, as they serve to build upon prior content and provide textual coherence. The coherence, cohesion, and semantic relationships necessitate that the recipient exert additional effort to comprehend the sentences within the text, their interrelations, and their connection to the overall content. This understanding is essential for discerning the nature of the connecting relationships. Notably, the semantic relationships in the poetry of Abu Talib (peace be upon him) play a significant role in the text's structure and the cohesion of the concepts articulated by the poet. His poetry is replete with diverse semantic relationships, which he skillfully employed to intricately link the text's themes and events, thereby fostering cohesion that supports the text's central idea.

An Adaptive Multimodal Fusion Network Based on Multilinear Gradients for Visual Question Answering

As an interdisciplinary field of natural language processing and computer vision, Visual Question Answering (VQA) has emerged as a prominent research focus in artificial intelligence. The core of the VQA task is to combine natural language understanding and image analysis to infer answers by extracting meaningful features from textual and visual inputs. However, most current models struggle to fully capture the deep semantic relationships between images and text owing to their limited capacity to comprehend feature interactions, which constrains their performance. To address these challenges, this paper proposes an innovative Trilinear Multigranularity and Multimodal Adaptive Fusion algorithm (TriMMF) that is designed to improve the efficiency of multimodal feature extraction and fusion in VQA tasks. Specifically, the TriMMF consists of three key modules: (1) an Answer Generation Module, which generates candidate answers by extracting fused features and leveraging question features to focus on critical regions within the image; (2) a Fine-grained and Coarse-grained Interaction Module, which achieves multimodal interaction between question and image features at different granularities and incorporates implicit answer information to capture complex multimodal correlations; and (3) an Adaptive Weight Fusion Module, which selectively integrates coarse-grained and fine-grained interaction features based on task requirements, thereby enhancing the model’s robustness and generalization capability. Experimental results demonstrate that the proposed TriMMF significantly outperforms existing methods on the VQA v1.0 and VQA v2.0 datasets, achieving state-of-the-art performance in question–answer accuracy. These findings indicate that the TriMMF effectively captures the deep semantic associations between images and text. The proposed approach provides new insights into multimodal interaction and fusion research, combining domain adaptation techniques to address a broader range of cross-domain visual question answering tasks.

Classification of Multi-Value Chain Business Data Resources Based on Semantic Association

Focusing on the classification of business data resources within a unified business semantic environment is an important method to simplify the data environment and a crucial approach to studying data intelligence. A multi-value chain data space is a typical business semantic heterogeneous complex data environment. This paper summarizes the characteristics of multi-value chain business data resources and proposes a study on their classification using business semantic logic. By constructing a semantic-based relational model for multi-value chain business data resources and a multi-value chain business lexicon, this paper unifies the semantics of business data resources. This creates conditions for their classification according to business logic. Based on the feature transformation of business data resources, this paper proposes a clustering algorithm for multi-value chain business data resources (Business data resource classification algorithm for multi-value chain data space, BDRCA4MVCDS) aimed at a data space, completing the classification of business data resources. Finally, comparative experiments with KMeans and KABSA demonstrate the clustering effectiveness of the proposed algorithm (BDRCA4MVCDS) as well as its good stability and adaptability.

What Do Chinese Guests Want for a Five-Star Hotel Guestroom?

ABSTRACT This study attempts to develop a comprehensive understanding of consumer needs of guest room design in the context of five-star hotels in China. Applying the Kano model and SOR framework, four studies were conducted, namely, a user-generated content (UGC) based semantic association analysis (N = 13,942), in-depth interviews with hotel designers (N = 20), affinity diagrams (N = 4) and online guest surveys using the Kano questionnaire (N = 1,220). The findings of these studies indicate that a hotel room design evaluation must include comfort, convenience, function, and gratification. The Kano model revealed that functional and dysfunctional factors impact customers’ levels of satisfaction differently. In addition, guests’ satisfaction with guest rooms is also influenced by their travel purposes. The mixed-methods approach revealed both explicit and implicit room needs from the perspectives of guests, hotel designers, and management, which can help managers focus more on the neglected demands of customers and has implications for innovative room design in five-star hotels.

A cognitive network analysis of semantic associates in monolingual English speakers and learners of Kaqchikel

A cognitive network analysis of semantic associates in monolingual English speakers and learners of Kaqchikel

Associations supporting items gained and maintained across recall tests.

When performing successive recall tests without restudy, subjects' recalls exhibit intriguing variability across tests, including gaining or losing items across tests. To examine the cognitive mechanisms underlying this variability, research has focused primarily on hypermnesia, the finding that recall performance increases across tests (Erdelyi & Becker, 1974). Hypermnesia studies commonly consider conditions that impact recall levels of items gained across tests versus items maintained across tests. By contrast, analyses of recall clustering in hypermnesia studies typically collapse across maintained items and item gains. Here, I examine associative processes separately for item gains and maintained items. Experiment 1 examines these effects in final free recall, a paradigm also used to examine changes in recall across tests but less commonly linked with hypermnesia, whereas Experiment 2 uses a classic hypermnesia design. In both experiments, subjects exhibited significant temporal and semantic clustering for maintained items, but there was less evidence of these associations supporting item gains. In Experiment 1, transitions to maintained items boasted a greater proportion of same-list transitions than item gains, and in Experiment 2, there were no significant clustering effects to item gains on a test producing hypermnesia. Further, in Experiment 1, subjects exhibiting greater list-level temporal clustering of maintained items also maintained more items across tests. The results highlight the importance of episodic and semantic associations to changes in recall across tests and have implications for current theories of hypermnesia. (PsycInfo Database Record (c) 2024 APA, all rights reserved).

An Enhanced Retrieval Scheme for a Large Language Model with a Joint Strategy of Probabilistic Relevance and Semantic Association in the Vertical Domain

Large language model (LLM) processing, with natural language as its core, carries out information retrieval through intelligent Q&A. It has a wide range of application scenarios and is commonly considered a kind of generative AI. However, when LLMs handle generation tasks, the results generated by fundamental LLMs with an insufficient comprehensive performance, specifically in the vertical domain, are often inaccurate due to a poor generalization ability, resulting in the so-called “hallucination” phenomenon. To solve these problems, in this study, an enhanced retrieval scheme for LLM processing was developed, named the BM-RAGAM (BM25 retrieval-augmented generation attention mechanism), by constructing a vectorized knowledge base, utilizing a hybrid joint retrieval strategy of keyword matching through searching and a semantic-enhanced association with an attention mechanism and taking ocean-front- and eddy-related knowledge in oceanography as an example. This scheme realized accurate word-based matching with the BM25 algorithm and text generation through a semantic-enhanced association using RAG, and it was used to construct a vector database of the text knowledge on ocean fronts and eddies. The output was compared and analyzed with the fundamental LLM of Qwen2-72B using the proposed scheme, and an ablation experiment was conducted. The results show that the proposed scheme greatly reduced hallucination generation in the process of text generation, making its outputs more interpretable.

A Chinese Short Text Similarity Method Integrating Sentence-Level and Phrase-Level Semantics

Short text similarity, as a pivotal research domain within Natural Language Processing (NLP), has been extensively utilized in intelligent search, recommendation systems, and question-answering systems. Most existing short-text similarity models focus on aligning the overall semantic content of an entire sentence, often ignoring the semantic associations between individual phrases in the sentence. It is particular in the Chinese context, as synonyms and near-synonyms can cause serious interference in the computation of text similarity. To overcome these limitations, a novel short text similarity computation method integrating both sentence-level and phrase-level semantics was proposed. By harnessing vector representations of Chinese words/phrases as external knowledge, this approach amalgamates global sentence characteristics with local phrase features to compute short text similarity from diverse perspectives, spanning from the global to the local level. Experimental results demonstrate that the proposed model outperforms previous methods in the Chinese short text similarity task. Specifically, the model achieves an accuracy of 90.16% in LCQMC, which is 2.23% and 1.46%, respectively, better than ERNIE and Glyce + BERT.

Advancing Large Language Models for Spatiotemporal and Semantic Association Mining of Similar Environmental Events

Advancing Large Language Models for Spatiotemporal and Semantic Association Mining of Similar Environmental Events

Multi-scale adaptive YOLO for instance segmentation of grape pedicels

To address the presence of misdetections, missed detections, and segmentation errors that easily occur in existing lightweight models when segmenting grape pedicels in vineyards with complex backgrounds, variable lighting conditions, and varying pedicel scales, this paper proposes a lightweight grape pedicel instance segmentation model based on an improved YOLOv8. The model is named Multi-Scale Adaptive YOLO (MSA-YOLO). Firstly, this paper proposes a Multi-scale Attention Mixing Head (MAMH), which allows for a wider network input to increase the scale range. It establishes high-level semantic associations between different scales and achieves output network compression through the Multi-scale Interactive-attention Module (MIM) and Cross-channel Mixing Module (CMM). Second, the paper presents the Multi-channel Enhanced Neck (MEN), which includes two main improvements: (1) adding a feature channel specifically for small targets in the Neck for a larger scale feature channel range; and (2) the Balanced Down-sampling Module (BDM) to retain more fine-grained features during the fusion of lower-level feature channels with higher-level feature channels. Finally, the paper presents the Star Fusion Module (SFM), which enhances the model’s ability to capture multi-scale features by integrating different subspace features in the backbone and increasing the diversity of features. The proposed MSA-YOLO model, with a significantly reduced GFLOPs of just 9.7 and a parameter count of only 2.3M, demonstrates exceptional performance on our self-constructed grape dataset. The model achieves AP@50 values of 99.3% for object detection and 99.5% for instance segmentation tasks. Compared to existing lightweight instance segmentation models, MSA-YOLO achieves better performance in segmenting grape pedicels under complex scenes.

A fine‐grained image classification method based on information interaction

AbstractTo enhance the accuracy of fine‐grained image classification and address challenges such as excessive interference factors within the dataset, inadequate extraction of local key features, and insufficient channel semantic association, a dual‐branch information interaction model that integrates convolutional neural networks (CNN) with Vision Transformers is proposed. This model leverages the Vision Transformer branch to extract global features, which are subsequently combined with the CNN branch to further augment the model's capability for local information extraction. In order to enhance the ability of the CNN branch to extract global information and reduce the loss of feature information, a feature enhancement module is added to the CNN branch. Since the Vision Transformer branch directly convolves with the convolution kernel will result in the inability to learn the underlying features of the image, a shallow feature extraction module is proposed, and the CNN and Vision Transformer branches interact with the information of the dual branches through the down‐sampling Down module and the up‐sampling UP module. The accuracy of the improved method on CUB‐200‐2011, Stanford Cars and FGVC‐Aircraft fine‐grained image classification datasets are 95.2%, 97.1% and 96.9%, respectively. The experimental results show that the method has good generalization on different datasets.

Bitter effect of a Sweet Disease‐ Exploring Cognitive dysfunction in Prediabetes from an Aging cohort

AbstractBackgroundIndia is unfortunately the “Diabetes Capital” of the world with estimated 101 million and 136 million patients suffering from diabetes and prediabetes respectively. Prediabetes is a transition state between euglycemia and diabetes. Although diabetes is associated with cognitive decline, studies that link prediabetes and cognition have been scarce and inconclusive especially from the Low and Middle Income (LMIC) countries. Therefore, the current study attempts to explore the relationship between prediabetes and cognition.Methods531 participants aged ≥ 45 years, recruited by CBR‐TLSA (Tata Longitudinal Study of Ageing) were included in this study. Glycosylated Haemoglobin (HbA1c) levels was utilized to categorise the participants into healthy, prediabetes and diabetes based on the American Diabetes Association (ADA), 2017 criteria. Among these participants, 65 were healthy and 234 were prediabetic. The remaining 232 participants with Diabetes were excluded and directed towards appropriate care pathways. The COGNITO (Computerized Assessment of Adult Information Processing) neuropsychological test battery was utilized to assess the cognitive functioning. Generalized Linear Model (GLM) was performed between prediabetes status and cognition after adjusting for confounding variables.ResultsThe estimated prevalence of prediabetes in our elderly cohort is 44%. After adjusting for ApoE status, GLM analysis revealed that healthy participants performed better in semantic association (B = 0.314, 95% CI (0.047, 0.582), p = 0.021) and name‐face recognition (B = 1.644, 95% CI (0.516, 2.77), p = 0.004) tasks when compared to prediabetics. Subsequently, after adjusting for age, gender, years of education and ApoE status, it was observed that the scores of semantic association (B = 0.290, 95% CI (0.025, 0.556), p = 0.032) and name‐face recognition (B = 1.390, 95% CI (0.260, 2.520), p = 0.016) tasks were higher among healthy participants.ConclusionThis study emphasizes the deleterious effect of a potentially modifiable risk factor like prediabetes. Participants with prediabetes performed poorer in memory and language related cognitive tasks. If diagnosed early, interventions aimed at improving prediabetes could potentially prevent or delay the progression to both minor and major neurocognitive disorders.

Camera-aware graph multi-domain adaptive learning for unsupervised person re-identification

Recently, unsupervised person re-identification (Re-ID) has gained much attention due to its important practical significance in real-world application scenarios without pairwise labeled data. A key challenge for unsupervised person Re-ID is learning discriminative and robust feature representations under cross-camera scene variation. Contrastive learning approaches treat unsupervised representation learning as a dictionary look-up task. However, existing methods ignore both intra- and inter-camera semantic associations during training. In this paper, we propose a novel unsupervised person Re-ID framework, Camera-Aware Graph Multi-Domain Adaptive Learning (CGMAL), which can conduct multi-domain feature transfer with semantic propagation for learning discriminative domain-invariant representations. Specifically, we treat each camera as a distinct domain and extract image samples from every camera domain to form a mini-batch. A heterogeneous graph is constructed for representing the relationships between all instances in a mini-batch. Then a Graph Convolutional Network (GCN) is employed to fuse the image samples into a unified space and implement promising semantic transfer for providing ideal feature representations. Subsequently, we construct the memory-based non-parametric contrastive loss to train the model. In particular, we design an adversarial training scheme for transferring the knowledge learned by GCN to the feature extractor. Experimental experiments on three benchmarks validate that our proposed approach is superior to the state-of-the-art unsupervised methods.