A transfer learning with data augmentation approach to emotion classification of Indonesian tweets

Implementation of the IndoBERT-LSTM Model for Indonesian Sentiment Analysis withan Explainable AI Approach Using SHAP

The integration of the IndoBERT-BiLSTM architecture with SHAP is demonstrated to deliver accurate and explainable Indonesian sentiment analysis, which effectively bridges the gap between deep learning performance and decision transparency without compromising classification accuracy.

A Transformer-Based Approach with Data Augmentation for Multilabel Emotional Context Detection

Emotion identification in texts is becoming increasingly difficult because of the wide variety of ways emotions are represented. This study uses a fine-tuned Robustly Optimized Bidirectional Encoder Representations from Transformers Approach (RoBERTa) to offer a Transformer-based model for identifying multilabel emotional context in textual data. To balance emotion categories and enhance the model's capacity for generalization, data augmentation is applied on two different datasets: Semantic Evaluation and Cross-lingual Emotion Dataset (SemEval and XED) English corpus. This stage is considered one of the most important steps in preprocessing as it greatly helps to improve the results. The RoBERTa model was then used to extract and comprehend the deep context of emotional expressions. The proposed model shows robust performance on both SemEval-2018 and XED datasets with F1-macro/F1-micro of 0.924/0.93, 0.707/0.748, and 0.729/0.77 on single, double and triple emotions respectively. Further, it gives consistent results on XED with F1-macro/F1-micro of 0.846/0.846 on single emotions, 0.819/0.833 for double emotions and 0.825/0.834 for triple emotions.

A Hybrid Approach to Sentiment Analysis using Recurrent and Convolutional Neural Networks

Enhancing Efficiency and Transparency in Transformer-Based Emotion Classification for Indonesian Tweets

The growing use of social media in Indonesia has led to an abundance of emotionally rich content, offering valuable insights into public sentiment while also creating challenges for computational analysis due to linguistic variability, informal expressions, and diverse writing styles. This study aims to evaluate and enhance emotion classification on Indonesian tweets through the lens of efficient and explainable AI. Four Transformer-based architectures, such as IndoBERTweet, IndoBERT-base, IndoBERT-large, and Multi-BERT, were compared to establish a baseline. Among these models, IndoBERT-base achieved the best baseline performance with an F1-macro score of 0.8386. To improve computational efficiency and reduce deployment cost, two compression techniques were explored, which is mixed-precision and unstructured pruning with varying sparsity ratios. Experimental results showed that the configuration combining FP16 mixed-precision and 50% pruning achieved the best trade-off, maintaining an F1-macro of 0.8536 while reducing model size by 50% and achieving a 5.3× inference speedup compared to the FP32 baseline. Finally, explainable AI techniques were applied to interpret model predictions and analyze misclassifications between the baseline and efficient models. Overall, the findings demonstrate that efficiency-oriented optimization can enhance performance without sacrificing the model interpretability and evaluation score, leading to a more transparent and deployable emotion analysis systems for Indonesian social media.

Stacking Approaches for Multi-Label Emotion Recognition in Persian Using Large and Small Transformer Models

A hybrid model, termed SE_LLM_ST, is introduced, which leverages recent advancements in large language models (LLMs) and transformer-based architectures to effectively capture both contextual and sequential information vital for Persian emotion recognition.

Sentiment Analysis of Student Perceptions of Generative AI using Data Augmentation and Machine Learning Models

The development of Generative AI has significantly changed how students access information, understand learning materials, and generate ideas in higher education. Although Generative AI supports independent learning, it also raises concerns regarding overdependence, declining critical thinking skills, and academic integrity. This study evaluates the performance of sentiment analysis models using a processing pipeline that incorporates lexical, semantic, and generative data augmentation. The main challenge addressed in this study is class imbalance, particularly the limited number of negative sentiment samples compared to positive and neutral classes. This study applies an experimental quantitative approach consisting of dataset preparation, text preprocessing, data augmentation, feature extraction using TF-IDF, model training, and evaluation using Stratified K-Fold Cross Validation. The machine learning models evaluated include Multinomial Naive Bayes, Logistic Regression, Random Forest, and Linear Support Vector Machine. The experimental results show that Linear SVM achieved the best performance, with an average accuracy of 79.07% and a weighted F1-score of 73.90%. Compared descriptively with the non-augmented baseline, Linear SVM showed an observed increase in accuracy from 65.00% to 79.07% and in weighted F1-score from 63.03% to 73.90%. Data augmentation also enabled partial recognition of minority-class sentiment, although a substantial proportion of negative and positive samples were still misclassified as neutral. These findings indicate that hybrid data augmentation can support the performance of classical machine learning models on small and imbalanced educational text datasets, particularly when combined with TF-IDF and Linear SVM. However, a post-hoc audit identified a discrepancy between the class distribution of the original dataset and that of the final processed dataset. Therefore, the observed model performance should be interpreted as the result of the overall processing pipeline rather than as the isolated effect of data augmentation.