Emotion Classification in a Resource Constrained Language Using Transformer-based Approach

Abstract

Although research on emotion classification has significantly progressed in highresource languages, it is still infancy for resource-constrained languages like Bengali. However, unavailability of necessary language processing tools and deficiency of benchmark corpora makes the emotion classification task in Bengali more challenging and complicated. This work proposes a transformer-based technique to classify the Bengali text into one of the six basic emotions: anger, fear, disgust, sadness, joy, and surprise. A Bengali emotion corpus consists of 6243 texts is developed for the classification task. Experimentation carried out using various machine learning (LR, RF, MNB, SVM), deep neural networks (CNN, BiLSTM, CNN+BiLSTM) and transformer (Bangla-BERT, m-BERT, XLM-R) based approaches. Experimental outcomes indicate that XLM-R outdoes all other techniques by achieving the highest weighted f 1 -score of 69.73% on the test data. The dataset is publicly available at https://github.com/omar-sharif03/ NAACL-SRW-2021.

Multi-class Textual Emotion Categorization using Ensemble of Convolutional and Recurrent Neural Network

“…However, emotion classification from Bengali text is quite challenging due to the deficit of benchmark corpora, complex morphological structure, critical linguistic construct, and huge verb inflexions. Deep learning models have recently shown significant improvements to classify textual emotion [1,8]. Therefore, this work aims to apply deep learning methods to categorize Bengali texts into one of six basic emotion (e.g., anger, disgust, fear, joy, sadness, surprise) classes defined by Ekman [10].…”

RSM-NLP at BLP-2023 Task 2: Bangla Sentiment Analysis using Weighted and Majority Voted Fine-Tuned Transformers

“…In (Das and Bandyopadhyay, 2010), the authors proposed a computational technique of generating an equivalent SentiWord-Net (Bangla) from publicly available English sentiment lexicons and an English-Bangla bilingual dictionary with few easily adaptable noise reduction techniques. However, with the Introduction of BERTs many works focused on fine-tuning multilingual BERTs (Ashrafi et al, 2020;Das et al, 2021), but BanglaBERT (Sarker, 2020) being the first model pre-trained on Bangla text corpus.…”

Classification of Textual Sentiment Using Ensemble Technique

“…Bengali is considered the seventh most widely spoken language globally. Nevertheless, the research on Bengali text processing is still in their infancy, especially in textual sentiment classification due to the unavailability of necessary resources and language processing tools [9]. Various ML techniques have been utilized for textual sentiment classification in Bengali, such as Multi-nomial naïve bayes (MNB) [16], SVM [35], and RF [33].…”

“…Cohen's kappa [7] scores are used to estimate the interannotator agreement. To ensure the quality of annotation and measure the goodness of the data samples, kappa statistic is utilized [9]. It is calculated by Eq.…”