Traditional Decision Research Articles

An Experimental Comparison of Self-Adaptive Differential Evolution Algorithms to Induce Oblique Decision Trees

This study addresses the challenge of generating accurate and compact oblique decision trees using self-adaptive differential evolution algorithms. Although traditional decision tree induction methods create explainable models, they often fail to achieve optimal classification accuracy. To overcome these limitations, other strategies, such as those based on evolutionary computation, have been proposed in the literature. In particular, we evaluate the use of self-adaptive differential evolution variants to evolve a population of oblique decision trees encoded as real-valued vectors. Our proposal includes (1) an alternative initialization strategy that reduces redundant nodes and (2) a fitness function that penalizes excessive leaf nodes, promoting smaller and more accurate decision trees. We perform a comparative performance analysis of these differential evolution variants, showing that while they exhibit similar statistical behavior, the Single-Objective real-parameter optimization (jSO) method produces the most accurate oblique decision trees and is second best in compactness. The findings highlight the potential of self-adaptive differential evolution algorithms to improve the effectiveness of oblique decision trees in machine learning applications.

AI-Driven Optimization of Financial Quantitative Trading Algorithms and Enhancement of Market Forecasting Capabilities

Abstract: The application of artificial intelligence (AI) into financial markets has revolutionised quantitative trading and market forecasting by increasing the efficiency of algorithmic trading, improving the accuracy of market predictions and facilitating real-time market decisions. This paper will provide an overview of the application of Al in the financial markets focusing on the use of machine learning (ML), deep learning (DL) and reinforcement learning (RL) in optimizing the trading algorithms, specifically the capability of Al to process very high data points and complex relationships that other quantitative models are unable to capture. We will discuss trading algorithms such as XGBoost, deep neural networks such as long short-term memory (LSTM) networks and convolutional neural networks (CNNs), how they can outperform traditional quantitative trading models and real-time decision making in stock price prediction, pattern recognition and trading strategy optimisation. We will also look at Al-enhanced predictive models that utilise deep learning and layered models, such as Natural language processing (NLP) sentiment analysis to capture the public sentiment in the market to forecast employing diverse datasets such as historical prices, market volatility, macroeconomic factors and social media sentiment to improve the forecasting accuracy. By going through several experiments and case studies, this paper will shed light on the impact of entrusting quantitative trading and market forecasting decisions to AI for improved performance and reduced errors. There are many challenges ahead but AI plays a constructive role in improving the trading strategies and forecasting market outcomes accurately.

Systematic benchmarking demonstrates large language models have not reached the diagnostic accuracy of traditional rare-disease decision support tools.

Large language models (LLMs) show promise in supporting differential diagnosis, but their performance is challenging to evaluate due to the unstructured nature of their responses. To assess the current capabilities of LLMs to diagnose genetic diseases, we benchmarked these models on 5,213 case reports using the Phenopacket Schema, the Human Phenotype Ontology and Mondo disease ontology. Prompts generated from each phenopacket were sent to three generative pretrained transformer (GPT) models. The same phenopackets were used as input to a widely used diagnostic tool, Exomiser, in phenotype-only mode. The best LLM ranked the correct diagnosis first in 23.6% of cases, whereas Exomiser did so in 35.5% of cases. While the performance of LLMs for supporting differential diagnosis has been improving, it has not reached the level of commonly used traditional bioinformatics tools. Future research is needed to determine the best approach to incorporate LLMs into diagnostic pipelines.

Research on the Application Framework of Generative AI in Emergency Response Decision Support Systems for Emergencies

With the rapid development of artificial intelligence technology, generative AI has shown broad application prospects and potential in various fields. Frequent emergencies have put forward higher requirements for traditional Emergency Response Decision Support Systems (ERDSS). This paper proposes a theoretical framework of ERDSS based on generative AI (ERDSS-GAI), which deeply integrates generative AI with three stages of emergency response decision-making. The framework aims to leverage the advantages of generative AI in massive data processing, knowledge mining, strategy optimization, and other aspects, thereby enhancing the intelligence level and emergency response capability of ERDSS. The key components and implementation path of ERDSS-GAI are systematically explained from a theoretical perspective, and its application value is analyzed through the case of rainstorm and flood disaster in Shenzhen. This research demonstrates that generative AI can improve the scientific and refined level of emergency response decision-making, providing a theoretical framework and practical insights for its widespread adoption in emergency management.

Approximating decision trees with priority hypotheses

This paper addresses the problem of creating decision trees for identifying hypotheses, also known as entities, in a setting where the cost of an action is dependent on the true hypothesis. Specifically, we consider the scenario where n hypotheses are divided into m groups based on their priority levels. Taking an action on a higher priority hypothesis incurs a higher cost. This is relevant to many real-world applications where cost-sensitive decisions need to be made. For example, in a medical diagnosis task, the goal is to take a series of actions (such as medical tests) to identify a cause. Each action in this process requires conducting a test on the patient and observing the outcome, which can take anywhere from a few minutes to several weeks depending on the test. In this case, the cost (the result of waiting for the outcome) is higher if the true hypothesis is more time-sensitive. For example, if the true hypothesis is toxic chemical exposure (as opposed to a chronic disease such as diabetes), a delay of a few minutes could significantly increase the patient's risk of mortality. We propose a group greedy algorithm to solve this problem. We demonstrate that under worst-case scenarios, our algorithm has an approximation ratio of O(mlog⁡n). Importantly, when m=1, meaning there is only one group of hypotheses, our result is consistent with the logarithmic approximation bound for the traditional optimal decision tree problem.

The impact of a primary aldosteronism predictive model in secondary hypertension decision support.

To determine whether the addition of a primary aldosteronism (PA) predictive model to a secondary hypertension decision support tool increases screening for PA in a primary care setting. One hundred fifty-three primary care clinics were randomized to receive a secondary hypertension decision support tool with or without an integrated predictive model between August 2023 and April 2024. For patients with risk scores in the top 1 percentile, 63/2896 (2.2%) patients where the alert was displayed in model clinics had the order set launched, while 12/1210 (1.0%) in no-model clinics had the order set launched (P = .014). Nineteen of 2896 (0.66%) of these highest risk patients in model clinics had an aldosterone-to-renin ratio (ARR) ordered compared to 0/1210 (0.0%) patients in no-model clinics (P = .010). For patients with scores not in the top 1 percentile, 438/20 493 (2.1%) patients in model clinics had the order set launched compared to 273/17 820 (1.5%) in no-model clinics (P < .001). One hundred twenty-four of 20 493 (0.61%) in model clinics had an ARR ordered compared to 34/17 820 (0.19%) in the no-model clinics (P < .001). The addition of a PA predictive model to secondary hypertension alert displays and triggering criteria along with order set displays and order preselection criteria results in a statistically and clinically significant increase in screening for PA, a condition that clinicians insufficiently screen for currently. Addition of a predictive model for an under-screened condition to traditional clinical decision support may increase screening for these conditions.

Evaluation of Deep Isolation Forest (DIF) Algorithm for Mineral Prospectivity Mapping of Polymetallic Deposits

Mineral prospectivity mapping (MPM) is crucial for efficient mineral exploration, where prospective zones are identified in a cost-effective manner. This study focuses on generating prospectivity maps for hydrothermal polymetallic mineralization in the Feizabad area, in northeastern Iran, using unsupervised anomaly detection methods, i.e., isolation forest (IForest) and deep isolation forest (DIF) algorithms. As mineralization events are rare and complex, traditional approaches continue to encounter difficulties, despite advances in MPM. In this respect, unsupervised anomaly detection algorithms, which do not rely on ground truth samples, offer a suitable solution. Here, we compile geospatial datasets on the Feizabad area, which is known for its polymetallic mineralization showings. Fourteen evidence layers were created, based on the geology and mineralization characteristics of the area. Both the IForest and DIF algorithms were employed to identify areas with high mineralization potential. The DIF, which uses neural networks to handle non-linear relationships in high-dimensional data, outperformed the traditional decision tree-based IForest algorithm. The results, evaluated through a success rate curve, demonstrated that the DIF provided more accurate prospectivity maps, effectively capturing complex, non-linear relationships. This highlights the DIF algorithm’s suitability for MPM, offering significant advantages over the IForest algorithm. The present study concludes that the DIF algorithm, and similar unsupervised anomaly detection algorithms, are highly effective for MPM, making them valuable tools for both brownfield and greenfield exploration.

On global robustness of an adversarial risk analysis solution

AbstractAdversarial Risk Analysis (ARA) can be a more realistic and practical alternative to traditional game theoretic or decision theoretic approaches for modeling strategic decision‐making in the presence of an adversary. ARA relies on quantifying the decision‐maker's (DM's) uncertainties about the adversary's strategic thinking, choices and utilities via probability distributions to identify the optimal solution for the DM. ARA solution will be sensitive to the choices of prior distributions used for modelling the expert beliefs. Yet, to date, no mathematical results to characterize the robustness of the ARA solution to the misspecification of one or more prior distributions exist. Prior elicitation is known to be challenging. We present the very first mathematical results on the global robustness of the ARA solution. We use the distorted band class of priors and establish the conditions under which an ordering on the ARA solution can be established when modelling the first‐price sealed‐bid auctions using the nonstrategic play and level‐ thinking solution concepts. We illustrate these results using numerical examples and discuss further areas of research.

Interpretable Machine Learning Models for Predicting Critical Outcomes in Patients with Suspected Urinary Tract Infection with Positive Urine Culture.

(1) Background: Urinary tract infection (UTI) is a leading cause of emergency department visits and hospital admissions. Despite many studies identifying UTI-related risk factors for bacteremia or sepsis, a significant gap remains in developing predictive models for in-hospital mortality or the necessity for emergent intensive care unit admission in the emergency department. This study aimed to construct interpretable machine learning models capable of identifying patients at high risk for critical outcomes. (2) Methods: This was a retrospective study of adult patients with urinary tract infection (UTI), extracted from the Medical Information Mart for Intensive Care IV Emergency Department (MIMIC-IV-ED) database. The critical outcome is defined as either in-hospital mortality or transfer to an intensive care unit within 12 h. ED visits were randomly partitioned into a 70%/30% split for training and validation. The extreme gradient boosting (XGBoost), random forest (RF), and support vector machine (SVM) algorithms were constructed using variables selected from the stepwise logistic regression model. The XGBoost model was then compared to the traditional model and clinical decision rules (CDRs) on the validation data using the area under the curve (AUC). (3) Results: There were 3622 visits among 3235 unique patients diagnosed with UTI. Of the 2535 patients in the training group, 836 (33%) experienced critical outcomes, and of the 1087 patients in the validation group, 358 (32.9%) did. The AUCs for different machine learning models were as follows: XGBoost, 0.833; RF, 0.814; and SVM, 0.799. The XGBoost model performed better than others. (4) Conclusions: Machine learning models outperformed existing traditional CDRs for predicting critical outcomes of ED patients with UTI. Future research should prospectively evaluate the effectiveness of this approach and integrate it into clinical practice.

Enhancing Medication Safety with ML-Enhanced Decision Support Systems: A Comparative Analysis of Prescription Error Detection

Background: Medication prescription errors are a global issue, leading to significant morbidity and mortality. Traditional rule-based Medical Decision Support Systems (MDSS) are often ineffective, generating numerous false alerts and failing to detect all potential errors. This study assesses a new anomaly detection system integrated with Electronic Health Records (EHR) to improve the accuracy and utility of medication error warnings. Methods: Anomalous prescription detection was implemented alongside an existing MDSS in a real-world inpatient setting over 18 months. The new system utilized Machine Learning (ML) combined with a rule-based MDSS to analyze historical EHR data. It aimed to identify and flag high-risk prescriptions through real-time anomaly detection. The performance of this hybrid system was compared against traditional MDSS and multicriteria query (MQ) methods. A clinical pharmacist reviewed 415 patients (3401 prescriptions) to validate the effectiveness of the system, assessing notifications for accuracy, clinical relevance, and practicality. Results: The ML-enhanced MDSS demonstrated superior performance compared to traditional systems. It achieved a 76% interception rate for prescriptions needing pharmacist review and a precision rate of 75%. The hybrid system outperformed traditional MDSS and MQ methods, with areas under the ROC and PRC curves of 0.84 and 0.79, respectively, compared to 0.66 and 0.57 for MDSS and 0.7 and 0.58 for MQ approaches. Conclusion: Integrating ML with rule-based MDSS significantly improves the detection of high-risk medication prescriptions, reducing false alerts and enhancing accuracy. This hybrid approach offers a more effective tool for identifying potential medication errors and improving patient safety in inpatient settings.

Quantum state synthesis: relation with decision complexity classes and impossibility of error reduction

This work investigates the relationships between quantum state synthesis complexity classes (a recent concept in computational complexity that focuses on the complexity of preparing quantum states) and traditional decision complexity classes. We especially investigate the role of the \emph{synthesis error parameter}, which characterizes the quality of the synthesis in quantum state synthesis complexity classes.We first show that in the high synthesis error regime, collapse of synthesis classes implies collapse of the equivalent decision classes. For more reasonable synthesis error, we then show a similar relationships for $\BQP$ and $\QCMA$. Finally, we show that for quantum state synthesis classes it is in general impossible to improve the quality of the synthesis: unlike the completeness and soundness parameters (which can be improved via repetition), the synthesis error cannot be reduced, even with arbitrary computational power.

On the role of the UMLS in supporting diagnosis generation proposed by Large Language Models

Objective:Traditional knowledge-based and machine learning diagnostic decision support systems have benefited from integrating the medical domain knowledge encoded in the Unified Medical Language System (UMLS). The emergence of Large Language Models (LLMs) to supplant traditional systems poses questions of the quality and extent of the medical knowledge in the models’ internal knowledge representations and the need for external knowledge sources. The objective of this study is three-fold: to probe the diagnosis-related medical knowledge of popular LLMs, to examine the benefit of providing the UMLS knowledge to LLMs (grounding the diagnosis predictions), and to evaluate the correlations between human judgments and the UMLS-based metrics for generations by LLMs. Methods:We evaluated diagnoses generated by LLMs from consumer health questions and daily care notes in the electronic health records using the ConsumerQA and Problem Summarization datasets. Probing LLMs for the UMLS knowledge was performed by prompting the LLM to complete the diagnosis-related UMLS knowledge paths. Grounding the predictions was examined in an approach that integrated the UMLS graph paths and clinical notes in prompting the LLMs. The results were compared to prompting without the UMLS paths. The final experiments examined the alignment of different evaluation metrics, UMLS-based and non-UMLS, with human expert evaluation. Results:In probing the UMLS knowledge, GPT-3.5 significantly outperformed Llama2 and a simple baseline yielding an F1 score of 10.9% in completing one-hop UMLS paths for a given concept. Grounding diagnosis predictions with the UMLS paths improved the results for both models on both tasks, with the highest improvement (4%) in SapBERT score. There was a weak correlation between the widely used evaluation metrics (ROUGE and SapBERT) and human judgments. Conclusion:We found that while popular LLMs contain some medical knowledge in their internal representations, augmentation with the UMLS knowledge provides performance gains around diagnosis generation. The UMLS needs to be tailored for the task to improve the LLMs predictions. Finding evaluation metrics that are aligned with human judgments better than the traditional ROUGE and BERT-based scores remains an open research question.

Intuitionistic fuzzy three-way decision method based on data envelopment analysis

As a powerful mathematical tool for tackling uncertain decision problems, three-way decision has garnered substantial attention since its inception. However, real-world decision problems are inherently complex, and decision-makers often exhibit characteristics of incomplete rationality. Traditional three-way decision models, which rely on functions or relationships, face challenges when confronted with multi-output problems. In response to this challenge, this paper introduces an intuitionistic fuzzy three-way decision model grounded in data envelopment analysis (DEA). Initially, we propose an input–output correlation degree that integrates hesitancy information and serves as a procedural indicator for benefit scores. Subsequently, the traditional DEA is extended to accommodate the intuitionistic fuzzy environment and utilized to construct a comprehensive loss function. Furthermore, a novel intuitionistic fuzzy three-way decision model is developed, incorporating three dimensions: optimism, neutrality, and pessimism, and corresponding decision rules and algorithms are provided. Finally, the effectiveness of the proposed model is rigorously validated through a series of experiments and comparative analyses. The model offers a pioneering approach to address uncertain multi-input–output decision problems, effectively integrating decision-maker’s risk preferences within an intuitionistic fuzzy environment.

Predicting borrower default risk using support vector machine AI models

Precise prediction on the likelihood of borrower default is pivotal for credit institution and decision makers to mitigate the loss of capital and rationalize decision process. This article reviewed the Effects of Support Vector Machine (SVM) models with radial basis function (RBF) kernel in predicting the mortality rate of borrowers. By integrating with a dataset of approximately 100,000 borrowers profile harvested through historical loan performance, we set up the SVM model, and employed a feature-distribution method utilizing grid search and cross-validation technique to fine-tune the predictive model of SVM. Results indicated that the model accomplished an excellent performance with accuracy of 92%, precision of 89%, the recall and F1-score of 85% and 87%, respectively, alongside an Area Under the Curve -Receiver Operating Characteristic (AUC-ROC value of 0.95). It was evinced that the model performed substantially better than traditional logistic regression and decision trees in discriminating defaulter from non-defaulter. The outcome informs that an in-depth process should be implemented on data preprocessing, featureselection, and parameter tuning to achieve a robust predictive model for credit risk assessment. The article concludes the potentials of AI based on the resort to artificial technology in revolutionising the risk assessment scheme within the financial industry.

Research and Practice on Instructional Methods for Piano Improvization Based on Computer Technology

In the backdrop of evolving technological landscapes, this paper delves into the utilization of computer technology, specifically Artificial Neural Networks (ANN), in enhancing piano improvisation instruction. Recognizing the growing demand for innovative teaching methods, our study aims to evaluate the practical effectiveness of ANN-based teaching evaluation in real-world piano improvisation settings. Through rigorous testing, we found that ANN demonstrates remarkable precision and consistency in assessing piano improvisation skills. In comparison to the traditional decision tree algorithm, ANN excels in managing complex nonlinear relationships, providing more accurate and reliable scoring results. This integration of technology not only elevates students’ performance but also fosters their musical creativity and perception. Our findings suggest potential improvements in refining instructional methodologies and expanding the use of computer technology in piano teaching. This underscores the importance of personalized teaching, blended learning models, and technical proficiency training for educators. Overall, our research methodologies and findings significantly contribute to advancing the modernization and technological progress of music education, equipping piano instructors with cutting-edge teaching tools and strategies.

Three-way open intent classification with nearest centroid-based representation

Open intent classification aims to identify the unknown (open) intents and simultaneously classify the known ones under the open-world assumption. However, the existing studies still face two challenges, i.e., coarse-grained representation learning and uncertain decision boundary. On the one hand, previous methods viewed each class as a unified entity during representation learning, which fails to capture the fine-grained intra-class data structure. On the other hand, traditional two-way decision for open classification struggle to classify the uncertain samples distributed at the edge of the decision boundary, increasing the risk of misclassification. To overcome these limitations, we present a three-way open intent classification method that utilizes the nearest centroid to learn representations, named 3WNC-Open. Specifically, we learn a structured representation by extracting fine-grained information from the sub-classes within each class. Then, we design a three-way open classification strategy to handle uncertainty, initially identifying uncertain samples and then processing them using an effective alternative approach. Experiments on challenging datasets demonstrate that 3WNC-Open outperforms strong baselines.

Multi-attribute perceptual fuzzy information decision-making technology in investment risk assessment of green finance Projects

Abstract In the investment risk assessment of green finance (GF) projects, the application of multi-attribute perceptual fuzzy information decision technology is taken as the main research object. With the promotion of the concept of environmental protection and the development of green economy, the investment risk assessment of GF projects has become more and more important. However, this requires dealing with a large amount of fuzzy information and multi-attribute decision problems, which is a big challenge for traditional decision techniques. Based on this background, a new decision model, intuitionistic fuzzy preference theory-based tomada de decisão interativa multicritério (IF-PT-TODIM), is adopted, which can better deal with fuzzy information and multi-attribute decision problems by taking two different choices as reference. By knowing the weight distribution of experts, the model can better assess the influence of various factors on the decision. In the research results, the calculated results of expert weights are 0.2796, 0.2221, 0.1914, 0.1328, and 0.1745, respectively, showing that each expert has different degrees of influence on decision-making. In addition, the application of IF-PT-TODIM model can effectively reduce the investment risk. Compared with national bank of Kuwait, systematic review, evolutionary algorithm, the improved method can reduce the risk of venture capital by 28.14, 15.47, and 11.05%, respectively. This result further confirms the advantage of the IF-PT-TODIM model in dealing with fuzzy information and multi-attribute decision problems. This study has practical implications for understanding and improving the investment risk assessment of GF projects. It not only provides a new decision model for risk assessment, but also provides an effective method to deal with fuzzy information and multi-attribute decision problems. This provides new ideas and methods for the risk management of GF projects and also provides a new perspective and reference for research in related fields.

A novel multi-attribute three-way decision model with three-parameter interval grey number decision-theoretic rough sets

PurposeTo overcome the limitations of traditional multi-attribute decision making (MADM) methods, which only provide deterministic rankings of decision objects, this paper proposes a novel multi-attribute 3WD model. This model presents three-parameter interval grey number decision-theoretic rough sets (TPIGNDTRSs), aiming to offer a reasoned interpretation of loss functions in grey environments and ensure objective assessment of conditional probabilities.Design/methodology/approachFirstly, the traditional equivalence relation is replaced with the probabilistic dominance relation (PDR), categorizing decision objects into two state sets in DTRS for more objective conditional probabilities. Secondly, as the three-parameter interval grey number (TPIGN) introduces the most probable value on the basis of the traditional two-parameter interval grey number, it provides a more comprehensive method for describing grey information. Consequently, integrating TPIGN into DTRS refines the interpretations of loss functions in grey environments. Finally, by utilizing two main sorting techniques, relative kernel and degree of accuracy ranking and possibility ranking, two types of 3WD rules with TPIGNDTRSs, are constructed.FindingsThis study has successfully developed and validated a new multi-attribute 3WD model. The model was tested in two distinct domains: evaluating innovation efficiency in high-tech enterprises and recommending movies in a practical case. The findings reveal that the model can effectively integrate relevant information of high-tech enterprises, provide the government with enterprise-level assessments, and gather consumer preferences to recommend the most suitable movies.Research limitations/implicationsThis study treats the loss function as grey information in the 3WD model but overlooks the grey nature of evaluation values, limiting its applicability. Additionally, the model’s reliance on subjective expert judgments and historical data to establish the loss function may affect its objectivity. The implications of this research are that the novel model overcomes traditional MADM limitations, enhancing decision-making quality and efficiency in complex and grey scenarios. The model’s successful application in evaluating high-tech enterprises and recommending movies illustrates its dual value in both theory and practice.Originality/valueInitially, the model proposed in this study is of significant importance for the development of the 3WD field, as it successfully addresses the challenges of uncertain loss functions and unknown conditional probabilities in grey information environments. Moreover, by integrating the 3WD model with MADM problems, it has broken through the bottlenecks of traditional MADM methods, offering new perspectives and strategies for solving MADM issues. Therefore, this research not only advances theoretical research but also provides powerful tools for practical applications.

An Incentive Mechanism-Based Minimum Adjustment Consensus Model Under Dynamic Trust Relationship.

In traditional group decision making, the inconsistent experts are usually forced to make compromises toward the group opinion to increase the group consensus level. However, the strategy of reaching group consensus via an incentive mechanism encouraging adjustment of preferences is more effective than forcing, which is the aim of this article. Specifically, this article establishes a novel incentive mechanism to support group consensus under dynamic trust relationship. First, the supremum and infimum incentives-based rule driven by trust relationship is defined. Based on the assumption that if incentive conditions are met, then experts will be willing to adjust their preferences, the incentive behavior-driven minimum adjustment consensus model is developed to generate optimal incentive-based recommendation preferences. Thus, the proposed incentive mechanism can effectively reduce the preference adjustment cost and promote group consensus reaching. Third, the updated trust relationships between experts are shown to be strengthen by the proposed incentive-driven preference revision. Consequently, the optimization model based on trust interaction relationship is constructed to obtain the final group preference matrix. Finally, a supplier selection case of high-end medical equipment is provided to illustrate the proposed method and show the rationality and advantages of the proposed methodology with both a sensitivity analysis and a comparison analysis.

Stress Recognition in Code-Mixed Social Media Texts using Machine Learning

Stress, being a complex emotional state caused by a variety of multiple sources, has the potential for serious effects if left untreated. The primary goal of this research is to select and consider AI models that effectively recognize stress within the complicated domain of social media posts. The significance of this study is not only the categorization of stress but also the interpretation of the sophisticated methods that serve as the basis for these emotional responses. Among the traditional machine learning models, Random Forest, K-Nearest Neighbor, Logistic Regression, Decision Tree, and Support Vector Machine are used. The deep learning model’s LSTM, BiLSTM, and transformer-based models m-BERT, AL-BERT, XLM-RoBERTa, IndicBERT, and Distil-BERT were used. Of those models, LSTM proved to be the best-performing model, with an F1-score of 0.75.