Implementation of a Bi-LSTM Model for Automatic Text Classification of Mathematics, Science, and Indonesian Language Questions

LSTM-Based Classification of Indonesian Regional Song Lyrics by Language

This study successfully proposes a Long Short-Term Memory (LSTM)-based model for automatic classification of Indonesian regional song lyrics by language, demonstrating that LSTM effectively captures sequential linguistic patterns and contextual relationships within regional languages.

Attention-Based Ensemble Deep Learning Model for Arabic and English Fake News Classification

It is difficult to classify articles as fake news since one article may consist of true facts with only some statements being fake. Moreover, classification becomes complicated for the Arabic language owing to its morphology and several ways of spelling, as well as the lack of well-classified and marked data sets. This paper presents an Ensemble Deep Learning Model (EDLM) used for Arabic and English fake news classification. The EDLM consists of CNN, Bi-LSTM with attention, and Bi-GRU with attention networks. Each of them produces one probability of the article, which is then summed up to a final probability via a sigmoid classification layer. The presented model was tested using AraNews, the Arabic Fake News Dataset (AFND), and the English Fake-or-Real dataset. Accuracy, precision, recall, and F1-score were used for evaluation. The highest accuracies obtained were 0.9146, 0.8363, and 0.9881, while the F1-scores reached 0.9032, 0.8358, and 0.9881. Compared to the best-performing network under the same conditions, the EDLM improved accuracy by 0.48, 1.80, and 0.74 percentage points correspondingly. It can be seen that the combination of all three networks provides additional information that makes the final decision better. There are some constraints concerning static embedding, only text input, source-level labels in the AFND, and missing details about the original software environment.

CLASSIFICATION OF RUSSIAN-LANGUAGE SHORT TEXTS: COMPARISON OF TF-IDF+ML AND SIMPLE NEURAL NETWORK MODELS BASED ON UNIFIED ASSESSMENT PROTOCOLS

The paper considers the problem of automatic classification of Russian-language short texts using traditional statistical and neural network approaches. The aim of the study is to compare the effectiveness of TF-IDF models in combination with classical machine learning algorithms (SVM, logistic regression) and a simple neural network architecture when solving the same classification problem using unified assessment protocols. During the experiments, the influence of various methods of text preprocessing (cleaning, stemming, lemmatization) on the classification quality and the stability of models to noisy data is analyzed. The novelty of the work lies in a replicated comparison of traditional and neural network methods on Russian-language corpora, as well as in assessing the impact of morphological normalization on quality indicators. The results show that with a limited amount of training data, TF-IDF-based models provide quality comparable to simple neural network architectures, while neural network approaches demonstrate an advantage when increasing the size of the corpus. The results of the research can be used in the development of text analysis systems, content filtering and intelligent dialog interfaces for the Russian language.

Evaluation of Transformer and Gradient Boosting Models for Indonesian Mental Health Text Classification

This study compares the performance between traditional feature-based classification methods and transformer architectures in mapping stress, anxiety, and depression conditions in Indonesian-language mental health discourse. The task is formulated as a multi-class classification problem, where each consultation is assigned a single dominant mental health category. By implementing an integrated experimental framework on an online consultation dataset, we tested Gradient Boosting as the baseline model against two specific transformer models, namely IndoBERT and IndoRoBERTa. Experimental findings indicate that transformer-based models consistently outperform traditional approaches, with IndoRoBERTa achieving the highest accuracy of 82%. These results affirm the capability of contextual language representation in capturing complex semantic and linguistic nuances in mental health texts. Nevertheless, this study notes ongoing challenges in differentiating categories with strong semantic overlap, particularly between stress and anxiety symptoms.

Analisis Sentimen Ulasan Aplikasi Duolingo di Google Play Store Menggunakan Algoritma Bidirectional Long Short-Term Memory (Bi-LSTM)

Overall, the study confirms that Bi-LSTM is a suitable deep learning approach for sentiment classification of application reviews and offers meaningful insights that can support Duolingo developers in evaluating user opinions and enhancing application quality.

@DravidianLangTech 2026: A Comparative Study of TF-IDF SVM and XLM-RoBERTa for Political Multiclass Text Classification.