Journal of Web Engineering最新文献

{"title":"Robust Cloud Service Ranking with Deep Learning and Multi-Criteria Analysis","authors":"Pooja Goyal;Sukhvinder Singh Deora","doi":"10.13052/jwe1540-9589.2453","DOIUrl":"https://doi.org/10.13052/jwe1540-9589.2453","url":null,"abstract":"With the rapid growth of cloud services, it is crucial to have strong assessment methods in place to rate these services according to their performance, dependability, and security. This study introduces a holistic methodology that utilizes advanced deep learning (DL) algorithms to prioritize and evaluate cloud services. Our model incorporates many assessment criteria, including latency, throughput, availability, and security measures. These criteria are trained using a varied collection of performance measurements from cloud services. We validate the effectiveness of our methodology by comprehensive experiments, attaining greater precision and significance in ranking compared to conventional approaches. The DL model underwent evaluation using a testing set, resulting in a mean absolute error (MAE) of 0.15 in ranking scores. The algorithm regularly achieved superior results compared to conventional ranking approaches, particularly in situations where performance measures varied. Through the incorporation of security metrics, the model successfully assessed and ranked cloud service providers (CSPs) based not only on their performance, but also on their ability to withstand security threats. The DL technique exhibited more flexibility and contextual awareness in its rankings, hence showcasing its superiority in adjusting to real-time data. The research conducted a comparison between DL-based rankings and conventional methodologies and industry standards, demonstrating its superiority in effectively adjusting to real-time data. The study technique entails gathering data from many CSPs to construct a resilient framework for evaluating cloud services using DL models. The data is obtained from publicly available performance statistics, cloud monitoring tools, user evaluations, and problem reports. The collection comprises both structured and unstructured data, including essential performance and accuracy indicators.","PeriodicalId":49952,"journal":{"name":"Journal of Web Engineering","volume":"24 5","pages":"739-772"},"PeriodicalIF":1.0,"publicationDate":"2025-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11135461","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144896808","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Prediction and Performance Optimization of Hospital Web Application Access Modes Based on Big Data Analysis","authors":"Xiaoye Zhang;Sen Wang","doi":"10.13052/jwe1540-9589.2456","DOIUrl":"https://doi.org/10.13052/jwe1540-9589.2456","url":null,"abstract":"Data in hospital information systems contain errors, inconsistencies, and other issues that mask the true underlying patterns in the data, making the existing time series patterns blurry and leading to increased prediction errors in access patterns. To this end, research is being conducted on the prediction and performance optimization of hospital web application access patterns based on big data analysis. Firstly, semi-structured log data and structured information data from hospital web applications are collected and preprocessed. Then, a deep belief network (DBN) is used for feature extraction, and a deep learning model consisting of a stacked restricted Boltzmann machine (RBM) and a BP neural network is utilized to automatically extract multidimensional information such as user behavior features, temporal features, and page features, constructing a comprehensive feature system. Finally, based on the gated recurrent unit (GRU) neural network for access mode prediction, the control information selection mechanism of GRU is utilized to capture time series information and improve the accuracy of prediction. The experimental results show that the proposed prediction method has a practical application value with a mean square error of 0–50 for predicting traffic and a response rate within 5 seconds after application.","PeriodicalId":49952,"journal":{"name":"Journal of Web Engineering","volume":"24 5","pages":"827-850"},"PeriodicalIF":1.0,"publicationDate":"2025-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11135459","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144896809","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Web Crawling Algorithm Fusing TF-IDF and Word2Vec Feature Extraction","authors":"Xinyue Feng","doi":"10.13052/jwe1540-9589.2452","DOIUrl":"https://doi.org/10.13052/jwe1540-9589.2452","url":null,"abstract":"Current research focuses on how to efficiently extract and crawl network information because, with the growth of the Internet, network information is becoming more and more diverse. To address the problem of incorrect data extraction and topic judgment of web crawlers, this study proposes a novel approach based on a file inverse frequency algorithm and Word2Vec feature extraction. The new method improves the retrieval capability of web crawlers by using the file inverse frequency algorithm and uses Word2Vec to extract data features, which improves the data extraction capability of current crawlers. The results showed that the F1 values of the research use model were 25.8% and 26.2% higher than those of the digital filtering algorithm, respectively. The total number of localization resources for the research use strategy was 2800 and the network coverage was 81%, which was 12% higher than the optimal strategy. The research use strategy had a shorter retrieval time and the model could recognize the vocabulary of the keywords. Finally, the model used by the research also had a good model processing capability when compared to other models. In summary, the new model built by the research can improve the data retrieval ability and data extraction ability of the web crawler, which provides new research ideas for future web information extraction.","PeriodicalId":49952,"journal":{"name":"Journal of Web Engineering","volume":"24 5","pages":"713-738"},"PeriodicalIF":1.0,"publicationDate":"2025-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11135464","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144896763","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Research on the Application of Graph Neural Networks Based on Multiple Attention Mechanisms in Personalized Recommendation","authors":"Lingling Kong;Hongyan Deng;Jiayi Huang","doi":"10.13052/jwe1540-9589.2454","DOIUrl":"https://doi.org/10.13052/jwe1540-9589.2454","url":null,"abstract":"Graph neural networks (GNNs) have been widely applied due to their ability to model interactions among different objects. However, from the perspective of mathematical graph theory, the existing GNN frameworks still face challenges when dealing with specific graph structure problems. Nevertheless, the existing graph neural networks are unable to accurately identify and capture user characteristics based on common interests, have difficulty in flexibly handling diverse user interests and the differences in interests among users, and cannot effectively extract and utilize the feature information of intermediate nodes. To address these issues, this paper proposes a heterogeneous graph recommendation model based on a multi-level attention mechanism (MAHGRM-HGNN). The MAHGRM model consists of three major modules: the node-level aggregation and feature fusion module, the semantic-level aggregation module, and the importance analysis module. By introducing dual attention mechanisms at the node level and semantic level, MAHGRM can effectively identify and fuse multi-hop neighbor information related to user interests, while modeling the semantic features represented by different paths. Additionally, MAHGRM adopts an innovative feature fusion method, integrating intermediate heterogeneous nodes and their related different paths according to the topological structure of the graph, thereby avoiding the loss of intermediate node information and enriching the feature representation of the target node. In the importance analysis module, MAHGRM introduces a strategy for evaluating the importance of product nodes by calculating the importance scores of different product nodes, selecting the most popular products as the candidate set, and randomly selecting some products from it for recommendation to users. MAHGRM combines the node-level aggregation and feature fusion, semantic-level aggregation, and importance analysis modules closely. The key advantage lies in its ability to effectively integrate multi-level information in heterogeneous graphs and the collaborative optimization effect brought by the cross-module feature sharing mechanism, making the final recommendation results more targeted and timely. This cross-module collaborative effect ensures the precise capture of user interests and the efficiency of product recommendations, preventing the repetition of recommending the same product to users. The experimental results were extensively tested on multiple real-world datasets. The results showed that the performance of MAHGRM was significantly superior to that of the comparison models such as GCN, GAT, HAN, HPN, OSGNN and ie-HGCN. On the MovieLens-1M dataset, the AUC, ACC and F1-score of MAHGRM reached 0.931, 0.867 and 0.863 respectively, achieving the best performance and fully demonstrating the superiority of MAHGRM in terms of performance.","PeriodicalId":49952,"journal":{"name":"Journal of Web Engineering","volume":"24 5","pages":"773-804"},"PeriodicalIF":1.0,"publicationDate":"2025-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11135463","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144896764","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A Memory Driven Self-learning Combat Agent Architecture in a 3D Virtual Environment","authors":"Tianci Zhang;Yongyong Wei;Hao Fang","doi":"10.13052/jwe1540-9589.2451","DOIUrl":"https://doi.org/10.13052/jwe1540-9589.2451","url":null,"abstract":"Agent behavior modeling in 3D virtual environments is a critical challenge in artificial intelligence and military simulation. While rule-based methods (e.g., finite state machines) are widely used, their limitations in adaptability and development efficiency hinder their application in dynamic combat scenarios. To address this, a memory-driven self-learning agent (MDSLA) architecture is proposed, integrating visual, auditory, and game features to simulate human-like battlefield decision-making. The architecture employs an asynchronous advantage actor-critic (A3C) framework to enhance training efficiency and incorporates a memory module for processing historical perception data. Experimental validation in the Vizdoom environment demonstrates that MDSLA outperforms traditional rule-based methods and mainstream reinforcement learning algorithms in convergence speed and combat effectiveness. Furthermore, a parallel simulation mechanism is implemented via high-speed middleware, enabling seamless deployment of the model on both Vizdoom and a high-precision simulation platform (HPSP). Results from HPSP experiments show a 33% reduction in task execution time and a 24.1% improvement in lethality compared to finite state machine-driven agents. This work provides a scalable framework for developing intelligent combat agents with enhanced adaptability and realism in 3D virtual environments.","PeriodicalId":49952,"journal":{"name":"Journal of Web Engineering","volume":"24 5","pages":"687-712"},"PeriodicalIF":1.0,"publicationDate":"2025-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11135462","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144896762","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Integration and Application of an Intelligent Content Classification Model Based on Artificial Intelligence Technology and Metadata in Web Applications","authors":"Guoxin Han;Hai Lin;Genchao Yan;Kaiye Dai","doi":"10.13052/jwe1540-9589.2455","DOIUrl":"https://doi.org/10.13052/jwe1540-9589.2455","url":null,"abstract":"With the explosive growth of Internet information, Web applications are facing the challenge of efficient classification and management of a massive amount of content. Traditional classification methods rely on manual rules, which are inefficient and difficult to adapt to dynamically changing content. This study proposes an intelligent content classification model based on artificial intelligence technology and metadata, and integrates it into web applications to achieve automated and precise content classification and management. Preprocessing operations such as cleaning, deduplication, and word segmentation on multimodal data such as text, images, and videos in web applications, and extract key metadata information such as title, author, publication time, tags, etc., are performed. Pre-trained language models and image feature extraction models are used to extract high-dimensional feature representations of text and images, respectively, and metadata information are combined to construct a comprehensive feature vector. Deep neural networks are used to learn from annotated training data and construct a classification model. The experimental results illustrate that compared with traditional methods, the proposed model has significantly improved in accuracy, recall, and F1 score, reaching 95.2%, 94.8%, and 95.0%, respectively. The proposed intelligent content classification model based on artificial intelligence technology and metadata can effectively solve the problem of content classification in web applications, and improve content management efficiency and user experience.","PeriodicalId":49952,"journal":{"name":"Journal of Web Engineering","volume":"24 5","pages":"805-826"},"PeriodicalIF":1.0,"publicationDate":"2025-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11135460","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144896810","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"TrADS: A Trust-Aware Decentralized Social Network","authors":"Valentin Siegert;Dirk Leichsenring;Alejandro Wurts Santos;Martin Gaedke","doi":"10.13052/jwe1540-9589.2443","DOIUrl":"https://doi.org/10.13052/jwe1540-9589.2443","url":null,"abstract":"In today's data-driven world, people are increasingly prioritising data privacy and control. This awareness has sparked an initiative for a decentralized web, where web applications no longer rely on centralized data storage. Solid, a prominent approach for a decentralized web, allows users to store their data in decentralized pods of their control. However, the integration of data from various and potentially untrusted sources can lead to malicious or harmful results and impair user experience. To solve this problem for social networks, we propose a trustaware and decentralized web application called TrADS. It utilises the MVC pattern to integrate external data from Solid pods based on trust evaluations. In this article, we extend our first paper on TrADS with further details on related work assessment, concept and implementation. We are also extending our evaluation to a second international user study with another 64 participants. We measure the user experience instead of pure usability and form two separate groups of participants, one of which experiences the trust awareness of TrADS and one of which does not. The results do not yet show significant improvement in the user experience but show that after using trust awareness in a social network, users favour a network with such features.","PeriodicalId":49952,"journal":{"name":"Journal of Web Engineering","volume":"24 4","pages":"529-562"},"PeriodicalIF":1.0,"publicationDate":"2025-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11112760","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144773296","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A Novel Approach to Integration of Manual Changes in Generated Code: SeamlessMDD","authors":"Bojana Dragaš;Nenad Todorović;Tijana Rajačić;Gordana Milosavljević;Željko Vuković","doi":"10.13052/jwe1540-9589.2442","DOIUrl":"https://doi.org/10.13052/jwe1540-9589.2442","url":null,"abstract":"Model-driven development (MDD) significantly improves web development by generating source code from models at higher abstraction levels, which enhances productivity and enables shorter, less expensive development cycles. However, not all aspects of a web application can be captured in a model, necessitating manual changes to the generated code. To prevent the loss of manual changes due to subsequent code generation, various strategies are recommended in the literature: keeping handwritten and generated code in separate files, utilizing protected regions, or employing a version control system (VCS) to merge handwritten and generated code. Unfortunately, these approaches can introduce complexity into web application architecture and impose an additional burden on developers. This paper presents SeamlessMDD, our novel open-source framework for seamless integration that allows us to maintain handwritten and generated code intertwined without the need to adjust the web application architecture or established workflows. The framework provides the following features: (1) incremental and iterative transformations derived from model versions comparison ensuring that only code for affected model elements is generated or modified; (2) integration of generated and handwritten code using API-based code generators (ABG) that operate on the syntax trees of target programming languages; (3) case-specific support for change propagation and conflict resolution, as opposed to VCS-based systems that operate on a single line. The proposed features were tested in practice within a complex industrial MDD tool. This paper is an extended version of a paper presented at the 24th International Conference on Web Engineering, held in Tampere, Finland.","PeriodicalId":49952,"journal":{"name":"Journal of Web Engineering","volume":"24 4","pages":"499-528"},"PeriodicalIF":1.0,"publicationDate":"2025-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11112783","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144773293","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"SPARQL Query Candidate Filtering for Improving the Quality of Multilingual Question Answering Over Knowledge Graphs Using Language Models","authors":"Aleksandr Perevalov;Aleksandr Gashkov;Maria Eltsova;Andreas Both","doi":"10.13052/jwe1540-9589.2444","DOIUrl":"https://doi.org/10.13052/jwe1540-9589.2444","url":null,"abstract":"Question answering is an approach to retrieving information from a knowledge base using natural language. Within question answering systems that work over knowledge graphs (KGQA), a ranked list of SPARQL query candidates is typically computed for the given natural-language input, where the top-ranked query should reflect the intention and semantics of the given user's question. This article follows our long-term research agenda of providing trustworthy KGQA systems by presenting an approach for filtering incorrect queries. Here, we employ (large) language models (LMs/LLMs) to distinguish between correct and incorrect queries. The main difference to the previous work is that we address here multilingual questions represented in major languages (English, German, French, Spanish, and Russian), and confirm the generalizability of the approach by also evaluating it on some low-resource languages (Ukrainian, Armenian, Lithuanian, Belarusian, and Bashkir). The considered LMs (BERT, DistilBERT, Mistral, Zephyr, GPT-3.5, and GPT-4) were applied to the KGQA systems - QAnswer (real-world system) and MemQA (idealized system) – as SPARQL query filters. The approach was evaluated on the multilingual dataset QALD-9-plus, which is based on the Wikidata knowledge graph. The experimental results imply that the considered KGQA systems achieve quality improvements for all languages when using our query-filtering approach.","PeriodicalId":49952,"journal":{"name":"Journal of Web Engineering","volume":"24 4","pages":"563-592"},"PeriodicalIF":1.0,"publicationDate":"2025-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11112782","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144773294","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Application and Optimization of Semantic-Enriched Keyword Prefetching Driven by Intelligent Technology in Language Education Network Platforms","authors":"Zhubin Luo;Feifei Guo","doi":"10.13052/jwe1540-9589.2446","DOIUrl":"https://doi.org/10.13052/jwe1540-9589.2446","url":null,"abstract":"With the rapid development of intelligent technology, the application of semantically rich keyword prefetching in language education network platforms has gradually become a key technology to improve learning efficiency and user experience. This article proposes a semantic rich keyword prefetching model driven by intelligent technology, aiming to achieve accurate keyword prefetching and recommendation in language education platforms through modeling and optimization. Firstly, based on user behavior data and semantic analysis techniques, a user interest model and a semantic association model were constructed to capture the semantic relationship between users' learning intentions and keywords. Secondly, by introducing a time decay factor and context aware mechanism, the real-time and accuracy of keyword prefetching have been optimized. Experimental data shows that the MAF1 value, keyword prefetching accuracy and user satisfaction of the model are 0.897, 89.8% and 96%, which are higher than those of compared models, while increasing user satisfaction by 20%. In addition, this article proposes an optimization framework based on A/B testing, which further verifies the robustness and scalability of the model by comparing the effects of different prefetching strategies. The research results indicate that intelligent technology driven semantic rich keyword prefetching can significantly improve the personalized recommendation ability and learning efficiency of language education platforms, providing new ideas for the future development of educational technology.","PeriodicalId":49952,"journal":{"name":"Journal of Web Engineering","volume":"24 4","pages":"635-654"},"PeriodicalIF":1.0,"publicationDate":"2025-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11112808","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144773295","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}