Cosine Similarity Research Articles

Adversarial nonnegative matrix factorization for temporal link prediction

Temporal link prediction has been extensively studied and widely applied in various applications, aiming to predict future network links based on the historical networks. However, most existing methods ignore the behavior of previous network updating information in temporal networks. To address these issues, we propose a novel link prediction model based on adversarial nonnegative matrix factorization, which fuses graph representation and adversarial learning to perform temporal link prediction. Specifically, we add a bounded adversary matrix to the input matrix to provide the robustness against real perturbations. Then, our model fully exploits the impact of snapshots by using communicability. Simultaneously, we utilize the cosine similarity to extract the node similarity and map it to low-dimensional latent representation to preserve the local structure. Additionally, we provide effective updating rules to learn the parameters of this model. Extensive experiments results on six real-world networks demonstrate that the proposed method outperforms several classical and the state-of-art matrix-based methods.

Oversampling-Based Imbalanced Signal Modulation Classification via Cosine Distance and Distribution

Oversampling-Based Imbalanced Signal Modulation Classification via Cosine Distance and Distribution

Novel modified weights and cosine similarity based maximum marginal projection and its application in fault diagnosis

Abstract Facing the problem that the data generated in industrial processes have few labeled samples and the local manifold learning dimensionality reduction method ignores the local spatial structure of sample points and the distance relationship in constructing different weights. To solve the above problems, this paper presents a novel modified weights and cosine similarity based maximum marginal projection named MCMMP. In MCMMP, cosine similarity is used to consider the space feature of sample points, which enhances the performance of dimensionality reduction. The new modified weights are applied to measure the between-class and the within-class sample points, which enhance the divisibility of sample points. After MCMMP dimensionality reduction, the classifier is used to classify the dimensionality reduction sample points. Finally, the proposed new method is used in two cases Tennessee Eastman Process (TEP) and Three-phase Flow Facility (TFF) to test the fault diagnosis performance. The results of the simulation process indicated that the new fault diagnosis method based on MCMMP, compared with other related diagnosis methods, has good performance.

Intelligent Fault Diagnosis for Aero-Engine Lubrication Systems Using Knowledge Graph and Deep Learning Techniques

Due to the complex structure and function of aero-engine lubrication system, fault diagnosis based on the existing health management system is not explicable and highly dependent on experts' experience. A method for constructing aeroengine lubrication system fault knowledge graph was proposed in this paper. Based on the experts' knowledge, the concept of lubrication system fault knowledge graph ontology was designed. With the help of deep learning techniques such as BiLSTM and CRF, we achieved the automatic extraction of unstructured knowledge. Next, based on the Cosine Distance and Jaccard coefficient, multi-source heterogeneous fault knowledge fusion was realized. In the end, intelligent fault knowledge question answering and fault attribution analysis are realized based on the building of areo-engine lubrication system fault knowledge graph. The application results show that the knowledge graph technology can realize the utilization of prior knowledge of lubrication system faults and the explanation of fault causes. And the knowledge graph technology has a good application prospect in the field of intelligent fault diagnosis.

Quantum Approach for Contextual Search, Retrieval, and Ranking of Classical Information.

Quantum-inspired algorithms represent an important direction in modern software information technologies that use heuristic methods and approaches of quantum science. This work presents a quantum approach for document search, retrieval, and ranking based on the Bell-like test, which is well-known in quantum physics. We propose quantum probability theory in the hyperspace analog to language (HAL) framework exploiting a Hilbert space for word and document vector specification. The quantum approach allows for accounting for specific user preferences in different contexts. To verify the algorithm proposed, we use a dataset of synthetic advertising text documents from travel agencies generated by the OpenAI GPT-4 model. We show that the "entanglement" in two-word document search and retrieval can be recognized as the frequent occurrence of two words in incompatible query contexts. We have found that the user preferences and word ordering in the query play a significant role in relatively small sizes of the HAL window. The comparison with the cosine similarity metrics demonstrates the key advantages of our approach based on the user-enforced contextual and semantic relationships between words and not just their superficial occurrence in texts. Our approach to retrieving and ranking documents allows for the creation of new information search engines that require no resource-intensive deep machine learning algorithms.

Mises-Fisher similarity-based boosted additive angular margin loss for breast cancer classification

To enhance the accuracy of breast cancer diagnosis, current practices rely on biopsies and microscopic examinations. However, this approach is known for being time-consuming, tedious, and costly. While convolutional neural networks (CNNs) have shown promise for their efficiency and high accuracy, training them effectively becomes challenging in real-world learning scenarios such as class imbalance, small-scale datasets, and label noises. Angular margin-based softmax losses, which concentrate on the angle between features and classifiers embedded in cosine similarity at the classification layer, aim to regulate feature representation learning. Nevertheless, the cosine similarity’s lack of a heavy tail impedes its ability to compactly regulate intra-class feature distribution, limiting generalization performance. Moreover, these losses are constrained to target classes when margin penalties are applied, which may not always optimize effectiveness. Addressing these hurdles, we introduce an innovative approach termed MF-BAM (Mises-Fisher Similarity-based Boosted Additive Angular Margin Loss), which extends beyond traditional cosine similarity and is anchored in the von Mises-Fisher distribution. MF-BAM not only penalizes the angle between deep features and their corresponding target class weights but also considers angles between deep features and weights associated with non-target classes. Through extensive experimentation on the BreaKHis dataset, MF-BAM achieves outstanding accuracies of 99.92%, 99.96%, 100.00%, and 98.05% for magnification levels of ×40, ×100, ×200, and ×400, respectively. Furthermore, additional experiments conducted on the BACH dataset for breast cancer classification, as well as on the LFW and YTF datasets for face recognition, affirm the generalization capability of our proposed loss function.

The distinct roles of NEIL1 and XPA in limiting aflatoxin B₁-induced mutagenesis in mice.

Dietary exposure to aflatoxin B₁ (AFB₁) is a risk factor for the development of hepatocellular carcinomas (HCCs). Following metabolic activation, AFB₁ reacts with guanines to form covalent DNA adducts, which induce high-frequency G > T transversions. The molecular signature associated with these mutational events aligns with the single base substitution signature 24 (SBS24) in the Catalog of Somatic Mutations in Cancer (COSMIC) database. Deficiencies in either base excision repair (BER) due to the absence of Nei-like DNA glycosylase 1 (NEIL1) or nucleotide excision repair (NER) due to the absence of xeroderma complementation group A protein (XPA) contribute to HCCs in murine models. In the current study, ultra-low error duplex sequencing was used to characterize mutational profiles in liver DNAs of NEIL1-deficient, XPA-deficient, and DNA repair-proficient mice following neonatal injection of 1 mg/kg AFB₁. Analyses of AFB₁-induced mutations showed high cosine similarity to SBS24, regardless of repair proficiency status. The absence of NEIL1 resulted in an approximately 30% increase in the frequency of mutations, with distribution suggesting preferential NEIL1-dependent repair of AFB₁ lesions in open chromatin regions. A trend of increased mutagenesis was also observed in the absence of XPA. Consistent with the role of XPA in transcription-coupled repair, mutational profiles in XPA-deficient mice showed disruption of the transcriptional bias in mutations associated with SBS24. Implications: Our findings define the roles of DNA repair pathways in AFB₁-induced mutagenesis and carcinogenesis in murine models, with these findings having implications in human health for those with BER and NER deficiencies.

Pottery evolution pattern discovery based on deep learning: case study of Miaozigou culture in China

Potteries, one of the tools widely used by early humans, encapsulates rich historical information. Deep neural networks have been applied to analyzing pottery digital images, bypassing the need for intricate handcrafted features. However, existing models focus solely on pottery shape comparison, neglecting the analysis of their evolution across different historical periods. In this work, we propose a method based on deep learning to assist experts in identifying the evolutionary patterns of a given pottery type within their specified chronological divisions. First we train a convolutional neural network for pottery classification, extracting low and high level features that represent different ages of pottery samples. Next, we employ clustering algorithms to identify representative potteries for each historical period based on high level features. To facilitate intuitive comparisons across different ages, we use shallow features and compute cosine similarities between potteries, visualizing shape and decoration differences. This approach enhances understanding of pottery evolution patterns directly through visual analysis. The effectiveness and efficiency of our proposed method are evaluated by validating it on three distinct era division cases using data from the Dabagou and Miaozigou archaeological sites, which represent the Miaozigou culture and exhibit clear evolutionary patterns. Our method identifies representative artifacts for each era and uncovers their evolutionary patterns effectively and efficiently, achieving conclusions comparable to those of experts while significantly reducing time compared to traditional manual methods.

Advanced classification of hot subdwarf binaries using artificial intelligence techniques and Gaia DR3 data

Hot subdwarf stars are compact blue evolved objects, burning helium in their cores surrounded by a tiny hydrogen envelope. In the Hertzsprung-Russell Diagram they are located by the blue end of the Horizontal Branch. Most models agree on a quite probable common envelope binary evolution scenario in the Red Giant phase. However, the current binarity rate for these objects is yet unsolved, but key, question in this field. This study aims to develop a novel classification method for identifying hot subdwarf binaries within large datasets using Artificial Intelligence techniques and data from the third Gaia data release (GDR3). The results will be compared with those obtained previously using Virtual Observatory techniques on coincident samples. The methods used for hot subdwarf binary classification include supervised and unsupervised machine learning techniques. Specifically, we have used Support Vector Machines (SVM) to classify 3084 hot subdwarf stars based on their colour-magnitude properties. Among these, 2815 objects have Gaia DR3 BP/RP spectra, which were classified using Self-Organizing Maps (SOM) and Convolutional Neural Networks (CNN). In order to ensure spectral quality, previously to SOM and CNN classification, our 2815 BP/RP set were pre-analysed with two different approaches: the cosine similarity technique and the Uniform Manifold Approximation and Projection (UMAP) technique. Additional analysis onto a golden sample of 88 well-defined objects, is also presented. The findings demonstrate a high agreement level (sim 70-90<!PCT!>) with the classifications from the Virtual Observatory Sed Analyzer (VOSA) tool. This shows that the SVM, SOM, and CNN methods effectively classify sources with an accuracy comparable to human inspection or non-AI techniques. Notably, SVM in a radial basis function achieves 70.97<!PCT!> reproducibility for binary targets using photometry, and CNN reaches 84.94<!PCT!> for binary detection using spectroscopy. We also found that the single--binary differences are especially observable on the infrared flux in our Gaia DR3 BP/BR spectra, at wavelengths larger than $ sim $700 nm. We find that all the methods used are in fairly good agreement and are particularly effective to discern between single and binary systems. The agreement is also consistent with the results previously obtained with VOSA. In global terms, considering all quality metrics, CNN is the method that provides the best accuracy. The methods also appear effective for detecting peculiarities in the spectra. While promising, challenges in dealing with uncertain compositions highlight the need for caution, suggesting further research is needed to refine techniques and enhance automated classification reliability, particularly for large-scale surveys.

CECS-CLIP: Fusing Domain Knowledge for Rare Wildlife Detection Model.

Accurate and efficient wildlife monitoring is essential for conservation efforts. Traditional image-based methods often struggle to detect small, occluded, or camouflaged animals due to the challenges posed by complex natural environments. To overcome these limitations, an innovative multimodal target detection framework is proposed in this study, which integrates textual information from an animal knowledge base as supplementary features to enhance detection performance. First, a concept enhancement module was developed, employing a cross-attention mechanism to fuse features based on the correlation between textual and image features, thereby obtaining enhanced image features. Secondly, a feature normalization module was developed, amplifying cosine similarity and introducing learnable parameters to continuously weight and transform image features, further enhancing their expressive power in the feature space. Rigorous experimental validation on a specialized dataset provided by the research team at Northwest A&F University demonstrates that our multimodal model achieved a 0.3% improvement in precision over single-modal methods. Compared to existing multimodal target detection algorithms, this model achieved at least a 25% improvement in AP and excelled in detecting small targets of certain species, significantly surpassing existing multimodal target detection model benchmarks. This study offers a multimodal target detection model integrating textual and image information for the conservation of rare and endangered wildlife, providing strong evidence and new perspectives for research in this field.

Hyperbolic map unravels eight regions in temperature volatility regionalization of Mainland China

Abstract Abrupt temperature volatility has detrimental effects on daily activities, macroeconomic growth, and human health. Predicting abrupt temperature volatility and thus diminishing its negative impacts can be achieved by exploring homogeneous regions of temperature volatility and analyzing the driving factors. To investigate the regionalization of temperature volatility in Mainland China, a network constructed by the cosine similarity of temperature volatility series from Mainland China was embedded in hyperbolic space. Subsequently, we partitioned the network on the hyperbolic map using the critical gap method and then found eight regions in all. Ultimately, a network of communities was constructed while the interaction among communities was quantified. This yields a perspective of temperature volatility regionalization that can accurately reflect factors including altitude, climate type, and the geographic location of mountains. Further analysis demonstrates that the regionalization in the hyperbolic map is distinct from provinces and has a realistic basis: communities in southwest China show strong correlations due to the temperature sensitivity to altitude, and communities in northern China show a convergence in the area of Dingxi, Gansu, mainly owing to the strong temperature sensitivity to climate types. As a consequence, node distributions and community divisions in the hyperbolic map can offer new insights into the regionalization of temperature volatility in Mainland China. The results demonstrate the potential of hyperbolic embedding of complex networks in forecasting future node associations in real-world data.

Effect of sequencing platforms on the sensitivity of chemical mutation detection using Hawk-Seq™

BackgroundError-corrected next-generation sequencing (ecNGS) technologies have enabled the direct evaluation of genome-wide mutations after exposure to mutagens. Previously, we reported an ecNGS methodology, Hawk-Seq™, and demonstrated its utility in evaluating mutagenicity. The evaluation of technical transferability is essential to further evaluate the reliability of ecNGS-based assays. However, cutting-edge sequencing platforms are continually evolving, which can affect the sensitivity of ecNGS. Therefore, the effect of differences in sequencing instruments on mutation data quality should be evaluated.ResultsWe assessed the performance of four sequencing platforms (HiSeq2500, NovaSeq6000, NextSeq2000, and DNBSEQ-G400) with the Hawk-Seq™ protocol for mutagenicity evaluation using DNA samples from mouse bone marrow exposed to benzo[a]pyrene (BP). The overall mutation (OM) frequencies per 106 bp in vehicle-treated samples were 0.22, 0.36, 0.46, and 0.26 for HiSeq2500, NovaSeq6000, NextSeq2000, and DNBSEQ-G400, respectively. The OM frequency of NextSeq2000 was significantly higher than that of HiSeq2500, suggesting the difference to be based on the platform. The relatively higher value in NextSeq2000 was a consequence of the G:C to C:G mutations in NextSeq2000 data (0.67 per 106 G:C bp), which was higher than the mean of the four platforms by a ca. of 0.25 per 106 G:C bp. A clear dose-dependent increase in G:C to T:A mutation frequencies was observed in all four sequencing platforms after BP exposure. The cosine similarity values of the 96-dimensional trinucleotide mutation patterns between HiSeq and the three other platforms were 0.93, 0.95, and 0.92 for NovaSeq, NextSeq, and DNBSeq, respectively. These results suggest that all platforms can provide equivalent data that reflect the characteristics of the mutagens.ConclusionsAll platforms sensitively detected mutagen-induced mutations using the Hawk-Seq™ analysis. The substitution types and frequencies of the background errors differed depending on the platform. The effects of sequencing platforms on mutagenicity evaluation should be assessed before experimentation.

A Comparative Analysis Of Collaborative Filtering Models For Game Recommendation Using Cosine Similarity, SVD, K-Means Clustering And Real-Time Game Insights

This paper presents a study on GameRS, a game recommendation system that employs collaborative filtering techniques, including Cosine Similarity, Singular Value Decomposition (SVD), and K-means. Clustering, in conjunction with real-time game insights facilitated by Groq AI. The system integrates data from the RAWG API to provide game recommendations and dynamically retrieves game details, including genres, platforms, reviews, ratings, release dates, trailers, and gameplay mechanics. Furthermore, it presents a novel User Satisfaction Index for Games (USIG), a metric designed to assess anticipated enjoyment by considering factors such as rating, genre similarity, and platform similarity. Users may pose specific inquiries related to games, to which Groq AI provides succinct and accurate answers. GameRS, developed with Streamlit, manages both the front-end interface and back-end logic, allowing users to access recommendations, game details, trailers, and additional features. Evaluation results indicate that Cosine Similarity surpasses alternative methods regarding recall and hit rate, whereas SVD and K-means provide insights into latent user preferences and clustering behaviors.

Enhancing Large Language Model Comprehension of Material Phase Diagrams through Prompt Engineering and Benchmark Datasets

Large Language Models (LLMs) excel in fields such as natural language understanding, generation, complex reasoning, and biomedicine. With advancements in materials science, traditional manual annotation methods for phase diagrams have become inadequate due to their time-consuming nature and limitations in updating thermodynamic databases. To overcome these challenges, we propose a framework based on instruction tuning, utilizing LLMs for automated end-to-end annotation of phase diagrams. High-quality phase diagram images and expert descriptions are collected from handbooks and then preprocessed to correct errors, remove redundancies, and enhance information. These preprocessed data form a golden dataset, from which a subset are used to train LLMs through hierarchical sampling. The fine-tuned LLM is then tested for automated phase diagram annotation. Results show that the fine-tuned model achieves a cosine similarity of 0.8737, improving phase diagram comprehension accuracy by 7% compared to untuned LLMs. To the best of our knowledge, this is the first paper to propose using LLMs for the automated annotation of phase diagrams, replacing traditional manual annotation methods and significantly enhancing efficiency and accuracy.

A PCA-based algorithm for online false data injection and jamming attacks detection in cyber-physical systems

Cyber-physical systems face cyberattacks that hinder performance, increase cost, or even collapse the system. Thus, rapid and accurate attack detection is crucial for quick activation of defense mechanisms. Model-based attack detection approaches are known for their precision; however, the unavailability of the exact system model poses a challenge. In response, model-free approaches have gained increased attention as a practical alternative. In this paper, an online model-free algorithm for detecting false data injection and jamming attacks on CPSs is proposed. The method leverages principal component analysis to reconstruct the expected observations in a reduced dimension space, emphasizing the most effective principal components. Then, deciding on attacked or normal operation relies on analyzing either the Euclidean distance or the cosine similarity of the discrepancy between the expected and actual observations. The proposed metrics effectively expose subtle deviations from expected behavior, as any alteration in these components augments the distance between the observed and reconstructed values. The proposed method was compared with the conventional cumulative sum discriminator and Kalman-based algorithm, using an IEEE-14, IEEE-30, and IEEE-118 bus systems. The results demonstrate the superiority of the proposed algorithm in terms of various evaluation metrics, including F-score, precision, recall, and miss detection ratio.

Stance Detection in the Context of Fake News—A New Approach

Online social networks (OSNs) are inundated with an enormous daily influx of news shared by users worldwide. Information can originate from any OSN user and quickly spread, making the task of fact-checking news both time-consuming and resource-intensive. To address this challenge, researchers are exploring machine learning techniques to automate fake news detection. This paper specifically focuses on detecting the stance of content producers—whether they support or oppose the subject of the content. Our study aims to develop and evaluate advanced text-mining models that leverage pre-trained language models enhanced with meta features derived from headlines and article bodies. We sought to determine whether incorporating the cosine distance feature could improve model prediction accuracy. After analyzing and assessing several previous competition entries, we identified three key tasks for achieving high accuracy: (1) a multi-stage approach that integrates classical and neural network classifiers, (2) the extraction of additional text-based meta features from headline and article body columns, and (3) the utilization of recent pre-trained embeddings and transformer models.

Imputing spatial transcriptomics through gene network constructed from protein language model.

Image-based spatial transcriptomic sequencing technologies have enabled the measurement of gene expression at single-cell resolution, but with a limited number of genes. Current computational approaches attempt to overcome these limitations by imputing missing genes, but face challenges regarding prediction accuracy and identification of cell populations due to the neglect of gene-gene relationships. In this context, we present stImpute, a method to impute spatial transcriptomics according to reference scRNA-seq data based on the gene network constructed from the protein language model ESM-2. Specifically, stImpute employs an autoencoder to create gene expression embeddings for both spatial transcriptomics and scRNA-seq data, which are used to identify the nearest neighboring cells between scRNA-seq and spatial transcriptomics datasets. According to the neighbored cells, the gene expressions of spatial transcriptomics cells are imputed through a graph neural network, where nodes are genes, and edges are based on cosine similarity between the ESM-2 embeddings of the gene-encoding proteins. The gene prediction uncertainty is further measured through a deep learning model. stImpute was shown to consistently outperform state-of-the-art methods across multiple datasets concerning imputation and clustering. stImpute also demonstrates robustness in producing consistent results that are insensitive to model parameters.

GCNPMDA: Human microbe-disease association prediction by hierarchical graph convolutional network with layer attention

Microorganisms play a crucial role in various physiological processes, including metabolism, immune defense, nutrition absorption, defense against cancer, and protection against pathogen colonization. Changes in microbial communities serve as potential biomarkers for diseases, offering significant insights into disease treatment and diagnosis. However, the association between microorganisms and diseases is still unclear, and more computational methods are needed to predict potential associations. In this paper, we introduce a novel computational model, the Graph Convolutional Network to Predict Microbe-Disease Associations (GCNPMDA), which employs layer attention mechanisms (see Figure 1). GCNPMDA integrates known microbe-disease associations, microbe–microbe similarities, and disease–disease similarities into a heterogeneous network. The model utilizes a Graph Convolutional Network (GCN) to learn embeddings for diseases and microbes. To enhance attribute information, microbe–microbe similarities are computed using Cosine similarity, Jaccard similarity, Gaussian kernel, and functional information, while disease–disease similarities are computed using Cosine similarity, Jaccard similarity, Gaussian kernel, and symptom information. Additionally, attention mechanisms are applied to combine embeddings from multiple graph convolution layers. The model’s predictive effectiveness is evaluated on Human Microbe-Disease Association Database (HMDAD). Leave-one-out cross-validation (LOOCV) was conducted. The Area Under ROC Curve (AUC) of LOOCV is 0.98. The 5-fold cross-validation (5-fold CV) on HMDAD yields average AUC of 0.98 ± 0.009. Furthermore, we carried out a case study of type 2 diabetes (T2D), inflammatory bowel disease (IBD), and rheumatoid arthritis. Based on existing literature evidence, it was confirmed that 6, 7, and 7 of the top-10 inferred microbes have established associations with T2D, IBD, and rheumatoid arthritis, respectively. GCNPMDA demonstrates potential efficacy in identifying disease-related microbes, offering a promising tool to uncover the intricate relationship between microorganisms and their human hosts.

A Study of the Evolution of Haze Microblog Concerns Based on a Co-Word Network Analysis

Haze is a phenomenon caused by excessive PM2.5 (air-borne particulate matter having a diameter of fewer than 2.5 μm) and other pollutants and results from the interaction between specific climatic conditions and human activities. It significantly impacts human health, transportation, and the natural environment and has aroused widespread concern. However, the influence of haze on human mental health, being hidden and indirect, is often overlooked. When haze pollution occurs, people express their feelings and concerns about haze events on media such as Weibo. At present, few studies focus on haze public opinion, as well as the changing trends in people’s discussion of haze since its emergence, which is of great significance for haze response and resource management. Based on the perspective of topic analysis, this study explores the psychological impact of haze on people by exploring the feelings of netizens in haze public opinion and investigates the evolution of people’s concerns based on long-term public opinion data. In this study, seven typical provinces and cities in China with severe haze pollution were selected as the research area. Based on data on the “haze” theme from Weibo from 2013 to 2019, first, the microblog posts were preprocessed, and the keyword co-word network was constructed. Second, the Louvain algorithm was used to detect the topic community. Based on this, the cosine similarity was calculated to realize the temporal evolution analysis of topics. The results show that with the development and change in haze pollution, the content and intensity of the topics netizens pay attention to have changed, including five types: merger, split, survival, transformation, and rebirth/extinction. People’s attention to haze shows obvious spatial differences, and it is related to the degree of haze pollution, which is bipolar. Areas with severe haze tend to pay more attention to haze itself and its influence, while areas with light haze pay more attention to haze control. The research results can provide valuable insights for governments and relevant departments in guiding public opinion and resource allocation.

Service priority classification using machine learning

This article details a procedure for classifying service cases with various priority levels based on machine learning (ML). It accurately defines the priority level of each service case. The presence of imbalanced datasets in service cases poses a challenge for achieving reliable classification accuracy. To address this, the use of the synthetic minority over-sampling technique (SMOTE) was proposed as the method for balancing the datasets prior to applying the ML method. From these experimental results, an improvement in the precision of the learning process was observed, which led to better outcomes in the test sets. This improvement was measured using the efficiency metrics from the confusion matrix. The experiment involved 6,182 service cases, categorized into four levels: critical, serious, moderate, and low. These were based on test comparisons with other ML methods. The accuracy achieved in the test data was 94.37%. By employing a hybrid technique to address the imbalance in SMOTE and the support vector machine model, it was found to be more effective than the comparative term frequency-inverse document frequency model that was used in conjunction with cosine similarity, which achieved an evaluation score of 70.14%.