Improve Text Classification Performance Research Articles

Enhanced text classification through an improved discrete laying chicken algorithm

AbstractThe exponential growth of digital text documents presents a significant challenge for text classification algorithms, as the vast number of words in each document can hinder their efficiency. Feature selection (FS) is a crucial technique that aims to eliminate irrelevant features and enhance classification accuracy. In this study, we propose an improved version of the discrete laying chicken algorithm (IDLCA) that utilizes noun‐based filtering to reduce the number of features and improve text classification performance. Although LCA is a newly proposed algorithm, it has not been systematically applied to discrete problems before. Our enhanced version of LCA employs different operators to improve both exploration and exploitation of this algorithm to find better solutions in discrete mode. To evaluate the effectiveness of the proposed method, we compared it with some conventional nature‐inspired feature selection methods using various learning models such as decision trees (DT), K‐nearest neighbor (KNN), Naive Bayes (NB), and support vector machine (SVM) on five benchmark datasets with three different evaluation metrics. The experimental results demonstrate the effectiveness of the proposed algorithm in comparison to the existing one. The code is available at https://github.com/m0javad/Improved-Discrete-Laying-Chicken-Algorithm.

Indonesian Hate Speech Detection Using IndoBERTweet and BiLSTM on Twitter

Hate speech is an act of speech to spread hate to other people. In this digital era where everyone connects with social media, hate speech is growing rapidly and uncontrollably. Many people do not realize they are giving hate speech when critics something on social media due to a lack of awareness of the difference between hate speech and free speech. The results make victims feel alienated from society, and the people who spread it would often face the law. Detection in the sentences to identify whether it contains hate speech is essential to counter people's ignorance. For detecting such sentences, a machine learning algorithm is widely used to help identify each sentence. In this paper, we used a subset from machine learning named deep learning with the latest IndoBERT model named IndoBERTweet and combined it with RNN layer named BiLSTM. The appearance of IndoBERTweet opened more chances to further improve text classification performance with the addition of BiLSTM layer. The model first made a token representative from the sentence, then calculated it to analyze and made the classification based on the calculation. For this model to be effective, we trained our model with the labeled public dataset retrieved from Twitter. These datasets are classified into hate speech and non-hate speech, and these labels are applied to the models. We evaluated our model and achieved an accuracy of 93.7%, an improvement for classifying hate speech sentences from previous research.

The Value of Numbers in Clinical Text Classification

Clinical text often includes numbers of various types and formats. However, most current text classification approaches do not take advantage of these numbers. This study aims to demonstrate that using numbers as features can significantly improve the performance of text classification models. This study also demonstrates the feasibility of extracting such features from clinical text. Unsupervised learning was used to identify patterns of number usage in clinical text. These patterns were analyzed manually and converted into pattern-matching rules. Information extraction was used to incorporate numbers as features into a document representation model. We evaluated text classification models trained on such representation. Our experiments were performed with two document representation models (vector space model and word embedding model) and two classification models (support vector machines and neural networks). The results showed that even a handful of numerical features can significantly improve text classification performance. We conclude that commonly used document representations do not represent numbers in a way that machine learning algorithms can effectively utilize them as features. Although we demonstrated that traditional information extraction can be effective in converting numbers into features, further community-wide research is required to systematically incorporate number representation into the word embedding process.

A Classification Method for English Texts Based on Hybrid Recurrent Neural Network and Graph Construction in Social Recommendation Systems

Text classification (TC) methods are widely used in the field of recommendation systems. Text data has the characteristics of short length, large capacity, and variable data distribution, resulting in sparsity and concept drift issues, which pose challenges to text classification methods. In view of this, a recursive neural network and graph construction method has been proposed for classifying English texts in social recommendation systems. First, the English text document serves as the original dataset. Then, the data is preprocessed through tokenization, removal of stop words, stemming, and min-max normalization. Meanwhile, the principal component analysis is used to extract text features from English texts. Finally, feature selection is performed using information gain technology to improve text classification performance. The simulation results show that compared with the comparison method, the proposed algorithm has ideal results in accuracy, precision, recall, F1-score, true positive rate, and false positive rate. Meanwhile, based on experimental data, it was found that the proposed method outperforms state-of-the-art methods in text analysis of English text works.

Application of Generative Adversarial Networks and Shapley Algorithm Based on Easy Data Augmentation for Imbalanced Text Data

Imbalanced data constitute an extensively studied problem in the field of machine learning classification because they result in poor training outcomes. Data augmentation is a method for increasing minority class diversity. In the field of text data augmentation, easy data augmentation (EDA) is used to generate additional data that would otherwise lack diversity and exhibit monotonic sentence patterns. Generative adversarial network (GAN) models can generate diverse sentence patterns by using the probability corresponding to each word in a language model. Therefore, hybrid EDA and GAN models can generate highly diverse and appropriate sentence patterns. This study proposes a hybrid framework that employs a generative adversarial network and Shapley algorithm based on easy data augmentation (HEGS) to improve classification performance. The experimental results reveal that the HEGS framework can generate highly diverse training sentences to form balanced text data and improve text classification performance for minority classes.

Improving automated Turkish text classification with learning‐based algorithms

AbstractText classification is the process of determining categories or tags of a document depending on its content. Although text classification is a well‐known process, it has many steps that require tuning to improve mathematical models. This article provides a novel methodology and expresses key points to improve text classification performance using learning‐based algorithms and techniques. First, to check the effectiveness of the proposed methodology, we selected two public Turkish news benchmarking datasets. Then, we performed extensive testing using both supervised machine learning algorithms and state‐of‐art pre‐trained language models. The experimental results show that our methodology outperforms previous news classification studies on these benchmarking datasets improving categorization results based on F1‐score. Therefore, we conclude that the presented methodology efficiently improves the classification results and selects the feasible classifier for a given dataset.

A comparative study of automated legal text classification using random forests and deep learning

Automated legal text classification is a prominent research topic in the legal field. It lays the foundation for building an intelligent legal system. Current literature focuses on international legal texts, such as Chinese cases, European cases, and Australian cases. Little attention is paid to text classification for U.S. legal texts. Deep learning has been applied to improving text classification performance. Its effectiveness needs further exploration in domains such as the legal field. This paper investigates legal text classification with a large collection of labeled U.S. case documents through comparing the effectiveness of different text classification techniques. We propose a machine learning algorithm using domain concepts as features and random forests as the classifier. Our experiment results on 30,000 full U.S. case documents in 50 categories demonstrated that our approach significantly outperforms a deep learning system built on multiple pre-trained word embeddings and deep neural networks. In addition, applying only the top 400 domain concepts as features for building the random forests could achieve the best performance. This study provides a reference to select machine learning techniques for building high-performance text classification systems in the legal domain or other fields.

Research on N-grams feature selection methods for text classification

Text classification requires previously extraction of features describing the text documents in the collection. Usually these features are based on the occurrence frequency of words, N-grams of words in documents, i.e. the vector space model for document representation is built. Feature selection allows to reduce redundancy in high-dimensional representation of text data, which can significantly improve text classification performance. In the present paper, research on feature selection methods is performed in terms of the accuracy and F-measure of text classification with different number of selected attributes (N-grams of words) for different classifiers and different datasets. The obtained results can be used to apply further pre-processing steps, which include modifying the vector space model in order to achieve its improvement in terms of the text classification.

Learning neural networks for text classification by exploiting label relations

Text classification has been a fundamental problem in the realm of Natural Language Processing (NLP), and a variety of approaches have been proposed with the development of deep learning. Despite recent progress, most existing approaches deal with the problem of multi-class text classification in a flat way, assuming that text labels are semantically independent. This assumption doesn’t always hold in realistic settings, since there usually exist hierarchical or within-layer dependencies in the latent label space, especially when we consider larger label sets. In this paper, we propose a label clustering algorithm to exploit the underlying structure of label relations, and express the stacked concept relationships in the form of a two-layer label space. Next, we present two different neural network structures to capture inter-layer and intra-layer label relations. The first model HSNN organizes a group of local classifiers in a hierarchical way according to the exploited label space, while the second model LSNN takes advantages of text representations in different granularity levels and the bidirectional inferences with recurrent connections to make predictions. Finally, we evaluate our methods on three benchmark datasets. The results empirically demonstrate that both models are capable of leveraging the exploited label relations to improve text classification performance.

A Methodology Combining Cosine Similarity with Classifier for Text Classification

ABSTRACTText Classification has received significant attention in recent years because of the proliferation of digital documents and is widely used in various applications such as filtering and recommendation. Consequently, many approaches, including those based on statistical theory, machine learning, and classifier performance improvement, have been proposed for improving text classification performance. Among these approaches, centroid-based classifier, multinomial naïve bayesian (MNB), support vector machines (SVM), convolutional neural network (CNN) are commonly used. In this paper, we introduce a cosine similarity-based methodology for improving performance. The methodology combines cosine similarity (between a test document and fixed categories) with conventional classifiers such as MNB, SVM, and CNN to improve the accuracy of the classifiers, and then we call the conventional classifiers with cosine similarity as enhanced classifiers. We applied the enhanced classifiers to famous datasets – 20NG, R8, R52, Cade12, and WebKB – and evaluated the performance of the enhanced classifiers in terms of the confusion matrix’s accuracy; we obtained outstanding results in that the enhanced classifiers show significant increases in accuracy. Moreover, through experiments, we identified which of two considered knowledge representation techniques (word count and term frequency-inverse document frequency (TFIDF)) is more suitable in terms of classifier performance.

Improving Text Classification Performance with Random Forests-Based Feature Selection

Feature selection (FS) is employed to make text classification (TC) more effective. Well-known FS metrics like information gain (IG) and odds ratio (OR) rank terms without considering term interactions. Building classifiers with FS algorithms considering term interactions can yield better performance. But their computational complexity is a concern. This has resulted in two-stage algorithms such as information gain-principal component analysis (IG–PCA). Random forests-based feature selection (RFFS), proposed by Breiman, has demonstrated outstanding performance while capturing gene–gene relations in bioinformatics, but its usefulness for TC is less explored. RFFS has fewer control parameters and is found to be resistant to overfitting and thus generalizes well to new data. It does not require use of a test dataset to report accuracy and does not use conventional cross-validation. This paper investigates the working of RFFS for TC and compares its performance against IG, OR and IG–PCA. We carry out experiments on four widely used text data sets using naive Bayes’ and support vector machines as classifiers. RFFS achieves macro-F1 values higher than other FS algorithms in 73 % of the experimental instances. We also analyze the performance of RFFS for TC in terms of its parameters and class skews of the data sets and yield interesting results.

Feature subset selection using naive Bayes for text classification

Feature subset selection is known to improve text classification performance of various classifiers. The model using the selected features is often regarded as if it had generated the data. By taking its uncertainty into account, the discrimination capabilities can be measured by a global selection index (GSI), which can be used in the prediction function. In this paper, we propose a latent selection augmented naive (LSAN) Bayes classifier. By introducing a latent feature selection indicator, the GSI can be factorized into each local selection index (LSI). Using conjugate priors, the LSI for feature evaluation can be explicitly calculated. Then the feature subset selection models can be pruned by thresholding the LSIs, and the LSAN classifier can be achieved by the product of a small percentage of single feature model averages. The numerical results on some real datasets show that the proposed method outperforms the contrast feature weighting methods, and is very competitive if compared with some other commonly used classifiers such as SVM.

An effective concept extraction method for improving text classification performance

This paper presents a new way to extract concept that can be used to improve text classification performance (precision and recall). The computational measure will be divided into two layers. The bottom layer called document layer is concerned with extracting the concepts of particular document and the upper layer called category layer is with finding the description and subject concepts of particular category. The relevant implementation algorithm that dramatically decreases the search space is discussed in detail. The experiment based on real-world data collected from Infor-Bank shows that the approach is superior to the traditional ones.