Text Classification by CEFR Levels Using Machine Learning Methods and the BERT Language Model

This paper presents a study of the problem of automatic classification of short coherent texts (essays) in English according to the levels of the international CEFR scale. Determining the level of text in natural language is an important component of assessing students knowledge, including checking open tasks in e-learning systems. To solve this problem, vector text models were considered based on stylometric numerical features of the character, word, sentence structure levels. The classification of the obtained vectors was carried out by standard machine learning classifiers. The article presents the results of the three most successful ones: Support Vector Classifier, Stochastic Gradient Descent Classifier, LogisticRegression. Precision, recall and F-score served as quality measures. Two open text corpora, CEFR Levelled English Texts and BEA-2019, were chosen for the experiments. The best classification results for six CEFR levels and sublevels from A1 to C2 were shown by the Support Vector Classifier with F-score 67 % for the CEFR Levelled English Texts. This approach was compared with the application of the BERT language model (six different variants). The best model, bert-base-cased, provided the F-score value of 69 %. The analysis of classification errors showed that most of them are between neighboring levels, which is quite understandable from the point of view of the domain. In addition, the quality of classification strongly depended on the text corpus, that demonstrated a significant difference in F-scores during application of the same text models for different corpora. In general, the obtained results showed the effectiveness of automatic text level detection and the possibility of its practical application.

Machine learning methods, including Deep learnings are popular for data processing. Deep learning methods have shown great promise in applied in natural language processing (NLP) tasks. Text classification is a supervised machine learning task that involves labelled documents to train classifier. Previous works involving machine learning and deep learning methods for text classification have been tested with relatively small- sized data instances. In this paper, we compared the performance of the machine leaning and deep learning algorithms in text classification task. This paper also studied, explored and compared the scalability of these methods with respect to bigger data instances. We used support vector machines (SVM), Logistic regression, Random forest and Naive Bayes Machine leaning algorithms and convolutional neural network (CNN) deep learning method. The task involved a multi-class classification problem involving six (6) classes consisting of six thousand (6,000) data instances with an average of 20 sentences in each data instance. The CNN deep leaning algorithm outperformed all the machine learning algorithms, achieving an accuracy of over 85%. This is because the filter weights are leaning are updated in backward propagation in each epoch, hence, this result in better result compared to the traditional methods.

Text classification is one of the most popular tasks in natural language processing, especially in the context of sentiment classification. Insufficient training data poses a significant challenge in many text classification studies. This research focuses on optimizing classification performance using the Passive Aggressive (PA) algorithm, leveraging limited training data. It compares conventional text representation methods like TF-IDF with modern approaches employing word embeddings such as FastText and BERT. The primary dataset encompasses sentiment issues related to Kaesang Pangarep's appointment as the chairman of PSI, gathered through Twitter crawling, and classified into positive, negative, and neutral sentiment labels. Two versions of the training data, each containing only 300 balanced tweets for positive, negative, and neutral classes, were used. The data was split 80% for training and 20% for validation in the search for an optimal model. External data with different issues and pre-existing sentiment labels was used to augment the training data. Experimental results demonstrated that the BERT language model, used as input features for the Passive Aggressive method with hyperparameter tuning, outperformed TF-IDF features. Evaluation on the test data revealed that BERT features with Passive Aggressive achieved an F1-score of 0.52, surpassing the conventional TF-IDF representation with an F1-score of 0.42. The utilization of the BERT language model significantly contributed to improving text classification performance in the field of natural language processing, particularly for the Passive Aggressive method.

The relevance and importance of voting advice applications (VAAs) are demonstrated by their popularity among potential voters. On average, around 30% of voters take into account the recommendations of these applications during elections. The comparison between potential voters' and parties' positions is made on the basis of VAA policy statements on which users are asked to express opinions. VAA designers devote substantial time and effort to analyzing domestic and international politics to formulate policy statements and select those to be included in the application. This procedure involves manually reading and evaluating a large volume of publicly available data, primarily party manifestos. A problematic part of the work is the limited time frame. This study proposes a system to assist VAA designers in formulating, revising, and selecting policy statements. Using pre-trained language models and machine learning methods to process politics-related textual data, the system produces a set of suggestions corresponding to relevant VAA statements. Experiments were conducted using party manifestos and YouTube comments from Japan, combined with VAA policy statements from six Japanese and two European VAAs. The technical approaches used in the system are based on the BERT language model, which is known for its capability to capture the context of words in the documents. Although the output of the system does not completely eliminate the need for manual human assessment, it provides valuable suggestions for updating VAA policy statements on an objective, i.e., bias-free, basis.

Artificial intelligence has been applied in wildfire science and management since the 1990s, with early applications including neural networks and expert systems. Since then, the field has rapidly progressed congruently with the wide adoption of machine learning (ML) methods in the environmental sciences. Here, we present a scoping review of ML applications in wildfire science and management. Our overall objective is to improve awareness of ML methods among wildfire researchers and managers, as well as illustrate the diverse and challenging range of problems in wildfire science available to ML data scientists. To that end, we first present an overview of popular ML approaches used in wildfire science to date and then review the use of ML in wildfire science as broadly categorized into six problem domains, including (i) fuels characterization, fire detection, and mapping; (ii) fire weather and climate change; (iii) fire occurrence, susceptibility, and risk; (iv) fire behavior prediction; (v) fire effects; and (vi) fire management. Furthermore, we discuss the advantages and limitations of various ML approaches relating to data size, computational requirements, generalizability, and interpretability, as well as identify opportunities for future advances in the science and management of wildfires within a data science context. In total, to the end of 2019, we identified 300 relevant publications in which the most frequently used ML methods across problem domains included random forests, MaxEnt, artificial neural networks, decision trees, support vector machines, and genetic algorithms. As such, there exists opportunities to apply more current ML methods — including deep learning and agent-based learning — in the wildfire sciences, especially in instances involving very large multivariate datasets. We must recognize, however, that despite the ability of ML models to learn on their own, expertise in wildfire science is necessary to ensure realistic modelling of fire processes across multiple scales, while the complexity of some ML methods such as deep learning requires a dedicated and sophisticated knowledge of their application. Finally, we stress that the wildfire research and management communities play an active role in providing relevant, high-quality, and freely available wildfire data for use by practitioners of ML methods.

A dose deposition matrix (DDM) prediction method using several voxel features and a machine learning (ML) approach is proposed for plan optimization in radiation therapy. Head and lung cases with the inhomogeneous medium are used as training and testing data. The prediction model is a cascade forward backprop neural network where the input is the features of the voxel, including 1) voxel to body surface distance along the beamlet axis, 2) voxel to beamlet axis distance, 3) voxel density, 4) heterogeneity corrected voxel to body surface distance, 5) heterogeneity corrected voxel to beamlet axis, and (6) the dose of voxel obtained from the pencil beam (PB) algorithm. The output is the predicted voxel dose corresponding to a beamlet. The predicted DDM was used for plan optimization (ML method) and compared with the dose of MC-based plan optimization (MC method) and the dose of pencil beam-based plan optimization (PB method). The mean absolute error (MAE) value was calculated for full volume relative to the dose of the MC method to evaluate the overall dose performance of the final plan. For patient with head tumor, the ML method achieves MAE value 0.49 × 10-4 and PB has MAE 1.86 × 10-4. For patient with lung tumor, the ML method has MAE 1.42 × 10-4 and PB has MAE 3.72 × 10-4. The maximum percentage difference in PTV dose coverage (D98) between ML and MC methods is no more than 1.2% for patient with head tumor, while the difference is larger than 10% using the PB method. For patient with lung tumor, the maximum percentage difference in PTV dose coverage (D98) between ML and MC methods is no more than 2.1%, while the difference is larger than 16% using the PB method. In this work, a reliable DDM prediction method is established for plan optimization by applying several voxel features and the ML approach. The results show that the ML method based on voxel features can obtain plans comparable to the MC method and is better than the PB method in achieving accurate dose to the patient, which is helpful for rapid plan optimization and accurate dose calculation. Establishment of a new machine learning method based on the relationship between the voxel and beamlet features for dose deposition matrix prediction in radiation therapy.

Developing Theory Using Machine Learning Methods

How Magic a Bullet Is Machine Learning for Credit Analysis? An Exploration with FinTech Lending Data

Machine learning guided design of functional materials with targeted properties

Parameter importance assessment improves efficacy of machine learning methods for predicting snow avalanche sites in Leh-Manali Highway, India

Machine learning (ML) methods are attracting considerable attention among academics in the field of finance. However, it is commonly believed that ML has not transformed the asset management industry to the same extent as other sectors. This survey focuses on the ML methods and empirical results available in the literature that matter most for active portfolio management. ML has asset management applications for signal generation, portfolio construction, and trade execution, and promising findings have been reported. Reinforcement learning (RL), in particular, is expected to play a more significant role in the industry. Nevertheless, the performance of a sample of active exchange-traded funds (ETF) that use ML in their investments tends to be mixed. Overall, ML techniques show great promise for active portfolio management, but investors should be cautioned against their main potential pitfalls. 
\n
\n

Prediction of chronic kidney disease (CKD) has emerged as a useful technique for early detection of at-risk persons and the introduction of appropriate management strategies. Machine learning and data-driven methods have been used in predictive modeling to examine massive databases of patient demographics, medical histories, test findings, and genetic information. These cutting-edge methods allow for the profiling of high-risk patients and the tailoring of healthcare administration approaches. Patient outcomes, complication rates, and healthcare system efficiency may all benefit greatly from CKD screening and prediction. Responsible use of CKD prediction algorithms, however, requires resolving issues with data availability, integration, and ethics. The area of medicine has benefited greatly from the use of Machine Learning (ML) methods, which have played an increasingly central role in illness prediction. In this study, we use a strategy that makes use of ML methods to construct effective tools for predicting the development of CKD. Multiple ML models are trained, and their results are compared using a variety of criteria. We applied five ML methods such as logistic regression (LR), Decision tree (DT), random forest (RF), support vector machine (SVM), and k-nearest neighbor (KNN). The LR and KNN have the highest accuracy with 99%.

P125. Development of a novel ensemble machine learning algorithm for prediction of complications and readmission after anterior cervical spinal fusion

PurposeInjuries are common in sports and can have significant physical, psychological and financial consequences. Machine learning (ML) methods could be used to improve injury prediction and allow proper approaches to injury prevention. The aim of our study was therefore to perform a systematic review of ML methods in sport injury prediction and prevention.MethodsA search of the PubMed database was performed on March 24th 2020. Eligible articles included original studies investigating the role of ML for sport injury prediction and prevention. Two independent reviewers screened articles, assessed eligibility, risk of bias and extracted data. Methodological quality and risk of bias were determined by the Newcastle–Ottawa Scale. Study quality was evaluated using the GRADE working group methodology.ResultsEleven out of 249 studies met inclusion/exclusion criteria. Different ML methods were used (tree-based ensemble methods (n = 9), Support Vector Machines (n = 4), Artificial Neural Networks (n = 2)). The classification methods were facilitated by preprocessing steps (n = 5) and optimized using over- and undersampling methods (n = 6), hyperparameter tuning (n = 4), feature selection (n = 3) and dimensionality reduction (n = 1). Injury predictive performance ranged from poor (Accuracy = 52%, AUC = 0.52) to strong (AUC = 0.87, f1-score = 85%). ConclusionsCurrent ML methods can be used to identify athletes at high injury risk and be helpful to detect the most important injury risk factors. Methodological quality of the analyses was sufficient in general, but could be further improved. More effort should be put in the interpretation of the ML models.

How to Improve Text Summarization and Classification by Mutual Cooperation on an Integrated Framework