Annals of Data Science最新文献

{"title":"An Integrated Pre-Trained Auto-Encoder and Graph Neural Network for General Social Bot Detection","authors":"Phu Pham","doi":"10.1007/s40745-025-00633-9","DOIUrl":"10.1007/s40745-025-00633-9","url":null,"abstract":"<div>\u0000 \u0000 <p>In recent years, the rapid expansion of the Internet has significantly lead to the increase in number as well as size of online social networks (OSNs) which connect millions of users across the world. While OSNs offer various benefits—such as enhancing communication, social interaction, and information dissemination—they have also become vulnerable to malicious activities in OSNs. Among these threats, the widespread distribution of fake or misleading content/cyberbullying has raised serious societal concerns. Recent studies reveal that such harmful content is often propagated by automated accounts or social bots, which are designed to mimic human behavior as well as manipulate public opinion at scale. As a result, effective detection of social bots has emerged as a critical task in ensuring the security and trustworthiness of social media platforms. Despite progress in this domain, most existing bot detection techniques rely heavily on supervised learning techniques that require large volumes of annotated networked data. These models are often tailored to specific platforms, such as Twitter; as a result, highly depending on manually engineered features which are derived from user profiles and behavioral patterns. Consequently, these graph learning techniques still faced limitations in terms of generalization and adaptability when applied to other OSNs with different structural characteristics. To overcome these challenges, we propose a novel model called AEG4BD, which integrates a pre-trained auto-encoder with a graph neural network (GNN) to facilitate robust and platform-independent social bot detection. Our proposed AEG4BD model can leverage multi-level representation learning to capture both local user attributes as well as global relational structures. Extensive experiments conducted on real-world social bot datasets demonstrate that AEG4BD outperforms existing baselines; as a result, offering improved accuracy, flexibility, as well as generalization across various social network environments.</p>\u0000 </div>","PeriodicalId":36280,"journal":{"name":"Annals of Data Science","volume":"13 5","pages":"1343 - 1363"},"PeriodicalIF":0.0,"publicationDate":"2025-08-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149098044","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Advancing Precision Healthcare: A Comparative Study of Machine Learning Approaches for Diabetes Classification","authors":"Xiaohua Li,&nbsp;Yue Teng","doi":"10.1007/s40745-025-00627-7","DOIUrl":"10.1007/s40745-025-00627-7","url":null,"abstract":"<div><p>This report underscores the supreme importance of diabetes classification in the medical field, a precursor to personalized treatment protocols and best disease control. Several methods have been described in the literature for classifying diabetes, with increasing focus in more recent times on machine-learning algorithms for analyzing medical records. With as much sincerity as previous research, the quest for the optimal method continues to provoke further investigations. This study investigates the experimentation of various machine-learning classification models to create stable and efficient models for diabetes classification. Creation of varied models from a diabetic clinical data set with strict validation, testing, and training protocols to determine efficiency. Experimental results and performance analyses are conducted to determine the models and compare performances using standard evaluation measures. Mass experiments demonstrate the technique’s efficacy, with accurate results that outdo existing methods.</p></div>","PeriodicalId":36280,"journal":{"name":"Annals of Data Science","volume":"13 1","pages":"125 - 142"},"PeriodicalIF":0.0,"publicationDate":"2025-07-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147342961","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Bivariate semiparametric mixed models to longitudinally measured systolic and diastolic blood pressure of adult diabetic patients","authors":"Tafere Tilahun Aniley,&nbsp;Legesse Kassa Debusho,&nbsp;Tadele Akeba Diriba","doi":"10.1007/s40745-025-00630-y","DOIUrl":"10.1007/s40745-025-00630-y","url":null,"abstract":"<div><p>In biomedical research, physicians collect systolic and diastolic blood pressures simultaneously when a patient visits a clinic for treatment and serve as indicators of the patient’s health status. Elevated blood pressure is a common comorbidity in diabetes patients and can increase the risk of developing hypertension over time. The aim of this study was to examine the joint evolution of systolic and diastolic blood pressure and estimate the rate of changes over time. In the analysis of correlated multiple outcomes, multivariate analysis yields satisfactory results compared to univariate analysis. Since the individual and mean profiles of systolic and diastolic blood pressure are nonlinear, we proposed bivariate semiparametric mixed models accounting for the correlation through joint random effects. Smoothing splines and thin-plate splines were specified to capture the nonlinear trends of systolic and diastolic blood pressure overtime and the nonlinear interaction effects between covariates, respectively. The bivariate semiparametric mixed models had a better fit with the data than the parametric counterparts. The study revealed a nonlinear association between weight and age with both systolic and diastolic blood pressure of diabetic patients. The results showed that weight had a more pronounced effect on increasing systolic and diastolic blood pressure in adult diabetic patients. There was a strong association between systolic and diastolic blood pressure, while the rate of change decreases with time. The proposed method may help physicians to monitor the blood pressure of patients regularly and hence to identify periods of changes early and to manage them effectively.</p></div>","PeriodicalId":36280,"journal":{"name":"Annals of Data Science","volume":"13 1","pages":"163 - 190"},"PeriodicalIF":0.0,"publicationDate":"2025-07-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://link.springer.com/content/pdf/10.1007/s40745-025-00630-y.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147341882","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Financial Flows, Economic Integration and Macroeconomic Convergence in Africa: An Interactive and Threshold Effects","authors":"Matthew I. Ogbuagu,&nbsp;Saibu M. Olufemi,&nbsp;Ogunniyi B. Matthew","doi":"10.1007/s40745-025-00631-x","DOIUrl":"10.1007/s40745-025-00631-x","url":null,"abstract":"<div><p>This study investigates the impacts of financial flows and economic integration on macroeconomic convergence by analysing 37 African countries over the period 1994 to 2021. The Augmented Neoclassical theory serves as the theoretical foundation of the study. The analysis employs the Fully Modified Ordinary Least Squares (FMOLS) technique along with other non-parametric methods. The findings confirm both beta and sigma-conditional convergence across Africa. Furthermore, financial flows and economic integration exert mixed effects on economic performance while jointly accelerating macroeconomic convergence. The results also suggest that financial flows and economic integration collectively enhance convergence toward the steady-state equilibrium in Africa. The estimated thresholds of foreign direct investment (FDI), official development assistance (ODA), and remittance inflows required to accelerate convergence are 3.44%, 1.43%, and 2.09%, respectively. Given a convergence speed of 5.3% and a time frame of 25 years, Africa is unlikely to achieve Sustainable Development Goal (SDG) 8 within the designated period. However, the African Union Agenda, which prioritises inclusive growth and regional integration, could be achieved by 2045, ceteris paribus. These findings imply that policymakers should intensify efforts to attract more foreign direct investment, as its threshold of 3.44% indicates a greater potential for enhancing convergence relative to ODA and remittances. Therefore, to maximise the benefits of economic integration, which amplifies the impact of financial flow components on macroeconomic convergence, the implementation of comprehensive structural reforms aimed at diversifying intra-African trade away from primary products is crucial.</p></div>","PeriodicalId":36280,"journal":{"name":"Annals of Data Science","volume":"13 1","pages":"191 - 214"},"PeriodicalIF":0.0,"publicationDate":"2025-07-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147341399","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Machine Learning-Based Analysis of College Student Performance and Examination Optimization","authors":"Liu Hao,&nbsp;Yu Zhi,&nbsp;Si Cheng-wei,&nbsp;Yuan An-feng,&nbsp;Liu Da-lian","doi":"10.1007/s40745-025-00629-5","DOIUrl":"10.1007/s40745-025-00629-5","url":null,"abstract":"<div><p>This paper conducts a thorough and rigorous analysis of student performance using machine learning algorithms and proposes corresponding strategies for optimizing examinations. The research is structured into three key aspects: first, the application of nonlinear models, such as Random Forest and Gradient Boosting Trees, to identify critical factors influencing student performance and provide targeted learning recommendations; second, the use of clustering analysis to stratify students and assess the difficulty coefficients of every question in the math paper, thereby optimizing exam difficulty; and third, the employment of linear regression models to predict student performance and validate correlations among different mathematics subjects. Additionally, this study incorporates Generative Adversarial Networks (GANs) to enhance model optimization, further improving their generalization capabilities and prediction accuracy. The findings reveal that midterm performance is a pivotal indicator for final grade warnings and that there is a significant correlation within mathematics subjects. Furthermore, exam question difficulty should be aligned with students’ learning levels. These results provide a scientific foundation for enhancing teaching quality, improving student learning efficiency, and offering valuable insights for teachers in implementing personalized teaching and optimizing examinations.</p></div>","PeriodicalId":36280,"journal":{"name":"Annals of Data Science","volume":"13 1","pages":"143 - 161"},"PeriodicalIF":0.0,"publicationDate":"2025-07-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147340768","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Optimizing Nigerian Bank Lending Systems: The Power of Discrete Wavelet Transform (DWT) in Denoising and Regression Analysis","authors":"C. J. Ogbonna,&nbsp;C. J. Ohabuka,&nbsp;D. C. Bartholomew,&nbsp;K. E. Anyiam,&nbsp;I. Adamu","doi":"10.1007/s40745-025-00626-8","DOIUrl":"10.1007/s40745-025-00626-8","url":null,"abstract":"<div><p>This study demonstrated the effectiveness of Discrete Wavelet Transform (DWT) as a denoising technique prior to regression modeling for loan prediction in Nigeria’s banking sector. Using monthly commercial bank loan data from the Central Bank of Nigeria spanning 1999 to 2022, the research addresses the common issue of noise in financial time series, which often leads to model misspecification, autocorrelated residuals, and unreliable forecasts. Four denoising methods were applied before model development: moving Average (MA), Savitzky-Golay (SG) filter, random forest regression, and DWT. Unlike many prior studies that adopt a single wavelet type, this work benchmarks over 90 DWT variants across multiple families (Haar, Daubechies, Symlets, and Coiflets) and decomposition levels to identify the optimal denoising configuration. The regression models were evaluated using standard performance metrics (R², MAE, MSE, RMSE, MAPE) and diagnostic statistics (Durbin–Watson, residual normality, and autocorrelation). Results show that while the raw data model achieved the highest R² (0.990), it exhibited strong residual autocorrelation (Durbin–Watson = 0.913). In contrast, the DWT-denoised model achieved superior residual independence and statistical robustness, with only a minimal reduction in R² (0.966). Although the random forest-denoised model offered slightly better predictive accuracy (R² = 0.9897), it required significant computational resources and lacked interpretability, limiting its applicability in regulatory or resource-constrained environments. This study contributes to the literature by positioning DWT as a practical, interpretable, and computationally efficient alternative to more complex machine learning approaches for financial forecasting—particularly in emerging economies with limited data and infrastructure. Future work may explore hybrid models that integrate DWT with deep learning techniques to further enhance forecasting accuracy while maintaining transparency and feasibility.</p></div>","PeriodicalId":36280,"journal":{"name":"Annals of Data Science","volume":"13 5","pages":"1305 - 1341"},"PeriodicalIF":0.0,"publicationDate":"2025-07-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149098958","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"SML-AAEA: A Systematic Method for Evaluating Advanced Activity of Daily Living Scale","authors":"Qinyan Wei,&nbsp;Aihua Li,&nbsp;Yuxue Chi,&nbsp;Xinzhu Xing","doi":"10.1007/s40745-025-00623-x","DOIUrl":"10.1007/s40745-025-00623-x","url":null,"abstract":"<div><p>With the intensification of global population aging, the incidence of cognitive impairment such as dementia continues to rise. The Activity of Daily Living (ADL) scale can help to assess daily living functions and early screen for dementia, which is crucial for delaying disease progression and improving the quality of life in older adults. As advanced ADL assessment tools continue to be developed and improved, how to evaluate their effectiveness is particularly important. However, most studies have assessed these tools from a single perspective and have often failed to examine the contribution of individual items within the scales. Therefore, we propose the Statistical and Machine Learning-based Advanced ADL scale Effectiveness Assessment Method (SML-AAEA) to evaluate the psychometric properties and early dementia screening ability of ADL assessment tool, including: (1) scale design and data collection based on traditional scales and advanced items; (2) analysis of scale validity and reliability; and (3) analysis of scale dementia diagnostic ability and item importance using machine learning. We then apply SML-AAEA to investigate the effectiveness of our proposed Advanced ADL scale for Early Dementia Screening (AADLs-EDS), which introduces three new advanced items, namely “Going far away”, “Online shopping” and “Using smartphone”. The results show that AADLs-EDS has excellent construct validity, measurement invariance, and scale reliability. The total score of AADLs-EDS can explain the changes in elderly cognitive functions to some extent. The study also finds that AADLs-EDS outperforms the traditional ADL scale in classifying dementia, with the three new items showing the strongest predictive contributions. The findings confirm that AADLs-EDS is a reliable and valid tool for early dementia screening.</p></div>","PeriodicalId":36280,"journal":{"name":"Annals of Data Science","volume":"12 6","pages":"1983 - 2008"},"PeriodicalIF":0.0,"publicationDate":"2025-07-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145537797","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A Transformation Tree Based on Extension Set Theory","authors":"Xingsen Li,&nbsp;Junwen Sun,&nbsp;Jiasheng Li,&nbsp;Yiqing Yan","doi":"10.1007/s40745-025-00605-z","DOIUrl":"10.1007/s40745-025-00605-z","url":null,"abstract":"<div><p>In the current era of information abundance, data mining and strategy generation have become crucial. Although decision trees are widely used across various domains, their direct application to obtain optimal solutions often lacks the flexibility and precision needed to adapt update themselves under specific conditions. This paper introduces an enhanced data mining algorithm, the Transformation Tree, which addresses these limitations by systematically comparing parameter variables under diverse conditions. The transformation tree algorithm builds on the traditional decision tree methodology to identify optimal transformation schemes, delivering precise and adaptable solutions. The algorithm employs basic-element theory to extract data features, evaluates them using information gain ratio and the comprehensive gain ratio metrics, and constructs a transformation tree structure. This structure facilitates the generation and refinement of transformation schemes and strategies through iterative testing. To validate its effectiveness, we applied the algorithm to a hypertension case study. The results indicate that while the transformation tree algorithm exhibits slightly lower efficiency in classification tasks, it excels in discovering multiple transformation strategies, enabling intelligent scheme generation, and providing flexible and accurate decision support.</p></div>","PeriodicalId":36280,"journal":{"name":"Annals of Data Science","volume":"12 6","pages":"1965 - 1981"},"PeriodicalIF":0.0,"publicationDate":"2025-07-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145537722","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Development of Customized Strategies for Emergency Language Teaching Content Based on Big Data","authors":"Tingting Qin","doi":"10.1007/s40745-025-00622-y","DOIUrl":"10.1007/s40745-025-00622-y","url":null,"abstract":"<div><p>This paper studies the application and effect of customized content strategy for emergency language teaching driven by big data. Using quantitative research methods, 300 college students and teachers were surveyed and standardized. Descriptive statistics, correlation analysis and regression analysis were used to evaluate the practical impact of big data technology on emergency language education. With the support of big data technology, customized teaching content can improve students’ learning performance, learning attitude, course satisfaction and teaching feedback evaluation, and improve teachers’ teaching strategies. This study proposes four strategies: real-time data collection and analysis, personalized learning path design, dynamic adjustment of teaching content, and intelligent learning feedback and evaluation. Use big data analytics and instructional design to dynamically adjust content based on students’ learning behaviors and needs to provide a highly personalized learning experience. The study highlights the unique role of big data technology in improving classroom interaction, fostering student self-directed learning, and optimizing instructional feedback. This paper verifies the significant impact of big data technology on emergency language teaching and provides theoretical and empirical support for its wide application in the field of education. The research results provide specific guidance for the integration of big data technology in education practice in the future to improve education quality, promote personalized learning, and enhance emergency education response ability.</p></div>","PeriodicalId":36280,"journal":{"name":"Annals of Data Science","volume":"13 5","pages":"1259 - 1278"},"PeriodicalIF":0.0,"publicationDate":"2025-07-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149098133","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"From pixels to profits: a novel approach to identify rare events for a group of US equities","authors":"Lubdhak Mondal,&nbsp;Kapil Chandak,&nbsp;Goirik Chakrabarty,&nbsp;Indranil SenGupta","doi":"10.1007/s40745-025-00625-9","DOIUrl":"10.1007/s40745-025-00625-9","url":null,"abstract":"<div><p>Investors are interested in the growth of their portfolios. The investment strategy focuses primarily on investing in low-risk and low-volatility companies. Nevertheless, it is important to acknowledge that every investment portfolio carries an inherent danger of experiencing financial losses due to negative progression and market crashes. This paper proposes an innovative methodology for forecasting rare events in financial time series based on the analysis of “images”. In addition, this paper deals with an enhancement to the current image formulation techniques, with the objective of addressing specific limitations that hinder their practical application in the financial analysis. In contrast to prior studies, which impose limitations on the “image-based-examination” of multiple securities, the approach presented in this paper enables the evaluation of various US Large Cap Securities, hence expanding its breadth and significance. Furthermore, the increased scope of applicability enhances the underlying algorithm’s adaptability and pertinence. One notable advancement is the incorporation of CVaR as a key measure for distinguishing between rare-event and non-rare-event scenarios. Expanding upon the limitations identified in the preceding studies, this paper presents a comprehensive enhancement in the study of financial data based on image analysis techniques.</p></div>","PeriodicalId":36280,"journal":{"name":"Annals of Data Science","volume":"13 5","pages":"1279 - 1303"},"PeriodicalIF":0.0,"publicationDate":"2025-06-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149098794","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}