Python Programming Language Research Articles

HiFiBGC: an ensemble approach for improved biosynthetic gene cluster detection in PacBio HiFi-read metagenomes.

Microbes produce diverse bioactive natural products with applications in fields such as medicine and agriculture. In their genomes, these natural products are encoded by physically clustered genes known as biosynthetic gene clusters (BGCs). Genome and metagenome sequencing advances have enabled high-throughput identification of BGCs as a promising avenue for natural product discovery. BGC mining from (meta)genomes using in silico tools has allowed access to a vast diversity of potentially novel natural products. However, a fundamental limitation has been the ability to assemble complete BGCs, especially from complex metagenomes. With their fragmented assemblies, short-read technologies struggle to recover complete BGCs, such as the long and repetitive nonribosomal peptide synthetase (NRPS) and polyketide synthase (PKS). Recent advances in long-read sequencing, such as the High Fidelity (HiFi) technology from PacBio, have reduced this limitation and can help retrieve both accurate and complete BGCs from metagenomes, warranting improvement in the existing BGC identification approach for better utilization of HiFi data. Here, we present HiFiBGC, a command-line-based workflow to identify BGCs in PacBio HiFi metagenomes. HiFiBGC leverages an ensemble of assemblies from three HiFi-tailored metagenome assemblers and the reads not represented in these assemblies. Based on our analyses of four HiFi metagenomic datasets from four different environments, we show that HiFiBGC identifies, on average, 78% more BGCs than the top-performing single-assembler-based method. This increase is due to HiFiBGC's ensemble assembly approach, which improves recovery by 25%, as well as from the inclusion of mostly fragmented BGCs identified in the unmapped reads. HiFiBGC is a computational workflow for identifying BGCs in long-read HiFi metagenomes, implemented majorly using Python programming language and workflow manager Snakemake. HiFiBGC is available on GitHub at https://github.com/ay-amityadav/HiFiBGC under the MIT license. The code related to the figures and analyses presented in the manuscript is available at https://github.com/ay-amityadav/HiFiBGC_analyses .

Analysis of the effectiveness of using U-net architecture for classification and segmentation of glioma in MRI images

The purpose of the research is to analyze the efficiency of the U-net neural network architecture in decision support systems for glioma diagnostics and segmentation of brain areas affected by it on MRI images.Methods. To conduct experimental studies, a training dataset was generated and the data was normalized. A software implementation of the U-Net neural network architecture was performed using the Keras framework in the Python programming language. The neural network model was trained.Results. A series of experiments were conducted, during which error and classification matrices were obtained, the efficiency of classification of the trained neural network model for the "Tumor" and "No tumor" classes was assessed using metrics such as Recall, Precision and F1-measure, and the quality of segmentation of glioma-affected areas on the test data set was assessed. The quality of segmentation was assessed using the IoU metric, which reflects the ratio of the areas of the bounding boxes and is used to assess the accuracy of the spatial correspondence of the predicted segmented areas highlighted on the masks. Based on the results of testing the neural network model in solving the problem of segmenting brain areas affected by glioma, the average value of the IoU metric was 0.812, which is an acceptable result.Conclusion. The testing results showed that the neural network model based on the U-net architecture is able to effectively diagnose the presence of glioma with acceptable values of the classification and segmentation quality metrics, which indicates the possibility of using this neural network model in medical decision support systems for glioma diagnostics, as well as its segmentation on MRI images. However, it is advisable to refine this neural network model to reduce the number of false negative classification results, which is critically important in medical diagnostics.

A two-stage deep-learning model for determination of the contact of mandibular third molars with the mandibular canal on panoramic radiographs.

This study aimed to assess the accuracy of a two-stage deep learning (DL) model for (1)detecting mandibular third molars (MTMs) and the mandibular canal (MC), and (2)classifying the anatomical relationship between these structures (contact/no contact) on panoramic radiographs. MTMs and MCs were labeled on panoramic radiographs by a calibrated examiner using bounding boxes. Each bounding box contained MTM and MC on one side. The relationship of MTMs with the MC was assessed on CBCT scans by two independent examiners without the knowledge of the condition of MTM and MC on the corresponding panoramic image, and dichotomized as contact/no contact. Data were split into training, validation, and testing sets with a ratio of 80:10:10. Faster R-CNN was used for detecting MTMs and MCs and ResNeXt for classifying their relationship. AP50 and AP75 were used as outcomes for detecting MTMs and MCs, and accuracy, precision, recall, F1-score, and the area-under-the-receiver-operating-characteristics curve (AUROC) were used to assess classification performance. The training and validation of the models were conducted using the Python programming language with the PyTorch framework. Three hundred eighty-seven panoramic radiographs were evaluated. MTMs were present bilaterally on 232 and unilaterally on 155 radiographs. In total, 619 images were collected which included MTMs and MCs. AP50 and AP75 indicating accuracy for detecting MTMs and MCs were 0.99 and 0.90 respectively. Classification accuracy, recall, specificity, F1-score, precision, and AUROC values were 0.85, 0.85, 0.93, 0.84, 0.86, and 0.91, respectively. DL can detect MTMs and MCs and accurately assess their anatomical relationship on panoramic radiographs.

SentinelGuard Pro: Deploying Cutting‐Edge FusionNet for Unerring Detection and Enforcement of Wrong Parking Incidents

ABSTRACTWrong parking incidents pose a pervasive challenge in urban environments, disrupting the smooth flow of traffic, compromising safety and contributing to various logistical issues. Unauthorized parking occurs when vehicles are parked in locations not designated for such purposes, leading to a myriad of problems for both authorities and the general public. This research introduces a pioneering approach to confront the persistent challenge of unauthorized parking incidents in urban environments. The study focuses on harnessing the advanced capabilities of the FusionNet model to enhance the accuracy of license plate detection. This paper introduces the YOLO v8 Model, a deep learning architecture designed to enhance urban parking management by accurately detecting vehicles parked in unauthorized slots. The objective is to enhance parking management efficiency by accurately detecting vehicles and their occupancy status in designated parking areas. The methodology begins with data collection and preprocessing of images of parking spaces, followed by the training of YOLO v8 to identify vehicles and parking spaces in real time. Leveraging a diverse dataset encompassing various parking scenarios, including instances of unauthorized parking, the model achieves an accuracy of 98.50% in identifying vehicles outside designated areas. This model segments characters from detected license plates, enabling the accurate extraction of alphanumeric information associated with each vehicle. The integrated system provides timely identification of parking violations and facilitates effective enforcement actions through captured license plate data. Results demonstrate the model's effectiveness in real‐world scenarios, showcasing its potential for improving urban safety and efficiency. The implementation of FusionNet in the Python programming language, the proposed solution aims to streamline parking management, improve compliance with parking regulations and enhance overall urban mobility., with robust precision 96.17%, specificity 97.42% and sensitivity 96.19%, surpassing other MobileNet, CNN, ANN, DNN and EfficientNet models.

Numerical Simulation Study of Thermal Performance in Hot Water Storage Tanks with External and Internal Heat Exchangers

This paper presents a numerical analysis of two hot water storage tank configurations—one equipped with an external heat exchanger (Tank-1) and the other with an internal heat exchanger (Tank-2). The objective is to evaluate and compare their thermal performance during charging and discharging processes. The numerical model is developed by solving a system of ordinary differential equations using the 4th-order Runge–Kutta method, implemented in the Python programming language. The results indicate that Tank-1 demonstrated a higher charging efficiency of 94.6%, achieving full charge in approximately 2 h and 20 min. In comparison, Tank-2 required 3 h and 47 min to reach full charge, with a charging efficiency of 85.9%. During discharge, both configurations exhibited similar behavior, with an efficiency of 13.63% over approximately 33 min. The analysis showed that the external heat exchanger configuration led to more effective thermal stratification, supported by the Richardson number analysis, which indicated a significant effect of buoyancy during charging. This design advantage makes Tank-1 particularly suitable for applications requiring rapid heating and minimal heat loss, such as in cold climates or intermittent demand systems. The numerical model demonstrated reliable predictive accuracy, achieving an RMSE of 6.1% for the charging process and 6.8% for the discharging process, thereby validating the model’s reliability. These findings highlight the superior performance of the external heat exchanger configuration for fast and efficient energy storage, particularly for applications in cold climates.

Constant Values Distribution Investigation in the C Programs Source Code

Currently, software engineering plays a key role in software development, one of the criteria for the development of which is the investigation of its factology and various scientific and practical patterns. An important aspect of this area is the logic of program execution, operating with internal data, and, in particular, constant values, the identification of patterns in which actualizes this research. The main applications of this pattern include obtaining fundamental knowledge about algorithms, creating new and expanding existing metrics for evaluating and comparing program code, developing methods for its optimization, using it in genetic programming, etc.The purpose of this article is to obtain the frequency distribution of constant values in the source code of programs in the C programming language.The essence of the presented approach is to create a method for statistical analysis of the text of the source codes of programs contained in the ExeBench dataset (which consists of a huge amount of source code of functions in the C programming language, their assembler code for various processor architectures, compilation errors and other information).The proposed method is based on the use of algorithms for lexical and syntactic analysis of source code functions, semantic definition of constant types, and conversion of the recording of programming language symbols into the corresponding numeric or string values.The method has an implementation in the form of a software tool in the Python programming language, given in the form of an intuitive pseudocode. Experiments using this prototype allowed us to obtain the desired distribution of constant values for the source code of programs in the C programming language. Analysis of the obtained results allowed us to make a number of important theoretical and practical conclusions regarding the most frequently used constants, the correspondence of the obtained distribution to the Zipf law and its proximity to the exponential function, the anomalous appearance of a number of constants in the Top 50, etc.The scientific novelty of the proposed approach lies in the fact that the distribution of constant values for the source code of programs in the C programming language is obtained for the first time.The theoretical significance consists in obtaining new fundamental knowledge regarding the features and patterns of source code constructions, which can be extended to other programming languages.The practical significance consists in applying the distribution to a wide range of tasks, including the author's genetic reverse engineering, which in itself is a qualitatively new direction.

Experience of applying convolutional neural network for binary classifcation of microphotographs of thyroid cytology specimens

Objective: to evaluate the effectiveness of a convolutional neural network model for automated cytologic diagnosis of papillary thyroid cancer and benign thyroid nodules.Material and Methods. The convolutional neural network was developed in the Python programming language using the TensorFlow 2.15.0 open source library. For the study, a dataset that included two categories of pathologies was generated: 1597 microphotographs of papillary carcinoma and 767 microphotographs of benign nodules (colloid goiter and adenomatous nodules). To form a training sample and evaluate the model’s performance metrics on the test sample, the dataset was divided in a ratio of 80/20.Results. In classifying papillary carcinoma, the model achieved precision of 89.3 %, recall of 92.4 %, specifcity of 77.4 % and F1 score of 91.4 %. When identifying benign nodules, the presicion, recall, specifcity and F1 score were 83.3 %, 77.4 %, 92.4 %, and 80.3 %, respectively, indicating a higher rate of false-positive and false-negative predictions. The AUC was 0.91 at the individual microphotograph level and 0.94 at the serial microphotograph level from one patient, indicating the high ability of the trained model to differentiate between malignant and benign thyroid lesions based on microphotographs of fne-needle aspiration biopsy specimens.Conclusion. Further improvement of the neural network model by training on larger and more diverse datasets of microphotographs of cytological specimens of the thyroid gland will help improve its diagnostic range and performance. The developed model can be used to develop software for identifying thyroid pathologies.

Application of Artificial Intelligence Technology for Prompt Diagnosis of Cast Iron Mechanical Properties

Kinetic indentation is widely used to measure physical and mechanical properties of materials as one of the most universal methods for non-destructive testing. This paper uses the latest advances in artificial intelligence and capabilities of the Python programming language libraries allowing to carry out accurate measurements of cast iron hardness based on the data of the material’s micro-impact loading diagram. It has been shown that use of machine learning allows eliminating gross errors and reducing the error of indirect hardness evaluation in several times – down to 10 units according to Brinell HB. It has also been established that formation of additional features for training models (based on traditionally used characteristics: penetration depths, indenter movement speed and contact forces at certain points in time) has a positive effect on the accuracy of measurements, but amount of measurements should also be optimized. Feasibility of effective use of machine learning to evaluate hardness has been demonstrated by comparing of calculated hardness values with data obtained with standard testing methods. Advantage of the developed testing method is the fact that the developed algorithms can be used for prompt diagnostics of cast iron hardness using existing equipment. It is appropriate to extend the proposed approach for determination of other mechanical properties of cast iron: yield strength, strain hardening index, creep, relaxation, determined by indentation methods.

What is the “best” way to measure the relative location variables in the market value assessment? An econometric method applied to an Italian case study

The present research is dedicated to investigating the explanatory power of relative location variables in assessing and forecasting market values. Here, relative location refers to the spatial position (geographical context) of a building or property in relation to a given Point Of Interest (POI). Specifically, a methodological approach is proposed for identifying the most suitable quantification modality based on statistical performance and consistency with the market mechanisms of the specific reference context. For a case study in Northern Italy, we collected data on 615 residential properties and 2673 POIs, including cultural facilities, school and education institutions, commercial services, sports, entertainment, and leisure facilities, health and care services, public transport systems, urban parks, and green areas. The relative location between the collected properties and the POIs is assessed using an automated calculation procedure developed in the Python programming language, in conjunction with Geographic Information Software (GIS). This automatism allows the assessment of relative location in terms of different Units Of Measure (UOM), such as straight-line distance, travel time by car, travel time on foot, travel time by public transport, and the number of POIs in a 400 m/1 km ring buffer. Since 615 residential buildings and 2673 POIs were analysed, with their relative locations measured using six different UOMs, a database of 9'865'215 data was produced. Furthermore, for each category of POI, a feature importance analysis guides the selection of the best UOM, i.e., the most statistically significant one. Considering the chosen UOM, an optimised econometric technique is finally implemented to analyse the functional relationships between the market values of residential properties and the set of identified relative location variables.

The infection post flexible UreteroreNoscopy (I-FUN) predictive model based on machine learning: a new clinical tool to assess the risk of sepsis post retrograde intrarenal surgery for kidney stone disease.

To create a machine-learning model for estimating the likelihood of post-retrograde intrarenal surgery (RIRS) sepsis. All consecutive patients with kidney stone(s) only undergoing RIRS in 16 centers were prospectively included (January 2022-August 2023). adult, renal stone(s) only, CT scan (within three months), mid-stream urine culture (within 10 days). concomitant ureteral stone, bilateral procedures. In case of symptomatic infection/asymptomatic bacteriuria, patients were given six days of antibiotics according to susceptibility profiles. All patients had antibiotics prophylaxis. Variables selected for the model: age, gender, age-adjusted Charlson Comorbidity Index, stone volume, indwelling preoperative bladder catheter, urine culture, single/multiple stones, indwelling preoperative stent/nephrostomy, ureteric access sheath, surgical time. Analysis was conducted using Python programming language, with Pandas library and machine learning models implemented using the Scikit-learn library. Machine learning algorithms tested: Decision Tree, Random Forest, Gradient Boosting. Overall performance was accurately estimated by K-Fold cross-validation with three folds. 1552 patients were included. There were 20 (1.3%) sepsis cases, 16 (1.0%) septic shock cases, and three more cases (0.2%) of sepsis-related deaths. Random Forest model showed the best performance (precision = 1.00; recall = 0.86; F1 score = 0.92; accuracy = 0.92). A web-based interface of the predictive model was built and is available at https://emabal.pythonanywhere.com/ CONCLUSIONS: Our model can predict post-RIRS sepsis with high accuracy and might facilitate patient selection for day-surgery procedures and identify patients at higher risk of sepsis who deserve extreme attention for prompt identification and treatment.

A machine learning and DFT assisted analysis of benzodithiophene based organic dyes for possible photovoltaic applications

We present a synergistic approach to combine Machine Learning (ML), Density Functional Theory (DFT), and molecular descriptor analysis for designing high-performance benzodithiophene (BDT) based chromophores. A dataset of 366 BDT incorporated moieties is compiled from literature while their molecular descriptors are designed by using Python programming language. Linear and Random Forest Regression models produces best results to predict their exciton binding energy (Eb) with their R-Squared (R2) value 0.87 and 0.94 respectively. Their DFT calculations provides additional features, including molecular charges. Their ML models also reveals that their Eb values are a crucial predictor for their photovoltaic (PV) performance as its lower value could facilitate efficient charge carrier separation. For this, their hydrogen bond acceptors (HBA) and topological polar surface area (TPSA) emerges as key descriptors during their regression analysis. Their DFT validation shows negligible differences in their molecular charges to suggest their electron donor/acceptor moieties can significantly impact their chromophore nature. The current research work is helpful for efficiently screening the suitability of organic chromophores for their PV applications through advanced computational tools.

IMPLEMENTASI METODE NAÏVE BAYES UNTUK PREDIKSI KELAYAKAN BANTUAN MODAL DAN KREDIT USAHA DI DESA SELAT ABIANSEMAL BADUNG

Small, Micro, and Medium Enterprises (MSMEs) are small-scale businesses carried out by individuals or business entities with a certain amount of net worth and sales proceeds. MSMEs in Abiansemal Strait Village, Badung, still use manual methods in analyzing data. Conditions like this are the basis for this study to create a system that can help make it easier for the Abiansemal Badung Strait Village if there is an assistance program from the government, both business capital assistance, and business credit applications to be given to MSME actors. Naïve Bayes' method of classifying MSMEs is built on concepts explored from the interview process, literature studies and system implementation. The design of this system was made using the Python programming language. The CRISP-DM model is a system development method used in the classification of MSMEs. The Feasibility Prediction Model for Capital Assistance and Business Credit using the Naïve Bayes Method can make it easier for users to find out whether the existence of a web-based classification and recommendation system can make it easier for users to carry out the MSME classification process easily and users can see the solutions recommended by referral MSMEs that have better business conditions directly.

RadicalPy: A Tool for Spin Dynamics Simulations.

Radical pairs (electron-hole pairs, polaron pairs) are transient reaction intermediates that are found and exploited in all areas of science, from the hard realm of physics in the form of organic semiconductors, spintronics, quantum computing, and solar cells to the soft domain of chemistry and biology under the guise of chemical reactions in solution, biomimetic systems, and quantum biology. Quantitative analysis of radical pair phenomena has historically been successful by a few select groups. With this in mind, we present an intuitive open-source framework in the Python programming language that provides classical, semiclassical, and quantum simulation methodologies. A radical pair kinetic rate equation solver, Monte Carlo-based spin dephasing rate estimations, and molecule database functionalities are implemented. We introduce the kine-quantum method, a new approach that amalgamates classical rate equations, semiclassical, and quantum techniques. This method resolves the prohibitively large memory requirement issues of quantum approaches while achieving higher accuracy, and it also offers wavelength-resolved simulations, producing time- and wavelength-resolved magnetic field effect simulations. Model examples illustrate the versatility and ease of use of the software, including the new approach applied to the magnetosensitive absorption and fluorescence of flavin adenine dinucleotide photochemistry, spin-spin interaction estimation from molecular dynamics simulations on radical pairs inside reverse micelles, radical pair anisotropy inside proteins, and triplet exciton pairs in anthracene crystals. The intuitive interface also allows this software to be used as a teaching or learning aid for those interested in the field of spin chemistry. Furthermore, the software aims to be modular and extensible, with the aim to standardize how spin dynamics simulations are performed.

DIGITAL METHOD FOR PROCESSING EVENTS OF (γ,np)-REACTIONS ON 12C, 14N, AND 16O NUCLEI, OBTAINED USING BY TRACK 4π-DETECTOR

To study (γ,np)-reactions on the nuclei of 12C, 14N, and 16O, an algorithm-sequence of specific actions has been developed to obtain physical information about events using digital methods. A set of corresponding graphical applications has been created in the Python programming language, which allows one specialist to perform all procedures to obtain physical information regarding the studied reactions on a computer. An automated method for determining the coordinates of points along the track has been developed, significantly speeding up the process of measuring tracks. A comparison of kinematic parameters obtained by the digital methods and with the help of specialized measuring devices has been made. It has been found that the digital method improves the quality of measurement and reduces the absolute measurement error.

Exploring Non-linear Dynamics: Constructing the Bifurcation Diagram of a Damped Driven Pendulum using Python

In this paper, we present a detailed analysis and construction of the bifurcation diagram for the damped-driven pendulum system. The bifurcation diagram in general presents the qualitative changes of the steady-state behavior for the pendulum. For this purpose, we implement the use of the Python programming language with the inclusion of scientific libraries. This nonlinear dynamical system is an example of a system that exhibits a chaotic regime, which is the sensitivity of its behavior to the initial conditions and the parameters of the system. We investigate the response of the system to a range of drive strengths γ applied. By changing the driving strength, the system reveals patterns of periodicity, quasi-periodic, and chaotic regimes. The critical values where it goes from regular motion to chaotic one are highlighted, offering further understanding of the mechanisms of the transitions. This study presents the use of the Python programming language for the modeling and visualization of non-dynamic systems and contributes to a deeper understanding of nonlinear oscillator dynamics.

Estimating the design parameters of a space-based radio surveillance system

Currently, small spacecraft with both optoelectronic and radar imaging equipment are becoming increasingly common. The purpose of the work is to improve the efficiency of preliminary assessment of achievable characteristics of radio surveillance payloads at the initial stages of design of small spacecraft. The paper describes the advantages of using radar imaging equipment, as well as the main trends in its development. The main areas of application of spacecraft with radar of different frequency ranges are given; the advantages of each frequency range are described. The methodology of determining the parameters of the trajectory signal when the platform moves in a circular orbit, taking into account the assumptions associated with estimating the size of the irradiation zone in azimuth is considered. Based on the considered methodology, a program is developed in Python programming language that makes it possible to estimate the length of synthesized aperture, synthesis time and azimuthal resolution of the target equipment on the basis of mass and dimensional characteristics of the antenna and spacecraft orbit parameters. A graphical user interface has been developed for the program which allows the user to interactively vary the initial data for calculation and evaluate the graphical representation of the result. The developed software system can be used for calculation of the main design parameters of small spacecraft with radar imaging equipment at the preliminary design stage.

Web Application Development for TODIM Method Automation and Alternatives Evaluation

The TODIM method (Tomada de Decisao Interativa Multicriterio), which in Portuguese means “Interactive and Multicriteria Decision Making”, is a process of evaluation alternatives, with various academic and professional uses. The current project focuses on the first approach, considering students, professors and investigators as the main beneficiaries and target audience. There is a shortage of software that automate the TODIM method, therefore it is proposed to develop a web application mainly using Python, HTML and JavaScript programming languages that can satisfy this necessity. To guarantee a uniformity in the results obtained by this program, samples of results obtained by this method by other researchers are taken as a basis and guide. To develop the application, the complete functioning of TODIM as an alternative evaluation approach must be understood. In a general view, TODIM uses pairwise comparisons between decision criteria while eliminating the inconsistencies that arise from such comparisons. Thus, the main idea is to measure the degree of dominance in each alternative over the others using the prospective value function. As result, it calculates the overall and partial degrees of dominance of each alternative to finally lead to a classification or “ranking” of the best alternatives.

Optimization of big data analysis resources supported by XGBoost algorithm: Comprehensive analysis of industry 5.0 and ESG performance

To enable state-owned enterprises in Industry 5.0 to better carry out M&A activities, it is important and necessary to provide early warning of M&A risks, which directly affects the interests of both parties and even affects the effectiveness of state-owned enterprise reform. The author proposes the optimization of big data analysis resources supported by the XGBoost algorithm: a comprehensive analysis of Industry 5.0 and ESG performance. Design a comprehensive evaluation system to measure the M&A risk of state-owned listed companies. Using Python programming language to achieve data crawling and processing. Build an early warning model using the XGBoost algorithm. To further evaluate the effectiveness of the early warning model, comparative experiments were conducted. Using multiple linear regression models to study the significant factors of merger and acquisition risk. The experimental results show that the prediction accuracy based on the XGBoost algorithm is 80 %, which performs the best among all models and has stronger reliability and applicability. ConclusionThe return on investment capital, operating profit margin, and net profit from paid consideration are more important and effective in predicting merger and acquisition risks; The total asset turnover rate, return on investment capital, equity balance, and audit quality are more conducive to suppressing merger and acquisition risks.

Sentiment Analysis of the MK Decision Trial of the Result of the 2024 President and Vice President General Election on Social Media X Using the Support Vector Machine Method

Support Vector Machine (SVM) is a method of machine learning often used in classification and regression issues, especially in the classification of commentary reviews on social media such as Twitter. The Constitutional Court (MK) has the authority to resolve disputes resulting from the general election, including the 2024 presidential election. As an institution that maintains fairness and transparency in the democratic process, the Constitutional Court's decisions are often at the center of public attention and debate, especially on social media. In the 2024 general election, various allegations of fraud led to protests from several parties who felt aggrieved. The final and binding Constitutional Court's decision is expected to resolve the conflict that arises, but it often does not satisfy all parties, causing political and social tensions. This conflict can be reflected through public opinion expressed on social media, such as Twitter, where various responses and sentiments to the decision are essential analysis materials. This Research uses the Support Vector Machine (SVM) algorithm with a dataset of 1383 review comments divided by an 80:20 ratio for training and testing. The system was implemented using the Python programming language, with evaluations showing the highest accuracy at 61.00%, precision at 61.00%, and recall at 62.00%. This study aims to analyze public sentiment regarding the Constitutional Court's decision using the SVM method and identify the tendency of public opinion as positive, negative, or neutral. Through this study, it is expected that a deeper understanding of the public's perception of the Constitutional Court's decision is obtained. In addition, this Research is likely to contribute to developing sentiment analysis methods in the future and provide a basis for recommendations for the Constitutional Court in handling election result disputes better.

Opinion divergence, investor sentiment, and stock liquidity: Evidence from social media

ABSTRACT This paper developed a mediating effect model of retail opinion divergence, investor sentiment, and stock liquidity to investigate how investor comments and bullish-bearish-polling activities on social media affect investors’ attitudes and behaviours, thus, the stock market. The paper first used the Python programming language to scrape the bullish-bearish-polling outcomes for each stock and developed an investor opinion divergence index. Next, the study collected online investor comments, from which an online investor sentiment index was developed through machine-learning-based ways. The analysis results show that both investor sentiment and retail opinion divergence significantly impact stock liquidity, and investor sentiment plays a mediating role in it.