Missing data presents a crucial challenge in data analysis,especially in high-dimensional datasets,where missing data often leads to biased conclusions and degraded model performance.In this study,we present a novel a...Missing data presents a crucial challenge in data analysis,especially in high-dimensional datasets,where missing data often leads to biased conclusions and degraded model performance.In this study,we present a novel autoencoder-based imputation framework that integrates a composite loss function to enhance robustness and precision.The proposed loss combines(i)a guided,masked mean squared error focusing on missing entries;(ii)a noise-aware regularization term to improve resilience against data corruption;and(iii)a variance penalty to encourage expressive yet stable reconstructions.We evaluate the proposed model across four missingness mechanisms,such as Missing Completely at Random,Missing at Random,Missing Not at Random,and Missing Not at Random with quantile censorship,under systematically varied feature counts,sample sizes,and missingness ratios ranging from 5%to 60%.Four publicly available real-world datasets(Stroke Prediction,Pima Indians Diabetes,Cardiovascular Disease,and Framingham Heart Study)were used,and the obtained results show that our proposed model consistently outperforms baseline methods,including traditional and deep learning-based techniques.An ablation study reveals the additive value of each component in the loss function.Additionally,we assessed the downstream utility of imputed data through classification tasks,where datasets imputed by the proposed method yielded the highest receiver operating characteristic area under the curve scores across all scenarios.The model demonstrates strong scalability and robustness,improving performance with larger datasets and higher feature counts.These results underscore the capacity of the proposed method to produce not only numerically accurate but also semantically useful imputations,making it a promising solution for robust data recovery in clinical applications.展开更多
Modern intrusion detection systems(MIDS)face persistent challenges in coping with the rapid evolution of cyber threats,high-volume network traffic,and imbalanced datasets.Traditional models often lack the robustness a...Modern intrusion detection systems(MIDS)face persistent challenges in coping with the rapid evolution of cyber threats,high-volume network traffic,and imbalanced datasets.Traditional models often lack the robustness and explainability required to detect novel and sophisticated attacks effectively.This study introduces an advanced,explainable machine learning framework for multi-class IDS using the KDD99 and IDS datasets,which reflects real-world network behavior through a blend of normal and diverse attack classes.The methodology begins with sophisticated data preprocessing,incorporating both RobustScaler and QuantileTransformer to address outliers and skewed feature distributions,ensuring standardized and model-ready inputs.Critical dimensionality reduction is achieved via the Harris Hawks Optimization(HHO)algorithm—a nature-inspired metaheuristic modeled on hawks’hunting strategies.HHO efficiently identifies the most informative features by optimizing a fitness function based on classification performance.Following feature selection,the SMOTE is applied to the training data to resolve class imbalance by synthetically augmenting underrepresented attack types.The stacked architecture is then employed,combining the strengths of XGBoost,SVM,and RF as base learners.This layered approach improves prediction robustness and generalization by balancing bias and variance across diverse classifiers.The model was evaluated using standard classification metrics:precision,recall,F1-score,and overall accuracy.The best overall performance was recorded with an accuracy of 99.44%for UNSW-NB15,demonstrating the model’s effectiveness.After balancing,the model demonstrated a clear improvement in detecting the attacks.We tested the model on four datasets to show the effectiveness of the proposed approach and performed the ablation study to check the effect of each parameter.Also,the proposed model is computationaly efficient.To support transparency and trust in decision-making,explainable AI(XAI)techniques are incorporated that provides both global and local insight into feature contributions,and offers intuitive visualizations for individual predictions.This makes it suitable for practical deployment in cybersecurity environments that demand both precision and accountability.展开更多
Reversible data hiding(RDH)enables secret data embedding while preserving complete cover image recovery,making it crucial for applications requiring image integrity.The pixel value ordering(PVO)technique used in multi...Reversible data hiding(RDH)enables secret data embedding while preserving complete cover image recovery,making it crucial for applications requiring image integrity.The pixel value ordering(PVO)technique used in multi-stego images provides good image quality but often results in low embedding capability.To address these challenges,this paper proposes a high-capacity RDH scheme based on PVO that generates three stego images from a single cover image.The cover image is partitioned into non-overlapping blocks with pixels sorted in ascending order.Four secret bits are embedded into each block’s maximum pixel value,while three additional bits are embedded into the second-largest value when the pixel difference exceeds a predefined threshold.A similar embedding strategy is also applied to the minimum side of the block,including the second-smallest pixel value.This design enables each block to embed up to 14 bits of secret data.Experimental results demonstrate that the proposed method achieves significantly higher embedding capacity and improved visual quality compared to existing triple-stego RDH approaches,advancing the field of reversible steganography.展开更多
The increasing complexity of China’s electricity market creates substantial challenges for settlement automation,data consistency,and operational scalability.Existing provincial settlement systems are fragmented,lack...The increasing complexity of China’s electricity market creates substantial challenges for settlement automation,data consistency,and operational scalability.Existing provincial settlement systems are fragmented,lack a unified data structure,and depend heavily on manual intervention to process high-frequency and retroactive transactions.To address these limitations,a graph-based unified settlement framework is proposed to enhance automation,flexibility,and adaptability in electricity market settlements.A flexible attribute-graph model is employed to represent heterogeneousmulti-market data,enabling standardized integration,rapid querying,and seamless adaptation to evolving business requirements.An extensible operator library is designed to support configurable settlement rules,and a suite of modular tools—including dataset generation,formula configuration,billing templates,and task scheduling—facilitates end-to-end automated settlement processing.A robust refund-clearing mechanism is further incorporated,utilizing sandbox execution,data-version snapshots,dynamic lineage tracing,and real-time changecapture technologies to enable rapid and accurate recalculations under dynamic policy and data revisions.Case studies based on real-world data from regional Chinese markets validate the effectiveness of the proposed approach,demonstrating marked improvements in computational efficiency,system robustness,and automation.Moreover,enhanced settlement accuracy and high temporal granularity improve price-signal fidelity,promote cost-reflective tariffs,and incentivize energy-efficient and demand-responsive behavior among market participants.The method not only supports equitable and transparent market operations but also provides a generalizable,scalable foundation for modern electricity settlement platforms in increasingly complex and dynamic market environments.展开更多
With the increasing emphasis on personal information protection,encryption through security protocols has emerged as a critical requirement in data transmission and reception processes.Nevertheless,IoT ecosystems comp...With the increasing emphasis on personal information protection,encryption through security protocols has emerged as a critical requirement in data transmission and reception processes.Nevertheless,IoT ecosystems comprise heterogeneous networks where outdated systems coexist with the latest devices,spanning a range of devices from non-encrypted ones to fully encrypted ones.Given the limited visibility into payloads in this context,this study investigates AI-based attack detection methods that leverage encrypted traffic metadata,eliminating the need for decryption and minimizing system performance degradation—especially in light of these heterogeneous devices.Using the UNSW-NB15 and CICIoT-2023 dataset,encrypted and unencrypted traffic were categorized according to security protocol,and AI-based intrusion detection experiments were conducted for each traffic type based on metadata.To mitigate the problem of class imbalance,eight different data sampling techniques were applied.The effectiveness of these sampling techniques was then comparatively analyzed using two ensemble models and three Deep Learning(DL)models from various perspectives.The experimental results confirmed that metadata-based attack detection is feasible using only encrypted traffic.In the UNSW-NB15 dataset,the f1-score of encrypted traffic was approximately 0.98,which is 4.3%higher than that of unencrypted traffic(approximately 0.94).In addition,analysis of the encrypted traffic in the CICIoT-2023 dataset using the same method showed a significantly lower f1-score of roughly 0.43,indicating that the quality of the dataset and the preprocessing approach have a substantial impact on detection performance.Furthermore,when data sampling techniques were applied to encrypted traffic,the recall in the UNSWNB15(Encrypted)dataset improved by up to 23.0%,and in the CICIoT-2023(Encrypted)dataset by 20.26%,showing a similar level of improvement.Notably,in CICIoT-2023,f1-score and Receiver Operation Characteristic-Area Under the Curve(ROC-AUC)increased by 59.0%and 55.94%,respectively.These results suggest that data sampling can have a positive effect even in encrypted environments.However,the extent of the improvement may vary depending on data quality,model architecture,and sampling strategy.展开更多
Automated essay scoring(AES)systems have gained significant importance in educational settings,offering a scalable,efficient,and objective method for evaluating student essays.However,developing AES systems for Arabic...Automated essay scoring(AES)systems have gained significant importance in educational settings,offering a scalable,efficient,and objective method for evaluating student essays.However,developing AES systems for Arabic poses distinct challenges due to the language’s complex morphology,diglossia,and the scarcity of annotated datasets.This paper presents a hybrid approach to Arabic AES by combining text-based,vector-based,and embeddingbased similarity measures to improve essay scoring accuracy while minimizing the training data required.Using a large Arabic essay dataset categorized into thematic groups,the study conducted four experiments to evaluate the impact of feature selection,data size,and model performance.Experiment 1 established a baseline using a non-machine learning approach,selecting top-N correlated features to predict essay scores.The subsequent experiments employed 5-fold cross-validation.Experiment 2 showed that combining embedding-based,text-based,and vector-based features in a Random Forest(RF)model achieved an R2 of 88.92%and an accuracy of 83.3%within a 0.5-point tolerance.Experiment 3 further refined the feature selection process,demonstrating that 19 correlated features yielded optimal results,improving R2 to 88.95%.In Experiment 4,an optimal data efficiency training approach was introduced,where training data portions increased from 5%to 50%.The study found that using just 10%of the data achieved near-peak performance,with an R2 of 85.49%,emphasizing an effective trade-off between performance and computational costs.These findings highlight the potential of the hybrid approach for developing scalable Arabic AES systems,especially in low-resource environments,addressing linguistic challenges while ensuring efficient data usage.展开更多
Objective expertise evaluation of individuals,as a prerequisite stage for team formation,has been a long-term desideratum in large software development companies.With the rapid advancements in machine learning methods...Objective expertise evaluation of individuals,as a prerequisite stage for team formation,has been a long-term desideratum in large software development companies.With the rapid advancements in machine learning methods,based on reliable existing data stored in project management tools’datasets,automating this evaluation process becomes a natural step forward.In this context,our approach focuses on quantifying software developer expertise by using metadata from the task-tracking systems.For this,we mathematically formalize two categories of expertise:technology-specific expertise,which denotes the skills required for a particular technology,and general expertise,which encapsulates overall knowledge in the software industry.Afterward,we automatically classify the zones of expertise associated with each task a developer has worked on using Bidirectional Encoder Representations from Transformers(BERT)-like transformers to handle the unique characteristics of project tool datasets effectively.Finally,our method evaluates the proficiency of each software specialist across already completed projects from both technology-specific and general perspectives.The method was experimentally validated,yielding promising results.展开更多
The rapid growth of biomedical data,particularly multi-omics data including genomes,transcriptomics,proteomics,metabolomics,and epigenomics,medical research and clinical decision-making confront both new opportunities...The rapid growth of biomedical data,particularly multi-omics data including genomes,transcriptomics,proteomics,metabolomics,and epigenomics,medical research and clinical decision-making confront both new opportunities and obstacles.The huge and diversified nature of these datasets cannot always be managed using traditional data analysis methods.As a consequence,deep learning has emerged as a strong tool for analysing numerous omics data due to its ability to handle complex and non-linear relationships.This paper explores the fundamental concepts of deep learning and how they are used in multi-omics medical data mining.We demonstrate how autoencoders,variational autoencoders,multimodal models,attention mechanisms,transformers,and graph neural networks enable pattern analysis and recognition across all omics data.Deep learning has been found to be effective in illness classification,biomarker identification,gene network learning,and therapeutic efficacy prediction.We also consider critical problems like as data quality,model explainability,whether findings can be repeated,and computational power requirements.We now consider future elements of combining omics with clinical and imaging data,explainable AI,federated learning,and real-time diagnostics.Overall,this study emphasises the need of collaborating across disciplines to advance deep learning-based multi-omics research for precision medicine and comprehending complicated disorders.展开更多
High-throughput transcriptomics has evolved from bulk RNA-seq to single-cell and spatial profiling,yet its clinical translation still depends on effective integration across diverse omics and data modalities.Emerging ...High-throughput transcriptomics has evolved from bulk RNA-seq to single-cell and spatial profiling,yet its clinical translation still depends on effective integration across diverse omics and data modalities.Emerging foundation models and multimodal learning frameworks are enabling scalable and transferable representations of cellular states,while advances in interpretability and real-world data integration are bridging the gap between discovery and clinical application.This paper outlines a concise roadmap for AI-driven,transcriptome-centered multi-omics integration in precision medicine(Figure 1).展开更多
Gastrointestinal tumors require personalized treatment strategies due to their heterogeneity and complexity.Multimodal artificial intelligence(AI)addresses this challenge by integrating diverse data sources-including ...Gastrointestinal tumors require personalized treatment strategies due to their heterogeneity and complexity.Multimodal artificial intelligence(AI)addresses this challenge by integrating diverse data sources-including computed tomography(CT),magnetic resonance imaging(MRI),endoscopic imaging,and genomic profiles-to enable intelligent decision-making for individualized therapy.This approach leverages AI algorithms to fuse imaging,endoscopic,and omics data,facilitating comprehensive characterization of tumor biology,prediction of treatment response,and optimization of therapeutic strategies.By combining CT and MRI for structural assessment,endoscopic data for real-time visual inspection,and genomic information for molecular profiling,multimodal AI enhances the accuracy of patient stratification and treatment personalization.The clinical implementation of this technology demonstrates potential for improving patient outcomes,advancing precision oncology,and supporting individualized care in gastrointestinal cancers.Ultimately,multimodal AI serves as a transformative tool in oncology,bridging data integration with clinical application to effectively tailor therapies.展开更多
We investigate the null tests of cosmic accelerated expansion by using the baryon acoustic oscillation(BAO)data measured by the dark energy spectroscopic instrument(DESI)and reconstruct the dimensionless Hubble parame...We investigate the null tests of cosmic accelerated expansion by using the baryon acoustic oscillation(BAO)data measured by the dark energy spectroscopic instrument(DESI)and reconstruct the dimensionless Hubble parameter E(z)from the DESI BAO Alcock-Paczynski(AP)data using Gaussian process to perform the null test.We find strong evidence of accelerated expansion from the DESI BAO AP data.By reconstructing the deceleration parameter q(z) from the DESI BAO AP data,we find that accelerated expansion persisted until z■0.7 with a 99.7%confidence level.Additionally,to provide insights into the Hubble tension problem,we propose combining the reconstructed E(z) with D_(H)/r_(d) data to derive a model-independent result r_(d)h=99.8±3.1 Mpc.This result is consistent with measurements from cosmic microwave background(CMB)anisotropies using the ΛCDM model.We also propose a model-independent method for reconstructing the comoving angular diameter distance D_(M)(z) from the distance modulus μ,using SNe Ia data and combining this result with DESI BAO data of D_(M)/r_(d) to constrain the value of r_(d).We find that the value of r_(d),derived from this model-independent method,is smaller than that obtained from CMB measurements,with a significant discrepancy of at least 4.17σ.All the conclusions drawn in this paper are independent of cosmological models and gravitational theories.展开更多
Parkinson’s disease(PD)is a debilitating neurological disorder affecting over 10 million people worldwide.PD classification models using voice signals as input are common in the literature.It is believed that using d...Parkinson’s disease(PD)is a debilitating neurological disorder affecting over 10 million people worldwide.PD classification models using voice signals as input are common in the literature.It is believed that using deep learning algorithms further enhances performance;nevertheless,it is challenging due to the nature of small-scale and imbalanced PD datasets.This paper proposed a convolutional neural network-based deep support vector machine(CNN-DSVM)to automate the feature extraction process using CNN and extend the conventional SVM to a DSVM for better classification performance in small-scale PD datasets.A customized kernel function reduces the impact of biased classification towards the majority class(healthy candidates in our consideration).An improved generative adversarial network(IGAN)was designed to generate additional training data to enhance the model’s performance.For performance evaluation,the proposed algorithm achieves a sensitivity of 97.6%and a specificity of 97.3%.The performance comparison is evaluated from five perspectives,including comparisons with different data generation algorithms,feature extraction techniques,kernel functions,and existing works.Results reveal the effectiveness of the IGAN algorithm,which improves the sensitivity and specificity by 4.05%–4.72%and 4.96%–5.86%,respectively;and the effectiveness of the CNN-DSVM algorithm,which improves the sensitivity by 1.24%–57.4%and specificity by 1.04%–163%and reduces biased detection towards the majority class.The ablation experiments confirm the effectiveness of individual components.Two future research directions have also been suggested.展开更多
The outbreak of the pandemic,caused by Coronavirus Disease 2019(COVID-19),has affected the daily activities of people across the globe.During COVID-19 outbreak and the successive lockdowns,Twitter was heavily used and...The outbreak of the pandemic,caused by Coronavirus Disease 2019(COVID-19),has affected the daily activities of people across the globe.During COVID-19 outbreak and the successive lockdowns,Twitter was heavily used and the number of tweets regarding COVID-19 increased tremendously.Several studies used Sentiment Analysis(SA)to analyze the emotions expressed through tweets upon COVID-19.Therefore,in current study,a new Artificial Bee Colony(ABC)with Machine Learning-driven SA(ABCMLSA)model is developed for conducting Sentiment Analysis of COVID-19 Twitter data.The prime focus of the presented ABCML-SA model is to recognize the sentiments expressed in tweets made uponCOVID-19.It involves data pre-processing at the initial stage followed by n-gram based feature extraction to derive the feature vectors.For identification and classification of the sentiments,the Support Vector Machine(SVM)model is exploited.At last,the ABC algorithm is applied to fine tune the parameters involved in SVM.To demonstrate the improved performance of the proposed ABCML-SA model,a sequence of simulations was conducted.The comparative assessment results confirmed the effectual performance of the proposed ABCML-SA model over other approaches.展开更多
Aflood is a significant damaging natural calamity that causes loss of life and property.Earlier work on the construction offlood prediction models intended to reduce risks,suggest policies,reduce mortality,and limit prop...Aflood is a significant damaging natural calamity that causes loss of life and property.Earlier work on the construction offlood prediction models intended to reduce risks,suggest policies,reduce mortality,and limit property damage caused byfloods.The massive amount of data generated by social media platforms such as Twitter opens the door toflood analysis.Because of the real-time nature of Twitter data,some government agencies and authorities have used it to track natural catastrophe events in order to build a more rapid rescue strategy.However,due to the shorter duration of Tweets,it is difficult to construct a perfect prediction model for determiningflood.Machine learning(ML)and deep learning(DL)approaches can be used to statistically developflood prediction models.At the same time,the vast amount of Tweets necessitates the use of a big data analytics(BDA)tool forflood prediction.In this regard,this work provides an optimal deep learning-basedflood forecasting model with big data analytics(ODLFF-BDA)based on Twitter data.The suggested ODLFF-BDA technique intends to anticipate the existence offloods using tweets in a big data setting.The ODLFF-BDA technique comprises data pre-processing to convert the input tweets into a usable format.In addition,a Bidirectional Encoder Representations from Transformers(BERT)model is used to generate emotive contextual embed-ding from tweets.Furthermore,a gated recurrent unit(GRU)with a Multilayer Convolutional Neural Network(MLCNN)is used to extract local data and predict theflood.Finally,an Equilibrium Optimizer(EO)is used tofine-tune the hyper-parameters of the GRU and MLCNN models in order to increase prediction performance.The memory usage is pull down lesser than 3.5 MB,if its compared with the other algorithm techniques.The ODLFF-BDA technique’s performance was validated using a benchmark Kaggle dataset,and thefindings showed that it outperformed other recent approaches significantly.展开更多
Today social media became a communication line among people to share their happiness,sadness,and anger with their end-users.It is necessary to know people’s emotions are very important to identify depressed people fr...Today social media became a communication line among people to share their happiness,sadness,and anger with their end-users.It is necessary to know people’s emotions are very important to identify depressed people from their messages.Early depression detection helps to save people’s lives and other dangerous mental diseases.There are many intelligent algorithms for predicting depression with high accuracy,but they lack the definition of such cases.Several machine learning methods help to identify depressed people.But the accuracy of existing methods was not satisfactory.To overcome this issue,the deep learning method is used in the proposed method for depression detection.In this paper,a novel Deep Learning Multi-Aspect Depression Detection with Hierarchical Atten-tion Network(MDHAN)is used for classifying the depression data.Initially,the Twitter data was preprocessed by tokenization,punctuation mark removal,stop word removal,stemming,and lemmatization.The Adaptive Particle and grey Wolf optimization methods are used for feature selection.The MDHAN classifies the Twitter data and predicts the depressed and non-depressed users.Finally,the proposed method is compared with existing methods such as Convolutional Neur-al Network(CNN),Support Vector Machine(SVM),Minimum Description Length(MDL),and MDHAN.The suggested MDH-PWO architecture gains 99.86%accuracy,more significant than frequency-based deep learning models,with a lower false-positive rate.The experimental result shows that the proposed method achieves better accuracy,precision,recall,and F1-measure.It also mini-mizes the execution time.展开更多
People started posting textual tweets on Twitter as soon as the novel coronavirus(COVID-19)emerged.Analyzing these tweets can assist institutions in better decision-making and prioritizing their tasks.Therefore,this s...People started posting textual tweets on Twitter as soon as the novel coronavirus(COVID-19)emerged.Analyzing these tweets can assist institutions in better decision-making and prioritizing their tasks.Therefore,this study aimed to analyze 43 million tweets collected between March 22 and March 30,2020 and describe the trend of public attention given to the topics related to the COVID-19 epidemic using evolutionary clustering analysis.The results indicated that unigram terms were trended more frequently than bigram and trigram terms.A large number of tweets about the COVID-19 were disseminated and received widespread public attention during the epidemic.The high-frequency words such as“death”,“test”,“spread”,and“lockdown”suggest that people fear of being infected,and those who got infection are afraid of death.The results also showed that people agreed to stay at home due to the fear of the spread,and they were calling for social distancing since they become aware of the COVID-19.It can be suggested that social media posts may affect human psychology and behavior.These results may help governments and health organizations to better understand the psychology of the public,and thereby,better communicate with them to prevent and manage the panic.展开更多
Purpose: Attention deficit hyperactivity disorder(ADHD) is a common behavioural condition. This article introduces a new data science method, word association thematic analysis, to investigate whether ADHD tweets can ...Purpose: Attention deficit hyperactivity disorder(ADHD) is a common behavioural condition. This article introduces a new data science method, word association thematic analysis, to investigate whether ADHD tweets can give insights into patient concerns and online communication needs. Design/methodology/approach: Tweets matching "my ADHD"(n=58,893) and 99 other conditions(n=1,341,442) were gathered and two thematic analyses conducted. Analysis 1: A standard thematic analysis of ADHD-related tweets. Analysis 2: A word association thematic analysis of themes unique to ADHD.Findings: The themes that emerged from the two analyses included people ascribing their brains agency to explain and justify their symptoms and using the concept of neurodivergence for a positive self-image. Research limitations: This is a single case study and the results may differ for other topics.Practical implications: Health professionals should be sensitive to patients' needs to understand their behaviour, find ways to justify and explain it to others and to be positive about their condition.Originality/value: Word association thematic analysis can give new insights into the(self-reported) patient perspective.展开更多
With the huge increase in popularity of Twitter in recent years, the ability to draw information regarding public sentiment from Twitter data has become an area of immense interest. Numerous methods of determining the...With the huge increase in popularity of Twitter in recent years, the ability to draw information regarding public sentiment from Twitter data has become an area of immense interest. Numerous methods of determining the sentiment of tweets, both in general and in regard to a specific topic, have been developed, however most of these functions are in a batch learning environment where instances may be passed over multiple times. Since Twitter data in real world situations are far similar to a stream environment, we proposed several algorithms which classify the sentiment of tweets in a data stream. We were able to determine whether a tweet was subjective or objective with an error rate as low as 0.24 and an F-score as high as 0.85. For the determination of positive or negative sentiment in subjective tweets, an error rate as low as 0.23 and an F-score as high as 0.78 were achieved.展开更多
Social media data created a paradigm shift in assessing situational awareness during a natural disaster or emergencies such as wildfire, hurricane, tropical storm etc. Twitter as an emerging data source is an effectiv...Social media data created a paradigm shift in assessing situational awareness during a natural disaster or emergencies such as wildfire, hurricane, tropical storm etc. Twitter as an emerging data source is an effective and innovative digital platform to observe trend from social media users’ perspective who are direct or indirect witnesses of the calamitous event. This paper aims to collect and analyze twitter data related to the recent wildfire in California to perform a trend analysis by classifying firsthand and credible information from Twitter users. This work investigates tweets on the recent wildfire in California and classifies them based on witnesses into two types: 1) direct witnesses and 2) indirect witnesses. The collected and analyzed information can be useful for law enforcement agencies and humanitarian organizations for communication and verification of the situational awareness during wildfire hazards. Trend analysis is an aggregated approach that includes sentimental analysis and topic modeling performed through domain-expert manual annotation and machine learning. Trend analysis ultimately builds a fine-grained analysis to assess evacuation routes and provide valuable information to the firsthand emergency responders<span style="font-family:Verdana;">.</span>展开更多
Handling sentiment drifts in real time twitter data streams are a challen-ging task while performing sentiment classifications,because of the changes that occur in the sentiments of twitter users,with respect to time....Handling sentiment drifts in real time twitter data streams are a challen-ging task while performing sentiment classifications,because of the changes that occur in the sentiments of twitter users,with respect to time.The growing volume of tweets with sentiment drifts has led to the need for devising an adaptive approach to detect and handle this drift in real time.This work proposes an adap-tive learning algorithm-based framework,Twitter Sentiment Drift Analysis-Bidir-ectional Encoder Representations from Transformers(TSDA-BERT),which introduces a sentiment drift measure to detect drifts and a domain impact score to adaptively retrain the classification model with domain relevant data in real time.The framework also works on static data by converting them to data streams using the Kafka tool.The experiments conducted on real time and simulated tweets of sports,health care andfinancial topics show that the proposed system is able to detect sentiment drifts and maintain the performance of the classification model,with accuracies of 91%,87%and 90%,respectively.Though the results have been provided only for a few topics,as a proof of concept,this framework can be applied to detect sentiment drifts and perform sentiment classification on real time data streams of any topic.展开更多
文摘Missing data presents a crucial challenge in data analysis,especially in high-dimensional datasets,where missing data often leads to biased conclusions and degraded model performance.In this study,we present a novel autoencoder-based imputation framework that integrates a composite loss function to enhance robustness and precision.The proposed loss combines(i)a guided,masked mean squared error focusing on missing entries;(ii)a noise-aware regularization term to improve resilience against data corruption;and(iii)a variance penalty to encourage expressive yet stable reconstructions.We evaluate the proposed model across four missingness mechanisms,such as Missing Completely at Random,Missing at Random,Missing Not at Random,and Missing Not at Random with quantile censorship,under systematically varied feature counts,sample sizes,and missingness ratios ranging from 5%to 60%.Four publicly available real-world datasets(Stroke Prediction,Pima Indians Diabetes,Cardiovascular Disease,and Framingham Heart Study)were used,and the obtained results show that our proposed model consistently outperforms baseline methods,including traditional and deep learning-based techniques.An ablation study reveals the additive value of each component in the loss function.Additionally,we assessed the downstream utility of imputed data through classification tasks,where datasets imputed by the proposed method yielded the highest receiver operating characteristic area under the curve scores across all scenarios.The model demonstrates strong scalability and robustness,improving performance with larger datasets and higher feature counts.These results underscore the capacity of the proposed method to produce not only numerically accurate but also semantically useful imputations,making it a promising solution for robust data recovery in clinical applications.
基金funded by Princess Nourah bint Abdulrahman University Researchers Supporting Project number(PNURSP2025R104)Princess Nourah bint Abdulrahman University,Riyadh,Saudi Arabia.
文摘Modern intrusion detection systems(MIDS)face persistent challenges in coping with the rapid evolution of cyber threats,high-volume network traffic,and imbalanced datasets.Traditional models often lack the robustness and explainability required to detect novel and sophisticated attacks effectively.This study introduces an advanced,explainable machine learning framework for multi-class IDS using the KDD99 and IDS datasets,which reflects real-world network behavior through a blend of normal and diverse attack classes.The methodology begins with sophisticated data preprocessing,incorporating both RobustScaler and QuantileTransformer to address outliers and skewed feature distributions,ensuring standardized and model-ready inputs.Critical dimensionality reduction is achieved via the Harris Hawks Optimization(HHO)algorithm—a nature-inspired metaheuristic modeled on hawks’hunting strategies.HHO efficiently identifies the most informative features by optimizing a fitness function based on classification performance.Following feature selection,the SMOTE is applied to the training data to resolve class imbalance by synthetically augmenting underrepresented attack types.The stacked architecture is then employed,combining the strengths of XGBoost,SVM,and RF as base learners.This layered approach improves prediction robustness and generalization by balancing bias and variance across diverse classifiers.The model was evaluated using standard classification metrics:precision,recall,F1-score,and overall accuracy.The best overall performance was recorded with an accuracy of 99.44%for UNSW-NB15,demonstrating the model’s effectiveness.After balancing,the model demonstrated a clear improvement in detecting the attacks.We tested the model on four datasets to show the effectiveness of the proposed approach and performed the ablation study to check the effect of each parameter.Also,the proposed model is computationaly efficient.To support transparency and trust in decision-making,explainable AI(XAI)techniques are incorporated that provides both global and local insight into feature contributions,and offers intuitive visualizations for individual predictions.This makes it suitable for practical deployment in cybersecurity environments that demand both precision and accountability.
基金funded by University of Transport and Communications(UTC)under grant number T2025-CN-004.
文摘Reversible data hiding(RDH)enables secret data embedding while preserving complete cover image recovery,making it crucial for applications requiring image integrity.The pixel value ordering(PVO)technique used in multi-stego images provides good image quality but often results in low embedding capability.To address these challenges,this paper proposes a high-capacity RDH scheme based on PVO that generates three stego images from a single cover image.The cover image is partitioned into non-overlapping blocks with pixels sorted in ascending order.Four secret bits are embedded into each block’s maximum pixel value,while three additional bits are embedded into the second-largest value when the pixel difference exceeds a predefined threshold.A similar embedding strategy is also applied to the minimum side of the block,including the second-smallest pixel value.This design enables each block to embed up to 14 bits of secret data.Experimental results demonstrate that the proposed method achieves significantly higher embedding capacity and improved visual quality compared to existing triple-stego RDH approaches,advancing the field of reversible steganography.
基金funded by the Science and Technology Project of State Grid Corporation of China(5108-202355437A-3-2-ZN).
文摘The increasing complexity of China’s electricity market creates substantial challenges for settlement automation,data consistency,and operational scalability.Existing provincial settlement systems are fragmented,lack a unified data structure,and depend heavily on manual intervention to process high-frequency and retroactive transactions.To address these limitations,a graph-based unified settlement framework is proposed to enhance automation,flexibility,and adaptability in electricity market settlements.A flexible attribute-graph model is employed to represent heterogeneousmulti-market data,enabling standardized integration,rapid querying,and seamless adaptation to evolving business requirements.An extensible operator library is designed to support configurable settlement rules,and a suite of modular tools—including dataset generation,formula configuration,billing templates,and task scheduling—facilitates end-to-end automated settlement processing.A robust refund-clearing mechanism is further incorporated,utilizing sandbox execution,data-version snapshots,dynamic lineage tracing,and real-time changecapture technologies to enable rapid and accurate recalculations under dynamic policy and data revisions.Case studies based on real-world data from regional Chinese markets validate the effectiveness of the proposed approach,demonstrating marked improvements in computational efficiency,system robustness,and automation.Moreover,enhanced settlement accuracy and high temporal granularity improve price-signal fidelity,promote cost-reflective tariffs,and incentivize energy-efficient and demand-responsive behavior among market participants.The method not only supports equitable and transparent market operations but also provides a generalizable,scalable foundation for modern electricity settlement platforms in increasingly complex and dynamic market environments.
基金supported by the Institute of Information&Communications Technology Planning&Evaluation(IITP)grant funded by the Korea government(MSIT)(No.RS-2023-00235509Development of security monitoring technology based network behavior against encrypted cyber threats in ICT convergence environment).
文摘With the increasing emphasis on personal information protection,encryption through security protocols has emerged as a critical requirement in data transmission and reception processes.Nevertheless,IoT ecosystems comprise heterogeneous networks where outdated systems coexist with the latest devices,spanning a range of devices from non-encrypted ones to fully encrypted ones.Given the limited visibility into payloads in this context,this study investigates AI-based attack detection methods that leverage encrypted traffic metadata,eliminating the need for decryption and minimizing system performance degradation—especially in light of these heterogeneous devices.Using the UNSW-NB15 and CICIoT-2023 dataset,encrypted and unencrypted traffic were categorized according to security protocol,and AI-based intrusion detection experiments were conducted for each traffic type based on metadata.To mitigate the problem of class imbalance,eight different data sampling techniques were applied.The effectiveness of these sampling techniques was then comparatively analyzed using two ensemble models and three Deep Learning(DL)models from various perspectives.The experimental results confirmed that metadata-based attack detection is feasible using only encrypted traffic.In the UNSW-NB15 dataset,the f1-score of encrypted traffic was approximately 0.98,which is 4.3%higher than that of unencrypted traffic(approximately 0.94).In addition,analysis of the encrypted traffic in the CICIoT-2023 dataset using the same method showed a significantly lower f1-score of roughly 0.43,indicating that the quality of the dataset and the preprocessing approach have a substantial impact on detection performance.Furthermore,when data sampling techniques were applied to encrypted traffic,the recall in the UNSWNB15(Encrypted)dataset improved by up to 23.0%,and in the CICIoT-2023(Encrypted)dataset by 20.26%,showing a similar level of improvement.Notably,in CICIoT-2023,f1-score and Receiver Operation Characteristic-Area Under the Curve(ROC-AUC)increased by 59.0%and 55.94%,respectively.These results suggest that data sampling can have a positive effect even in encrypted environments.However,the extent of the improvement may vary depending on data quality,model architecture,and sampling strategy.
基金funded by Deanship of Graduate studies and Scientific Research at Jouf University under grant No.(DGSSR-2024-02-01264).
文摘Automated essay scoring(AES)systems have gained significant importance in educational settings,offering a scalable,efficient,and objective method for evaluating student essays.However,developing AES systems for Arabic poses distinct challenges due to the language’s complex morphology,diglossia,and the scarcity of annotated datasets.This paper presents a hybrid approach to Arabic AES by combining text-based,vector-based,and embeddingbased similarity measures to improve essay scoring accuracy while minimizing the training data required.Using a large Arabic essay dataset categorized into thematic groups,the study conducted four experiments to evaluate the impact of feature selection,data size,and model performance.Experiment 1 established a baseline using a non-machine learning approach,selecting top-N correlated features to predict essay scores.The subsequent experiments employed 5-fold cross-validation.Experiment 2 showed that combining embedding-based,text-based,and vector-based features in a Random Forest(RF)model achieved an R2 of 88.92%and an accuracy of 83.3%within a 0.5-point tolerance.Experiment 3 further refined the feature selection process,demonstrating that 19 correlated features yielded optimal results,improving R2 to 88.95%.In Experiment 4,an optimal data efficiency training approach was introduced,where training data portions increased from 5%to 50%.The study found that using just 10%of the data achieved near-peak performance,with an R2 of 85.49%,emphasizing an effective trade-off between performance and computational costs.These findings highlight the potential of the hybrid approach for developing scalable Arabic AES systems,especially in low-resource environments,addressing linguistic challenges while ensuring efficient data usage.
基金supported by the project“Romanian Hub for Artificial Intelligence-HRIA”,Smart Growth,Digitization and Financial Instruments Program,2021–2027,MySMIS No.334906.
文摘Objective expertise evaluation of individuals,as a prerequisite stage for team formation,has been a long-term desideratum in large software development companies.With the rapid advancements in machine learning methods,based on reliable existing data stored in project management tools’datasets,automating this evaluation process becomes a natural step forward.In this context,our approach focuses on quantifying software developer expertise by using metadata from the task-tracking systems.For this,we mathematically formalize two categories of expertise:technology-specific expertise,which denotes the skills required for a particular technology,and general expertise,which encapsulates overall knowledge in the software industry.Afterward,we automatically classify the zones of expertise associated with each task a developer has worked on using Bidirectional Encoder Representations from Transformers(BERT)-like transformers to handle the unique characteristics of project tool datasets effectively.Finally,our method evaluates the proficiency of each software specialist across already completed projects from both technology-specific and general perspectives.The method was experimentally validated,yielding promising results.
文摘The rapid growth of biomedical data,particularly multi-omics data including genomes,transcriptomics,proteomics,metabolomics,and epigenomics,medical research and clinical decision-making confront both new opportunities and obstacles.The huge and diversified nature of these datasets cannot always be managed using traditional data analysis methods.As a consequence,deep learning has emerged as a strong tool for analysing numerous omics data due to its ability to handle complex and non-linear relationships.This paper explores the fundamental concepts of deep learning and how they are used in multi-omics medical data mining.We demonstrate how autoencoders,variational autoencoders,multimodal models,attention mechanisms,transformers,and graph neural networks enable pattern analysis and recognition across all omics data.Deep learning has been found to be effective in illness classification,biomarker identification,gene network learning,and therapeutic efficacy prediction.We also consider critical problems like as data quality,model explainability,whether findings can be repeated,and computational power requirements.We now consider future elements of combining omics with clinical and imaging data,explainable AI,federated learning,and real-time diagnostics.Overall,this study emphasises the need of collaborating across disciplines to advance deep learning-based multi-omics research for precision medicine and comprehending complicated disorders.
文摘High-throughput transcriptomics has evolved from bulk RNA-seq to single-cell and spatial profiling,yet its clinical translation still depends on effective integration across diverse omics and data modalities.Emerging foundation models and multimodal learning frameworks are enabling scalable and transferable representations of cellular states,while advances in interpretability and real-world data integration are bridging the gap between discovery and clinical application.This paper outlines a concise roadmap for AI-driven,transcriptome-centered multi-omics integration in precision medicine(Figure 1).
基金Supported by Xuhui District Health Commission,No.SHXH202214.
文摘Gastrointestinal tumors require personalized treatment strategies due to their heterogeneity and complexity.Multimodal artificial intelligence(AI)addresses this challenge by integrating diverse data sources-including computed tomography(CT),magnetic resonance imaging(MRI),endoscopic imaging,and genomic profiles-to enable intelligent decision-making for individualized therapy.This approach leverages AI algorithms to fuse imaging,endoscopic,and omics data,facilitating comprehensive characterization of tumor biology,prediction of treatment response,and optimization of therapeutic strategies.By combining CT and MRI for structural assessment,endoscopic data for real-time visual inspection,and genomic information for molecular profiling,multimodal AI enhances the accuracy of patient stratification and treatment personalization.The clinical implementation of this technology demonstrates potential for improving patient outcomes,advancing precision oncology,and supporting individualized care in gastrointestinal cancers.Ultimately,multimodal AI serves as a transformative tool in oncology,bridging data integration with clinical application to effectively tailor therapies.
基金supported in part by the National Key Research and Development Program of China (Grant No.2020YFC2201504)the National Natural Science Foundation of China (Grant Nos.12588101 and 12535002)。
文摘We investigate the null tests of cosmic accelerated expansion by using the baryon acoustic oscillation(BAO)data measured by the dark energy spectroscopic instrument(DESI)and reconstruct the dimensionless Hubble parameter E(z)from the DESI BAO Alcock-Paczynski(AP)data using Gaussian process to perform the null test.We find strong evidence of accelerated expansion from the DESI BAO AP data.By reconstructing the deceleration parameter q(z) from the DESI BAO AP data,we find that accelerated expansion persisted until z■0.7 with a 99.7%confidence level.Additionally,to provide insights into the Hubble tension problem,we propose combining the reconstructed E(z) with D_(H)/r_(d) data to derive a model-independent result r_(d)h=99.8±3.1 Mpc.This result is consistent with measurements from cosmic microwave background(CMB)anisotropies using the ΛCDM model.We also propose a model-independent method for reconstructing the comoving angular diameter distance D_(M)(z) from the distance modulus μ,using SNe Ia data and combining this result with DESI BAO data of D_(M)/r_(d) to constrain the value of r_(d).We find that the value of r_(d),derived from this model-independent method,is smaller than that obtained from CMB measurements,with a significant discrepancy of at least 4.17σ.All the conclusions drawn in this paper are independent of cosmological models and gravitational theories.
基金The work described in this paper was fully supported by a grant from Hong Kong Metropolitan University(RIF/2021/05).
文摘Parkinson’s disease(PD)is a debilitating neurological disorder affecting over 10 million people worldwide.PD classification models using voice signals as input are common in the literature.It is believed that using deep learning algorithms further enhances performance;nevertheless,it is challenging due to the nature of small-scale and imbalanced PD datasets.This paper proposed a convolutional neural network-based deep support vector machine(CNN-DSVM)to automate the feature extraction process using CNN and extend the conventional SVM to a DSVM for better classification performance in small-scale PD datasets.A customized kernel function reduces the impact of biased classification towards the majority class(healthy candidates in our consideration).An improved generative adversarial network(IGAN)was designed to generate additional training data to enhance the model’s performance.For performance evaluation,the proposed algorithm achieves a sensitivity of 97.6%and a specificity of 97.3%.The performance comparison is evaluated from five perspectives,including comparisons with different data generation algorithms,feature extraction techniques,kernel functions,and existing works.Results reveal the effectiveness of the IGAN algorithm,which improves the sensitivity and specificity by 4.05%–4.72%and 4.96%–5.86%,respectively;and the effectiveness of the CNN-DSVM algorithm,which improves the sensitivity by 1.24%–57.4%and specificity by 1.04%–163%and reduces biased detection towards the majority class.The ablation experiments confirm the effectiveness of individual components.Two future research directions have also been suggested.
基金The Deanship of ScientificResearch (DSR)at King Abdulaziz University,Jeddah,Saudi Arabia has funded this project,under Grant No. (FP-205-43).
文摘The outbreak of the pandemic,caused by Coronavirus Disease 2019(COVID-19),has affected the daily activities of people across the globe.During COVID-19 outbreak and the successive lockdowns,Twitter was heavily used and the number of tweets regarding COVID-19 increased tremendously.Several studies used Sentiment Analysis(SA)to analyze the emotions expressed through tweets upon COVID-19.Therefore,in current study,a new Artificial Bee Colony(ABC)with Machine Learning-driven SA(ABCMLSA)model is developed for conducting Sentiment Analysis of COVID-19 Twitter data.The prime focus of the presented ABCML-SA model is to recognize the sentiments expressed in tweets made uponCOVID-19.It involves data pre-processing at the initial stage followed by n-gram based feature extraction to derive the feature vectors.For identification and classification of the sentiments,the Support Vector Machine(SVM)model is exploited.At last,the ABC algorithm is applied to fine tune the parameters involved in SVM.To demonstrate the improved performance of the proposed ABCML-SA model,a sequence of simulations was conducted.The comparative assessment results confirmed the effectual performance of the proposed ABCML-SA model over other approaches.
文摘Aflood is a significant damaging natural calamity that causes loss of life and property.Earlier work on the construction offlood prediction models intended to reduce risks,suggest policies,reduce mortality,and limit property damage caused byfloods.The massive amount of data generated by social media platforms such as Twitter opens the door toflood analysis.Because of the real-time nature of Twitter data,some government agencies and authorities have used it to track natural catastrophe events in order to build a more rapid rescue strategy.However,due to the shorter duration of Tweets,it is difficult to construct a perfect prediction model for determiningflood.Machine learning(ML)and deep learning(DL)approaches can be used to statistically developflood prediction models.At the same time,the vast amount of Tweets necessitates the use of a big data analytics(BDA)tool forflood prediction.In this regard,this work provides an optimal deep learning-basedflood forecasting model with big data analytics(ODLFF-BDA)based on Twitter data.The suggested ODLFF-BDA technique intends to anticipate the existence offloods using tweets in a big data setting.The ODLFF-BDA technique comprises data pre-processing to convert the input tweets into a usable format.In addition,a Bidirectional Encoder Representations from Transformers(BERT)model is used to generate emotive contextual embed-ding from tweets.Furthermore,a gated recurrent unit(GRU)with a Multilayer Convolutional Neural Network(MLCNN)is used to extract local data and predict theflood.Finally,an Equilibrium Optimizer(EO)is used tofine-tune the hyper-parameters of the GRU and MLCNN models in order to increase prediction performance.The memory usage is pull down lesser than 3.5 MB,if its compared with the other algorithm techniques.The ODLFF-BDA technique’s performance was validated using a benchmark Kaggle dataset,and thefindings showed that it outperformed other recent approaches significantly.
基金funded by Princess Nourah bint Abdulrahman University Researchers Supporting Project Number(PNURSP2022R300),Princess Nourah bint Abdulrahman University,Riyadh,Saudi Arabia.
文摘Today social media became a communication line among people to share their happiness,sadness,and anger with their end-users.It is necessary to know people’s emotions are very important to identify depressed people from their messages.Early depression detection helps to save people’s lives and other dangerous mental diseases.There are many intelligent algorithms for predicting depression with high accuracy,but they lack the definition of such cases.Several machine learning methods help to identify depressed people.But the accuracy of existing methods was not satisfactory.To overcome this issue,the deep learning method is used in the proposed method for depression detection.In this paper,a novel Deep Learning Multi-Aspect Depression Detection with Hierarchical Atten-tion Network(MDHAN)is used for classifying the depression data.Initially,the Twitter data was preprocessed by tokenization,punctuation mark removal,stop word removal,stemming,and lemmatization.The Adaptive Particle and grey Wolf optimization methods are used for feature selection.The MDHAN classifies the Twitter data and predicts the depressed and non-depressed users.Finally,the proposed method is compared with existing methods such as Convolutional Neur-al Network(CNN),Support Vector Machine(SVM),Minimum Description Length(MDL),and MDHAN.The suggested MDH-PWO architecture gains 99.86%accuracy,more significant than frequency-based deep learning models,with a lower false-positive rate.The experimental result shows that the proposed method achieves better accuracy,precision,recall,and F1-measure.It also mini-mizes the execution time.
文摘People started posting textual tweets on Twitter as soon as the novel coronavirus(COVID-19)emerged.Analyzing these tweets can assist institutions in better decision-making and prioritizing their tasks.Therefore,this study aimed to analyze 43 million tweets collected between March 22 and March 30,2020 and describe the trend of public attention given to the topics related to the COVID-19 epidemic using evolutionary clustering analysis.The results indicated that unigram terms were trended more frequently than bigram and trigram terms.A large number of tweets about the COVID-19 were disseminated and received widespread public attention during the epidemic.The high-frequency words such as“death”,“test”,“spread”,and“lockdown”suggest that people fear of being infected,and those who got infection are afraid of death.The results also showed that people agreed to stay at home due to the fear of the spread,and they were calling for social distancing since they become aware of the COVID-19.It can be suggested that social media posts may affect human psychology and behavior.These results may help governments and health organizations to better understand the psychology of the public,and thereby,better communicate with them to prevent and manage the panic.
文摘Purpose: Attention deficit hyperactivity disorder(ADHD) is a common behavioural condition. This article introduces a new data science method, word association thematic analysis, to investigate whether ADHD tweets can give insights into patient concerns and online communication needs. Design/methodology/approach: Tweets matching "my ADHD"(n=58,893) and 99 other conditions(n=1,341,442) were gathered and two thematic analyses conducted. Analysis 1: A standard thematic analysis of ADHD-related tweets. Analysis 2: A word association thematic analysis of themes unique to ADHD.Findings: The themes that emerged from the two analyses included people ascribing their brains agency to explain and justify their symptoms and using the concept of neurodivergence for a positive self-image. Research limitations: This is a single case study and the results may differ for other topics.Practical implications: Health professionals should be sensitive to patients' needs to understand their behaviour, find ways to justify and explain it to others and to be positive about their condition.Originality/value: Word association thematic analysis can give new insights into the(self-reported) patient perspective.
文摘With the huge increase in popularity of Twitter in recent years, the ability to draw information regarding public sentiment from Twitter data has become an area of immense interest. Numerous methods of determining the sentiment of tweets, both in general and in regard to a specific topic, have been developed, however most of these functions are in a batch learning environment where instances may be passed over multiple times. Since Twitter data in real world situations are far similar to a stream environment, we proposed several algorithms which classify the sentiment of tweets in a data stream. We were able to determine whether a tweet was subjective or objective with an error rate as low as 0.24 and an F-score as high as 0.85. For the determination of positive or negative sentiment in subjective tweets, an error rate as low as 0.23 and an F-score as high as 0.78 were achieved.
文摘Social media data created a paradigm shift in assessing situational awareness during a natural disaster or emergencies such as wildfire, hurricane, tropical storm etc. Twitter as an emerging data source is an effective and innovative digital platform to observe trend from social media users’ perspective who are direct or indirect witnesses of the calamitous event. This paper aims to collect and analyze twitter data related to the recent wildfire in California to perform a trend analysis by classifying firsthand and credible information from Twitter users. This work investigates tweets on the recent wildfire in California and classifies them based on witnesses into two types: 1) direct witnesses and 2) indirect witnesses. The collected and analyzed information can be useful for law enforcement agencies and humanitarian organizations for communication and verification of the situational awareness during wildfire hazards. Trend analysis is an aggregated approach that includes sentimental analysis and topic modeling performed through domain-expert manual annotation and machine learning. Trend analysis ultimately builds a fine-grained analysis to assess evacuation routes and provide valuable information to the firsthand emergency responders<span style="font-family:Verdana;">.</span>
文摘Handling sentiment drifts in real time twitter data streams are a challen-ging task while performing sentiment classifications,because of the changes that occur in the sentiments of twitter users,with respect to time.The growing volume of tweets with sentiment drifts has led to the need for devising an adaptive approach to detect and handle this drift in real time.This work proposes an adap-tive learning algorithm-based framework,Twitter Sentiment Drift Analysis-Bidir-ectional Encoder Representations from Transformers(TSDA-BERT),which introduces a sentiment drift measure to detect drifts and a domain impact score to adaptively retrain the classification model with domain relevant data in real time.The framework also works on static data by converting them to data streams using the Kafka tool.The experiments conducted on real time and simulated tweets of sports,health care andfinancial topics show that the proposed system is able to detect sentiment drifts and maintain the performance of the classification model,with accuracies of 91%,87%and 90%,respectively.Though the results have been provided only for a few topics,as a proof of concept,this framework can be applied to detect sentiment drifts and perform sentiment classification on real time data streams of any topic.
