Semantic Relations Research Articles

349 Rare Disease Alert System (RDAS) to promote rare disease research

Objectives/Goals: Rare disease patients often face lengthy delays in receiving accurate diagnoses or experience misdiagnoses due to a lack of available information. The NCATS Rare Disease Alert System (RDAS) is a public, comprehensive rare disease resource to collect and share accurate, up-to-date, and standardized data on rare diseases. Methods/Study Population: RDAS is composed of a frontend UI, Application Programming Interfaces, and backend Neo4j graph database. Each component of data collection, data annotation, data standardization, and data representation as steps were implemented during the process of each graph database creation. The UI allows users to search, browse, and subscribe to RDAS to receive the latest information and findings about their rare disease(s) of interest. The back-end data include four knowledge graphs built by integrating information from the NCATS Genetic and Rare Disease program, PubMed articles, clinical trials, and NIH grant funding. Ultimately, the integrative information pertinent to rare diseases from RDAS would advance rare diseases research. Results/Anticipated Results: Of 5001 rare diseases belonging to 32 distinct disease categories, we identified 1294 diseases that are mapped to 45,647 distinct, NIH-funded projects obtained from the NIH ExPORTER by implementing semantic annotation of project titles. To capture semantic relationships presenting among mapped research funding data, we defined a data model comprised of seven primary classes and corresponding object and data properties. A Neo4j knowledge graph based on this predefined data model has been developed, and we performed multiple case studies over this knowledge graph to demonstrate its use in directing and promoting rare disease research. Discussion/Significance of Impact: We developed an integrative knowledge graph with rare disease data and demonstrated its use as a source to identify and generate scientific evidence to support rare disease research. With the success of this study, we plan to implement advanced computation to analyze more funding related data and link to other types of data to perform further research.

High Performance of LSTM on Dengue Shock Syndrome Detection Using DNA Sequence Encoding Methods

Dengue fever (DF) is a significant global health challenge, affecting approximately 390 million people annually and imposing substantial public health and economic burdens. Accurate DNA sequence classification is crucial for identifying genetic factors in diseases such as DF. However, many machine learning (ML) models for disease detection rely on basic encoding methods such as one-hot encoding, which fail to fully exploit the sequential and contextual nature of DNA data. To address this limitation, this study applies long short-term memory (LSTM) networks, a neural architecture adept at handling sequential data, to classify DNA sequences for detecting dengue and dengue shock syndrome (DSS). The study evaluates three encoding techniques— one-hot encoding, term frequency-inverse document frequency (TF-IDF), and Word2Vec— using datasets of 3,458 DNA sequences sourced from genomics repositories. Preprocessing included the removal of non-ACGT sequences and duplicates to ensure data integrity, followed by under-sampling to address class imbalance. Experimental results demonstrate that the LSTM model with Word2Vec encoding achieved the highest accuracy (0.98), significantly outperforming other encoding techniques. Word2Vec captures contextual and semantic relationships within DNA sequences, enabling superior classification performance. These findings highlight the potential of combining advanced encoding techniques with LSTM networks to improve the accuracy of disease detection models. The study’s approach offers promising implications for genomic diagnostics, particularly in resource-limited settings, and lays the foundation for future research into applying similar methodologies to other diseases or datasets.

Optimizing Contextonym Analysis for Terminological Definition Writing

To write terminological definitions that meet user needs, terminologists require methods that help them effectively select the most relevant information to be included in a definition. In this sense, a corpus technique that can be useful for the definition of terms is contextonym analysis. It involves the quantitative analysis of the other terms with which the term to be defined usually co-occurs (i.e., its contextonyms), regardless of any syntactic or semantic relationship. This paper presents a study conducted to determine the optimal configuration for extracting contextonyms for the creation of terminological definitions. More specifically, this study aims to create a word sketch column in Sketch Engine that lists contextonyms, offering a user-friendly method for their extraction. This study has identified that the optimal context window for extracting contextonyms in the form of word sketches in English to inform definition writing is 50 tokens, and that these contextonyms should be ranked by frequency.

A study on large-scale disease causality discovery from biomedical literature

BackgroundBiomedical semantic relationship extraction could reveal important biomedical entities and the semantic relationships between them, providing a crucial foundation for the biomedical knowledge discovery, clinical decision making and other artificial intelligence applications. Identifying the causal relationships between diseases is a significant research field, since it expedites the identification of underlying disease pathogenesis mechanisms and promote better disease prevention and treatment. SemRep is an effective tool for semantic relationship extraction in the biomedical field, but it is not accurate enough for disease causality extraction, bringing challenges for downstream tasks. In this study, we proposed an optimization strategy for SemRep to enhance its accuracy in disease causality extraction.MethodsThis study aims to optimize disease causality extraction of SemRep tool by constructing a semantic predicate vocabulary that precisely expresses disease causality to support the automatic extraction of disease causality knowledge from biomedical literature. The proposed method invloves the following four steps: Firstly, we obtained a collection of semantic feature words expressing disease causality based on current causality predicate studies and the disease causality pairs extracted from SemMedDB. Then, we constructed a disease causality semantic predicate vocabulary by filtering and evaluating the clue words using quantitative comparisons. Following that, we extracted disease causality pairs from the biomedical literature using 36 semantic predicates with an accuracy greater than 80% for more meaningful knowledge discovery. Finally, we conducted knowledge discovery based on the extracted disease causality triples, which primarily includes unidirectional disease causality, bidirectional disease causality, as well as two specific types of disease causality: primary disease causality and rare disease causality.ResultsWe obtained a disease causality semantic predicate vocabulary containing 50 textual predicates with an accuracy of above 40%. 36 semantic predicates from the 60% accuracy group were used for disease causality extraction, yielding 259,434 disease causality pairs for subsequent knowledge discovery. Among them, 92,557 types with 176,010 unidirectional disease causality triples, and 6084 types with 83,424 bidirectional disease causality triples were found eventually. Two other types of disease causality, primary disease causality and rare disease causality, were also discovered.ConclusionsThe novelty of this research is that the proposed method enhanced the disease causality extraction of SemRep tool, resulting a more accurate and comprehensive disease causality extraction. It also facilitates an automatic disease causality extraction from large-scale biomedical literature. Additionally, a customized extraction of disease causality for its accuracy and comprehensiveness can be made possible by leveraging the quantified causality predicate vocabulary, allowing for flexible extraction of disease causality according to the actual circumstance.

Incorporating Lexical Semantics in Vocabulary Teaching: Effects and Student Perceptions in Language Acquisition

This study adopts a mixed-methods approach to explore the integration of lexical semantics in vocabulary instruction at Thang Long University. Using pre- and post-tests, Likert-scale surveys, semi-structured interviews, focus groups, and classroom observations, the study examines the impact of teaching vocabulary through semantic relationships on students’ language acquisition. Results indicate a significant improvement in vocabulary retention and comprehension, with mean test scores increasing from 2.39 (pre-test) to 4.04 (post-test). Both students and teachers viewed semantic-based instruction favourably, particularly for its use of contextualized learning and semantic mapping. However, lower-proficiency learners faced challenges in grasping abstract semantic relationships. The study suggests that scaffolding techniques and context-driven learning can enhance the effectiveness of lexical semantics in vocabulary teaching, leading to more meaningful language acquisition.

“Quit treating me like a child, I don’t like it”: Partner cueing turns in conversation restrict language, while social turns facilitate self-expression; a case study of a man with severe Broca’s aphasia and his wife

ABSTRACT Purpose During conversation, partners of people with aphasia (PWA) often use phonemic/semantic cues and ask questions with known answers, with the goal to prompt the person to talk more. However, cued turns are usually structured to elicit single words, thereby limiting verbalization. This case study investigates the impact of partner cued and social turns during conversation on the language produced by Ben, a man with severe Broca’s aphasia. Method Ben and his wife Margo participated in three unstructured conversations, as part of pre-treatment testing during another study. They were asked to have casual conversations, similar to their everyday interactions. Margo spontaneously used a high frequency of both cueing turns and social turns, providing rich data for understanding the impact of these two conditions on Ben’s verbalizations. Margo’s turns were designated as either cued or social, and Ben’s subsequent turns in each condition were analyzed for form, content, and use. Margo’s turns were also analyzed for presence of negative judgement of Ben’s turns. Results In the social condition, Ben used a greater variety of semantic relations, pragmatic intents, and syntactic forms than in the cued condition. Margo used negative judgments for 35% of his utterances in the cued condition and for 3.4% of his utterances in the social condition. Conclusions Partners’ cueing turns can restrict verbalizations in people with nonfluent aphasia, contrary to the intent to encourage more language. Increasing awareness of how partner turn-types may influence language of PWA can support partners in making choices that facilitate language opportunities for PWA.

Advancing Deliberative Discourse Measurement: The Intersection with Computational Abstract Argumentation in Discourse Quality Evaluations

This research investigates the potential of computational argumentation, specifically the application of the Abstract Argumentation Framework (AAF), to enhance the evaluation of deliberative quality in public discourse. It focuses on integrating AAF and its related semantics with the Discourse Quality Index (DQI), which is a reputable indicator of deliberative quality. The motivation is to overcome the DQI’s constraints using the AAF’s formal and logical features by addressing dependency on hand coding and attention to specific speech acts. This is done by exploring how the AAF can identify conflicts among arguments and assess the acceptability of different viewpoints, potentially leading to a more automated and objective evaluation of deliberative quality. A pilot study is conducted on the topic of abortion to illustrate the proposed methodology. The findings of this research demonstrate that AAF methods can improve discourse analysis by automatically identifying strong arguments through conflict resolution strategies. They also emphasise the potential of the proposed procedure to mitigate the dependence on manual coding and improve deliberation processes.

Human-Machine Course Evaluation With an ALBERT-Based Position Embedding Feature Enhancement Network

As online learning grows, effective course evaluation helps educators improve teaching and guides students in course selection. However, current sentiment analysis models for course reviews face two key issues: (1) they fail to adequately capture positional information in text, limiting their ability to understand semantic and contextual relationships, and (2) they overlook the correlation between review content and ratings. To address these, we propose the ALBERT-based position embedding feature enhancement network (ALBERT-PEFE). Our model combines local and global positional information through a position encoding module and designs a feature enhancement module to adjust the weights of text and rating features, capturing their correlations and modeling the alignment between review content and ratings. Experiments on a MOOC dataset show that ALBERT-PEFE outperforms baseline models. Additionally, we designed a four-level course evaluation framework using a human-machine collaborative approach, offering actionable insights for educators and reliable references for students.

The Function of the Plural Marker -lAr in Turkish from the Construction Morphology Perspective

This study aims to investigate the properties of the -lAr construction in Turkish within the framework of Construction Morphology (CxM). According to CxM, constructions are signs which are conventionalized pairings of form and meaning. As an output-oriented theory, it is argued that CxM enables us to account for the various but still relatable semantics of one construction. The plural construction -lAr in Turkish is quite productive and it can be motivated by various semantic relations in addition to its plurality denotations. It will be argued that our grammar is composed of a lexical network consisting of constructional schemas. The existing literature consists of research on its scopal features, its associative meaning, and whether its reading is inclusive or not; however, the additional functions such as its usages in greetings, making wishes are disregarded. There are also descriptive analyses which list several connotations of the morpheme but which fail to account for the systematicity of the relationships among these meanings. This paper thus accounts for both core grammar and the so-called peripheral usages of the -lAr morpheme and displays how production of different connotations is structured and enabled.

What’s in a Name? On the Problem of Meaning-Change

This article examines the phenomenon of meaning-change in general names, emphasizing its linguistic, philosophical, and societal dimensions. It explores the role of conventions in establishing the relationship between general names and their meanings, highlighting how shifts in meaning can impact language and communication. Structural categories of meaning-change – saliently: strengthening, weakening, and conceptual exclusivity – are presented, along with illustrative examples. The study also proposes a rational framework for evaluating meaning-changes, offering three key precepts: preferring meaning-distinction over change, favoring reform over revolution, and appropriately incorporating moral considerations. Additionally, the implications of politically driven meaning-changes and the challenges of semantic relativism are addressed. The findings aim to provide a nuanced understanding of how meaning-change occurs and guidelines for navigating this process in both theoretical and practical contexts.

Enhancing Hierarchical Classification in Tree-Based Models Using Level-Wise Entropy Adjustment

Hierarchical classification, which organizes items into structured categories and subcategories, has emerged as a powerful solution for handling large and complex datasets. However, traditional flat classification approaches often overlook the hierarchical dependencies between classes, leading to suboptimal predictions and limited interpretability. This paper addresses these challenges by proposing a novel integration of tree-based models with hierarchical-aware split criteria through adjusted entropy calculations. The proposed method calculates entropy at multiple hierarchical levels, ensuring that the model respects the taxonomic structure during training. This approach aligns statistical optimization with class semantic relationships, enabling more accurate and coherent predictions. Experiments conducted on real-world datasets structured according to the GS1 Global Product Classification (GPC) system demonstrate the effectiveness of our method. The proposed model was applied using tree-based ensemble methods combined with the newly developed hierarchy-aware metric Penalized Information Gain (PIG). PIG was implemented with level-wise entropy adjustments, assigning greater weight to higher hierarchical levels to maintain the taxonomic structure. The model was trained and evaluated on two real-world datasets based on the GS1 Global Product Classification (GPC) system. The final dataset included approximately 30,000 product descriptions spanning four hierarchical levels. An 80-20 train–test split was used, with model hyperparameters optimized through 5-fold cross-validation and Bayesian search. The experimental results showed a 12.7% improvement in classification accuracy at the lowest hierarchy level compared to traditional flat classification methods, with significant gains in datasets featuring highly imbalanced class distributions and deep hierarchies. The proposed approach also increased the F1 score by 12.6%. Despite these promising results, challenges remain in scaling the model for very large datasets and handling classes with limited training samples. Future research will focus on integrating neural networks with hierarchy-aware metrics, enhancing data augmentation to address class imbalance, and developing real-time classification systems for practical use in industries such as retail, logistics, and healthcare.

Multilevel Context Learning with Large Language Models for Text-Attributed Graphs on Social Networks

There are complex graph structures and rich textual information on social networks. Text provides important information for various tasks, while graph structures offer multilevel context for the semantics of the text. Contemporary researchers tend to represent these kinds of data by text-attributed graphs (TAGs). Most TAG-based representation learning methods focus on designing frameworks that convey graph structures to large language models (LLMs) to generate semantic embeddings for downstream graph neural networks (GNNs). However, these methods only provide text attributes for nodes, which fails to capture the multilevel context and leads to the loss of valuable information. To tackle this issue, we introduce the Multilevel Context Learner (MCL) model, which leverages multilevel context on social networks to enhance LLMs’ semantic embedding capabilities. We model the social network as a multilevel context textual-edge graph (MC-TEG), effectively capturing both graph structure and semantic relationships. Our MCL model leverages the reasoning capabilities of LLMs to generate semantic embeddings by integrating these multilevel contexts. The tailored bidirectional dynamic graph attention layers are introduced to further distinguish the weight information. Experimental evaluations on six real social network datasets show that the MCL model consistently outperforms all baseline models. Specifically, the MCL model achieves prediction accuracies of 77.98%, 77.63%, 74.61%, 76.40%, 72.89%, and 73.40%, with absolute improvements of 9.04%, 9.19%, 11.05%, 7.24%, 6.11%, and 9.87% over the next best models. These results demonstrate the effectiveness of the proposed MCL model.

Multi-Granularity Temporal Knowledge Graph Question Answering Based on Data Augmentation and Convolutional Networks

The multi-granularity temporal knowledge graph question-answering model consists of two core tasks: question information extraction and knowledge graph embedding representation. Existing studies typically compute the relevance score between the question and the associated temporal knowledge graph to identify the answer. However, current multi-granularity temporal knowledge graph datasets are relatively scarce, and most research has not fully exploited the potential of these limited datasets, resulting in limitations in the model’s ability to capture complex temporal relationships. Additionally, existing methods often overlook the model’s ability to capture the rich semantic relationships within questions, especially when dealing with diverse and dynamically changing temporal information. To make full use of the limited datasets and help the model better capture the complex relationships in the question, this paper proposes a multi-granularity temporal knowledge graph question-answering model based on data augmentation and convolutional networks. By using semantic paraphrasing to expand the questions and obtain more comprehensive question representations, and incorporating convolutional networks in the feature learning phase to capture more diverse and richer question representations, the proposed method outperforms baseline models on publicly available datasets, as demonstrated by experimental results.

MMRAD-Net: A Multi-Scale Model for Precise Building Extraction from High-Resolution Remote Sensing Imagery with DSM Integration

High-resolution remote sensing imagery (HRRSI) presents significant challenges for building extraction tasks due to its complex terrain structures, multi-scale features, and rich spectral and geometric information. Traditional methods often face limitations in effectively integrating multi-scale features while maintaining a balance between detailed and global semantic information. To address these challenges, this paper proposes an innovative deep learning network, Multi-Source Multi-Scale Residual Attention Network (MMRAD-Net). This model is built upon the classical encoder–decoder framework and introduces two key components: the GCN OA-SWinT Dense Module (GSTDM) and the Res DualAttention Dense Fusion Block (R-DDFB). Additionally, it incorporates Digital Surface Model (DSM) data, presenting a novel feature extraction and fusion strategy. Specifically, the model enhances building extraction accuracy and robustness through hierarchical feature modeling and a refined cross-scale fusion mechanism, while effectively preserving both detail information and global semantic relationships. Furthermore, we propose a Hybrid Loss, which combines Binary Cross-Entropy Loss (BCE Loss), Dice Loss, and an edge-sensitive term to further improve the precision of building edges and foreground reconstruction capabilities. Experiments conducted on the GF-7 and WHU datasets validate the performance of MMRAD-Net, demonstrating its superiority over traditional methods in boundary handling, detail recovery, and adaptability to complex scenes. On the GF-7 Dataset, MMRAD-Net achieved an F1-score of 91.12% and an IoU of 83.01%. On the WHU Building Dataset, the F1-score and IoU were 94.04% and 88.99%, respectively. Ablation studies and transfer learning experiments further confirm the rationality of the model design and its strong generalization ability. These results highlight that innovations in multi-source data fusion, multi-scale feature modeling, and detailed feature fusion mechanisms have enhanced the accuracy and robustness of building extraction.

Enhancing Doctor-Patient Shared Decision-Making: Design of a Novel Collaborative Decision Description Language.

Effective shared decision-making between patients and physicians is crucial for enhancing health care quality and reducing medical errors. The literature shows that the absence of effective methods to facilitate shared decision-making can result in poor patient engagement and unfavorable decision outcomes. In this paper, we propose a Collaborative Decision Description Language (CoDeL) to model shared decision-making between patients and physicians, offering a theoretical foundation for studying various shared decision scenarios. CoDeL is based on an extension of the interaction protocol language of Lightweight Social Calculus. The language utilizes speech acts to represent the attitudes of shared decision-makers toward decision propositions, as well as their semantic relationships within dialogues. It supports interactive argumentation among decision makers by embedding clinical evidence into each segment of decision protocols. Furthermore, CoDeL enables personalized decision-making, allowing for the demonstration of characteristics such as persistence, critical thinking, and openness. The feasibility of the approach is demonstrated through a case study of shared decision-making in the disease domain of atrial fibrillation. Our experimental results show that integrating the proposed language with GPT can further enhance its capabilities in interactive decision-making, improving interpretability. The proposed novel CoDeL can enhance doctor-patient shared decision-making in a rational, personalized, and interpretable manner.

Spatial Semantic Expression of Terrain Viewshed: A Data Mining Method

With the rapid development of geographic information technology, the expression of topographical spatial semantic relationships has become a research hotspot in the field of intelligent geographic information systems. Geographical spatial semantic relationships refer to the spatial relationships and inherent meanings between geographical entities, including topological relationships, metric relationships, etc. This study proposes a novel method of viewshed analysis, which solves the limitation of treating the viewshed as a unified unit in traditional viewshed analysis by decomposing the viewshed into multiple viewsheds and quantifying their spatial semantic relationships. The method uses a DBSCAN clustering algorithm with terrain adaptability to divide a viewshed into spatially different viewsheds and characterizes these viewsheds through a systematic measurement framework, including azimuth, area, and sparsity. The method was applied to a case study of Purple Mountain in Nanjing. The experiment used 12.5 m accuracy topographic data from Purple Mountain, and two observation points were selected. For the first observation point near the mountain park, during the DBSCAN clustering partition of the viewshed, the number of clusters and the number of noise points were compared with determine the neighborhood radius of 18 m and the minimum sample point number of 4. Five viewsheds were successfully generated, with the largest viewshed having 468 visible points and the smallest only 16, located in different locations from the observer, reflecting the spatial variability of terrain features. All viewsheds are basically distributed to the north of the observer, two of which also share the northeast 87° direction with the observer in a straight line distribution but at different distances. In three-dimensional space, the distance between the two viewsheds is 317.298 m. Azimuth angle verification showed significant aggregation in the northeast direction. The second point is near the ridgeline, where one viewshed accounts for 87.52% of the total viewshed, showing significant visual effects. One viewshed is 3121.113 m away from the observer, with only 113 visible points, and is not located at a low altitude, so it is suitable for a long-distance fixed-point intermittent observation. The experimental results of the two observation points reveal the directional dominance and distance stratification of viewshed spatial relationships. This paper proposes a model to express topographical viewshed spatial relationships. The model analyzes and describes the spatial features of the viewshed through quantitative and qualitative methods. These metric features provide a basis for constructing spatial topological relationships between observation points and viewsheds, helping optimize viewpoint selection and enhance landscape planning. Compared with traditional methods, the proposed method significantly improves the resolution of spatial semantic relationship expression and has practical application value in fields such as archaeology, tourism planning, and urban design.

PCLSurv: a prototypical contrastive learning-based multi-omics data integration model for cancer survival prediction.

Accurate cancer survival prediction remains a critical challenge in clinical oncology, largely due to the complex and multi-omics nature of cancer data. Existing methods often struggle to capture the comprehensive range of informative features required for precise predictions. Here, we introduce PCLSurv, an innovative deep learning framework designed for cancer survival prediction using multi-omics data. PCLSurv integrates autoencoders to extract omics-specific features and employs sample-level contrastive learning to identify distinct yet complementary characteristics across data views. Then, features are fused via a bilinear fusion module to construct a unified representation. To further enhance the model's capacity to capture high-level semantic relationships, PCLSurv aligns similar samples with shared prototypes while separating unrelated ones via prototypical contrastive learning. As a result, PCLSurv effectively distinguishes patient groups with varying survival outcomes at different semantic similarity levels, providing a robust framework for stratifying patients based on clinical and molecular features. We conduct extensive experiments on 11 cancer datasets. The comparison results confirm the superior performance of PCLSurv over existing alternatives. The source code of PCLSurv is freely available at https://github.com/LiangSDNULab/PCLSurv.

Semantic relationship extraction of English long sentences and quality optimization of machine translation based on BERT model

With the acceleration of globalization, cross-linguistic communication has become an indispensable part of daily life, and the status of English as an international lingua franca has become increasingly prominent. Faced with the complex semantic relations contained in long English sentences, the existing machine translation systems often show understanding deviations and translation distortions, which seriously affect the accuracy and coherence of information transmission. To solve this pain point, this study focuses on the latest achievement in the field of deep learning models and explores its application potential in English long sentence semantic relationship extraction and machine translation quality optimization. Firstly, the BERT model is fine-tuned to specialize in long sentence structure analysis and semantic relationship extraction. Experiments show that the F1 score of the model reaches 89.6% on the standard evaluation dataset CoNLL 2004, which is significantly higher than the previous best record. Based on this deeply mined semantic information, we further optimize the neural network machine translation system to effectively solve the long-distance dependency problem and significantly reduce the ambiguity and omission phenomenon in the translation process by introducing a novel attention guidance mechanism. In the blind test of the WMT ‘14 English-German translation task, the BLEU score of the translated version using the optimized NMT system is 29.5, which is 3.2 points higher than that of the benchmark model, which proves the remarkable effect of this method in improving translation quality.

Influence of household virtual reality products on emotions during the COVID-19 pandemic: a semantic network analysis

This study aimed to explore the emotional effects of virtual reality (VR) products during the COVID-19 pandemic by analyzing user comments of VR and COVID-19 on Steam platforms and uncovering the association between emotions and themes, and trends in emotional expression. A total of 1249 valid English-language content data were collected from January 1, 2020 to December 31, 2022 on the Steam platform, by searching for VR- and COVID-19-related keywords. Emotion analysis was used to encode each user comments. Semantic network analysis and a clustering algorithm were used to mine the potential semantic relationship between different topics and sentiments in the content. The changes and trends of topics and sentiments in each time period were analyzed. The findings indicate that during COVID-19, users were more likely to express anticipation and trust in VR products than they were to complain about COVID19. The use of VR devices is one of the sources of positive emotions during the COVID-19 pandemic. Promoting the use of metaverse social products, such as VR, in major health and pandemic prevention events may be beneficial for fostering positive emotions. The proposed framework of semantic networks and sentiment analysis is also a theoretical contribution. This study reveals the complex relationship between emotional changes and VR usage scenarios, further expanding the theoretical framework of virtual reality in social interaction and emotional regulation. From a policy perspective, governments and public health organizations should recognize the emotional support functions of VR technology during social crises.

Using Word2Vec method to improve the efficiency of word meaning understanding and memory in English teaching

In order to improve the efficiency of word meaning understanding and memory in English teaching, this article studied a new vocabulary teaching method by applying Word2Vec, a neural network-based word embedding technology. Word2Vec technology can map vocabulary to high-dimensional space and represent semantic relationships between vocabulary in vector form, thereby capturing subtle semantic differences between vocabulary. By calculating the distance and direction between vectors to infer the relationship between vocabulary, this article also introduced a mobile application that integrated multiple functional modules such as vocabulary learning, memory games, learning progress tracking, and regular push notifications, providing students with a personalized learning experience. Through this application, students can learn vocabulary anytime and anywhere, and dynamically adjust their learning plans based on their learning progress and memory effects. The significance of this paper is that the accuracy and recall rates of word meaning comprehension and memory efficiency reached 96% and 98%, respectively, proving the effectiveness of this method in English teaching. This study is not only of great significance to improving the efficiency of primary school English vocabulary teaching, but also provides new ideas for the application of natural language processing and machine learning in the field of education.