Bangla Text Research Articles

Accurate Prediction of Bangla Text Article Categorization by Utilizing Novel Bangla Stemmer

Text categorization involves assigning predefined category labels to an unlabeled document. With the exponential growth in the accessibility and availability of digital documents over the past decade, this field significantly attracted the scientific community that immensely demands rapid and accurate categorization of these documents. Relying on experts for manual classification is time-consuming and resource-intensive. Consequently, labeling unlabeled digital documents faster more accurately, and more efficiently is inescapable. One promising approach to addressing this demand is the use of machine learning algorithms. Training these algorithms on a large dataset of labeled texts lets them learn patterns and predicted unlabeled documents. This strategy might greatly expedite the categorizing process while retaining a substantial level of accuracy through leveraging artificial intelligence. These algorithms have also enhanced natural language processing techniques, making them more accurate at classifying unlabeled digital documents. In this study, we propose a novel machine-learning computational framework to address this challenge. Our framework incorporates a novel Bangla stemmer, which reduces words to their stems. We then employed TF-IDF for document vectorization, a statistical measure assessing word relevance for categorization purposes. Experimental results reveal that our framework significantly enhances prediction performance, achieving an impressive 95.3% prediction accuracy.

An Upgraded Approach for Identifying Partially Reduplicated Forms in Bengali Text

An Upgraded Approach for Identifying Partially Reduplicated Forms in Bengali Text

Hate speech detection in the Bengali language: a comprehensive survey

The detection of hate speech (HS) in online platforms has become extremely important for maintaining a safe and inclusive environment. While significant progress has been made in English-language HS detection, methods for detecting HS in other languages, such as Bengali, have not been explored much like English. In this survey, we outlined the key challenges specific to HS detection in Bengali, including the scarcity of labeled datasets, linguistic nuances, and contextual variations. We also examined different approaches and methodologies employed by researchers to address these challenges, including classical machine learning techniques, ensemble approaches, and more recent deep learning advancements. Furthermore, we explored the performance metrics used for evaluation, including the accuracy, precision, recall, receiver operating characteristic (ROC) curve, area under the ROC curve (AUC), sensitivity, specificity, and F1 score, providing insights into the effectiveness of the proposed models. Additionally, we identified the limitations and future directions of research in Bengali HS detection, highlighting the need for larger annotated datasets, cross-lingual transfer learning techniques, and the incorporation of contextual information to improve the detection accuracy. This survey provides a comprehensive overview of the current state-of-the-art HS detection methods used in Bengali text and serves as a valuable resource for researchers and practitioners interested in understanding the advancements, challenges, and opportunities in addressing HS in the Bengali language, ultimately assisting in the creation of reliable and effective online platform detection systems.

Depression Intensity Identification using Transformer Ensemble Technique for the Resource-constrained Bengali Language

Depression is an ordinary mental health-related disorder that hampers people’s daily activities, and sometimes, it destroys an individual’s life. It is one of the major social issues at present. Since depressed people use various social networking sites for sharing their thoughts and feelings, many scholars have tried to identify depression texts in highly resourced languages like English; however, only a small quantity of papers are detected in the resource-constrained Bengali language. This paper focuses on developing a depression intensity detection system from Bengali text data. In this regard, this study experiments on a 2,596 sample-sized dataset with four levels of depression by utilizing five state-of-the-art transformer models, including multilingual Bidirectional Encoder Representations from Transformers, DistilmBERT, XLM-RoBERTa, Bangla-BERT-Base, and BanglaBERT, and suggests a new ensemble method called MaxOfAvgProb. This method goes beyond the performance of the previous work on the same dataset, scoring 63.47% F1-score and 62.90% accuracy. To increase the reliability of the proposed method, we utilize this approach on another available dataset with 4,897 entries. In this case, our recommended method also surpasses the performance of the existing work on the same dataset, with accuracy at 86.45% and F1-score at 86.35%. Identifying the intensity of depression, depressed people may get proper counseling or treatment from their respected guardians or psychologists according to the victims’ level of depression.

Detecting cyberbullying text using the approaches with machine learning models for the low-resource Bengali language

The rising usage of social media sites and the advances in communication technologies have led to a considerable increase in cyberbullying events. Here, people are intimidated, harassed, and humiliated via digital messaging. To identify cyberbullying texts, several research have been undertaken in English and other languages with abundant resources, but relatively few studies have been conducted in low-resource languages like Bengali. This research focuses on Bengali text to find cyberbullying material by experimenting with pre-processing, feature selection, and three types of machine learning (ML) models: classical ML, deep learning (DL), and transformer learning. In classical ML, four models, support vector machine (SVM), multinomial Naive Bayes (MNB), random forest (RF), and logistic regression (LR) are used. In DL, three models, long short term memory (LSTM), Bidirectional LSTM, and convolutional neural network with bidirectional LSTM (CNN-BiLSTM) are employed. As the transformerbased pre-trained model, bidirectional encoder representations from transformers (BERT) is utilized. Using our proposed pre-processing tasks, the MNB-based approach achieves the best accuracy of 78.816% among the other classical ML models, the LSTM-based approach gains the highest result of 77.804% accuracy among the DL models, and the BERT-based approach outperforms both with 80.165% accuracy.

Dialectics of impairment: historical anxieties in late-colonial Bengali fictional narratives on disability

ABSTRACT This article examines a body of early twentieth-century Bengali fiction foregrounding persons marked as disabled (including people experiencing physical disability, learning disability and chronic illness). A number of Bengali short stories and novels offer embodied narratives, which consider the human body as a productive site of contest between the colonial social order, the attempt to impose Western modernity and indigenous consciousness. An emergent sense of cultural agency can be found to be claimed by people, whose physical and mental states deviate from codes of ‘normalcy’. These works unearth social discrimination based on the binary of ‘fit’ and ‘unfit’ under the converging rules of native feudalism and foreign colonialism. The treatment of corporeality in Bengali texts of the period from the 1930s to the 1950s cannot be fully grasped by applying the disability theories of the Global North. Rather these texts conflate multiple forms of marginalization of subject bodies to explore several socio-historical cross-sections and address the question of identity formation. This article rereads selected fiction on disability by Manik Bandyopadhyay (1908–1956) and Tarashankar Bandyopadhyay (1898–1971).

Analyzing Sentiments in eLearning: A Comparative Study of Bangla and Romanized Bangla Text Using Transformers

Analyzing Sentiments in eLearning: A Comparative Study of Bangla and Romanized Bangla Text Using Transformers

Classifying Bengali Newspaper Headlines with Advanced Deep Learning Models: LSTM, Bi-LSTM, and Bi-GRU Approaches

Reading newspapers is beneficial for people of all ages and the global community. The enjoyment of gathering diverse data from various sources adds to the overall experience. To enhance specificity in Bengali news headlines, recognizing the news genre becomes crucial. Recognizing the genre of the news, it is a very challenging task in Bengali Text Classification with the help of AI. A very few research works is done on Bengali News headline classification and we have done a model to provide a solution to the addressed issue. Due to the continuous change of the structure of the news headlines, we have employed a neural network adoption connection to our methodology experiment on a mixture of primary and secondary dataset. Achieving significant results, we implemented a Bengali dataset in Multi Classification using Long-Short Term Memory (LSTM), Bi- Long-Short Term Memory (Bi-LSTM), and Bi-Gated Recurrent Unit (Bi-GRU). The dataset is established by aggregating news headlines from various Bengali news portals and websites, showcasing robust categorization performance in the end product. Six categories were employed for the classification of Bengali newspaper headlines. The Bi-LSTM Model emerged with the highest training accuracy at 97.96% and the lowest validation accuracy at 77.91%. Furthermore, it demonstrated enhanced sensitivity and specificity.

A transformer-based generative adversarial learning to detect sarcasm from Bengali text with correct classification of confusing text

Sarcasm detection research in Bengali is still limited due to a lack of relevant resources. In this context, getting high-quality annotated data is costly and time-consuming. Therefore, in this paper, we present a transformer-based generative adversarial learning for sarcasm detection from Bengali text based on available limited labeled data. Here, we use the Bengali sarcasm dataset ‘Ben-Sarc’. Besides, we construct another dataset containing Bengali sarcastic and non-sarcastic comments from YouTube and newspapers to observe the model's performance on the new dataset. On top of that, we utilize another Bengali sarcasm dataset ‘BanglaSarc’ to further prove our models' robustness. Among all models, the Bangla BERT-based Generative Adversarial Model has achieved the highest accuracy with 77.1% for the ‘Ben-Sarc’ dataset. Besides, this model has achieved the highest accuracy of 68.2% for the dataset constructed from YouTube and newspaper, and 97.2% for the ‘BanglaSarc’ dataset.

A crowdsource based framework for Bengali scene text data collection and detection

Scene texts are the type of texts that we see in our surroundings when we are outside. They have custom fonts, sizes, shapes and colors that are often different from the fonts or styles typically found in documents. Scene text recognition has grown in popularity due to its significance in the development of smarter automated systems. Despite the fact that numerous types of research on scene text detection and recognition have been conducted in different languages, similar work on the Bengali language is limited by the lack of large-scale usable datasets. In this paper, we propose a multipurpose system for Bengali Scene text that allows for easy dataset collection via crowdsourcing as well as annotation, classification and detection tasks to be performed on the same platform. It comes with an Android-based application that can be used to capture or load images from the device, select Bengali texts over the images and annotate them. The images and labels are stored in the cloud. A Python-based script is used to perform real-time data processing, analysis, and detection tasks. The proposed system has also been tested on a crowdsourced Bengali scene text dataset collected by this system. The classification model achieved an accuracy score of 97%, and the detection model achieved a Mean Average Precision score of 92 on the on these crowd contributed dataset.

Bangla text normalization for text-to-speech synthesizer using machine learning algorithms

Text normalization (TN) for text-to-speech (TTS) synthesizer is the transformation of non-standard words like times, ordinal numbers, equations, ranges, dates, etc. into standard words that have similarities with their pronunciations. An essential part of all TTS synthesizers is text normalization. Without text normalization, generated voice from the TTS synthesizer will be unintelligible. For the unsatisfactory performance of previous research, a text normalization method for the Bangla language is proposed in this paper. At first, we have produced a tokenized dataset with a semiotic class using regular expressions from a Bangla corpus. Then, each token has been trained using the XGBClassifier algorithm. After that, it identifies the semiotic class for each token in a new Bangla text corpus using the trained XGBClassifier model. Finally, it produces a normalized text for each token by calling the class function according to the predicted class. This text normalization method will help the Bangla TTS synthesizer in producing more intelligible voices. The token classification accuracy of this method is 99.997%.

Sentiment analysis in multilingual context: Comparative analysis of machine learning and hybrid deep learning models

This research paper investigates the efficacy of various machine learning models, including deep learning and hybrid models, for text classification in the English and Bangla languages. The study focuses on sentiment analysis of comments from a popular Bengali e-commerce site, "DARAZ," which comprises both Bangla and translated English reviews. The primary objective of this study is to conduct a comparative analysis of various models, evaluating their efficacy in the domain of sentiment analysis. The research methodology includes implementing seven machine learning models and deep learning models, such as Long Short-Term Memory (LSTM), Bidirectional LSTM (Bi-LSTM), Convolutional 1D (Conv1D), and a combined Conv1D-LSTM. Preprocessing techniques are applied to a modified text set to enhance model accuracy. The major conclusion of the study is that Support Vector Machine (SVM) models exhibit superior performance compared to other models, achieving an accuracy of 82.56% for English text sentiment analysis and 86.43% for Bangla text sentiment analysis using the porter stemming algorithm. Additionally, the Bi-LSTM Based Model demonstrates the best performance among the deep learning models, achieving an accuracy of 78.10% for English text and 83.72% for Bangla text using porter stemming. This study signifies significant progress in natural language processing research, particularly for Bangla, by enhancing improved text classification models and methodologies. The results of this research make a significant contribution to the field of sentiment analysis and offer valuable insights for future research and practical applications.

An improved extrinsic monolingual plagiarism detection approach of the Bengali text

Plagiarism is an act of literature fraud, which is presenting others’ work or ideas without giving credit to the original work. All published and unpublished written documents are under the cover of this definition. Plagiarism, which increased significantly over the last few years, is a concerning issue for students, academicians, and professionals. Due to this, there are several plagiarism detection tools or software available to detect plagiarism in different languages. Unfortunately, negligible work has been done and no plagiarism detection software available in the Bengali language where Bengali is one of the most spoken languages in the world. In this paper, we have proposed a plagiarism detection tool for the Bengali language that mainly focuses on the educational and newspaper domain. We have collected 82 textbooks from the National Curriculum of Textbooks (NCTB), Bangladesh, scrapped all articles from 12 reputed newspapers and compiled our corpus with more than 10 million sentences. The proposed method on Bengali text corpus shows an accuracy rate of 97.31%

A robust hybrid machine learning model for Bengali cyber bullying detection in social media

Social networking platforms give users countless opportunities to share information, collaborate, and communicate positively. The same platform can be extended to a fabricated and poisonous atmosphere that gives an impersonal, harmful platform for online misuse and assault. Cyberstalking is when someone uses an internet system to ridicule, torment, insult, criticize, slander, and discredit a victim while never seeing them. With the growth of social networks, Facebook has become the online arena for bullying. Since the effects could result in a widespread contagion, it is vital to have models and mechanisms in place for the automatic identification and removal of internet cyberbullying data. This paper presents a robust hybrid ML model for cyberbullying detection in the Bengali language on social media. The Bengalibullying proposal involves an effective text preprocessing to make the Bengali text data into a useful text format, feature extraction using the TfidfVectorizer (TFID) to get the beneficial information of text data and resampling by Instance Hardness Threshold (IHT) procedure to balance the dataset to avoid overfitting or underfitting problems. In our experiment, we used the publicly available Bangla text dataset (44,001 comments) and got the highest performance ever published works on it. The model achieved the most elevated accuracy rate of 98.57% and 98.82% in binary and multilabel classification to detect cyberbullying on social media in the Bengali language. Our best performance findings are more effective than any previous effort in identifying and categorizing bullying in the Bengali language. As a result, we might use our model to correctly classify Bengali bullying in online bullying detection systems, protecting people from being the targets of social bullying.

Strategies for enhancing the performance of news article classification in Bangla: Handling imbalance and interpretation

The rapid increase in obtainable online text data has made text categorization an important tool for data analysts to extract relevant information on the web. However, incorrect or incomplete classification of marginalized groups may result from using biased text data. In order to remedy the disparity in available data, this research suggests a system for classifying and analyzing Bangla news articles. The suggested approach first uses both Random Under-Sampling (RUS) and Synthetic Minority Oversampling Techniques to balance the massive unbalanced Bangla News dataset consisting of 4,37,948 instances (SMOTE). Secondly, the proposed system employs three machine learning models: Logistic Regression, Decision Tree, and Stochastic Gradient Descent along with three deep learning models: Artificial Neural Network (ANN), Convolutional Neural Network (CNN), and Bidirectional Encoder Representations from Transformers (BERT) for Bangla text categorization. The experimental results signify the superior performance of BERT to other classification models of the system as well as other existing methods in this domain. The proposed system achieves the maximum accuracy of 99.04% in balanced dataset and 72.23% in imbalanced dataset using BERT. K-fold cross validation with varied K values is used to determine the performance consistency of BERT. Finally, both LIME (Local Interpretable Model agnostic Explanations and SHAP (SHapley Additive exPlanations) techniques are applied for interpreting each prediction made by BERT.

Lexeme connexion measure of cohesive lexical ambiguity revealing factor: a robust approach for word sense disambiguation of Bengali text

Lexeme connexion measure of cohesive lexical ambiguity revealing factor: a robust approach for word sense disambiguation of Bengali text

A Voting classification approach for Sentiment Extraction from Bengali text

Sentiment extraction is one of the most challenging tasks in Natural Language Processing (NLP). It is essential for analysing consumer and user feedback on social media sites and in the commercial world. Finding sentiments or emotions in raw text data and identifying their polarity, or whether they are positive or negative, is the main objective of sentiment extraction. This area has been the focus of various research projects for English and other significant natural languages. In this article, we offer a voting classification method that uses a variety of machine learning classifiers to extract sentiment from Bengali language text. We explored Logistic Regression, Decision Tree Classifier, Random Forest Classifier, Support Vector Classifier, Multinomial Nave Base and Ridge Classifier, and lastly, we used a voting classification strategy to extract sentiments from social media comments.

A Comprehensive Roadmap on Bangla Text-based Sentiment Analysis

The effortless expansion of Internet access has eventually transformed the dissemination behavior toward E-Mode. Thus, the usage of online or, more specifically, “Digital” texts has expanded abruptly. “Bangla,” the seventh most spoken language globally, has no different nature. Communication in the Bangla language has also been exposed on the Internet, which describes the feelings of individuals in any specific context. These enormously generated data from diverse sources have drawn the interest of the researchers working in the Natural Language Processing domain. Despite its relatively complicated structure, a lesser amount of annotated data, as well as a limited number of frameworks and approaches, exist. This lacking of resources has kept several stones unturned in this diverse, emotion-rich, and widely spoken language. To bridge the lacking and absence of resources, this article aims to provide a generalized deduced working procedure in this domain. To do so, the existing research work in the domain of sentiment analysis using Bangla text has been collected, evaluated, and summarized. Also, in this article, the techniques used in pre-processing, feature extraction, and eventually used algorithms have been identified and discussed. Considering these facts, this research work sketches a tentative blueprint of sentiment analysis using Bangla text. Additionally, this article discusses existing regional language corpora such as Tamil, Urdu, and Hindi, as well as English and methodologies used to extract emotional essence from Bangla language comparing other languages. That will assist in determining the probable chosen path of exploring Bangla in a deeper aspect. Moreover, this work has deduced and presented a generalized framework that will direct aspiring researchers to decide the pathway of choosing data vis-à-vis methodologies based on their interests.

Englishization of the Bangla Print Advertisement: An Ideological Apparatus for the Capitalist Regime

The Bangla text of the print advertisement is continuously being changed due to the influence of English for diverse reasons. This sheer impact may be termed as the Englishization of print advertisement. This paper analyzes the feature and frequency of the Englishization of Bangla sentences in print advertisements. Ultimately, this study scrutinizes how the Englishization of Bangla Print Advertisement works as an ideological apparatus for the capitalist regime. Data were collected from 50 advertisement taglines. The researcher selected advertisements directly from the widely- circulated national dailies in Bangladesh. The data were analyzed from the perspectives of Raymond Williams’s essay “Advertising: The Magic System” and cultural studies scholar Stuart Hall’s Encoding and Decoding Model of Communication. The findings of this research included: the romanization of Bangla texts, code-switching and code- borrowing in the Bangla texts, merging of English words with Bangla suffixes, both Bangla and English numerals in the same Bangla sentence, evidence of English and loan word acronyms in the same Bangla sentence. This research confirmed that the Englishization of Bangla print advertisements has developed further with time and has become an inevitable trend. Moreover, the Englishization of Bangla print advertisements is used to transform commodities into “fetishes”, which protects the interests of capitalism.

CovTiNet: Covid text identification network using attention-based positional embedding feature fusion.

Covid text identification (CTI) is a crucial research concern in natural language processing (NLP). Social and electronic media are simultaneously adding a large volume of Covid-affiliated text on the World Wide Web due to the effortless access to the Internet, electronic gadgets and the Covid outbreak. Most of these texts are uninformative and contain misinformation, disinformation and malinformation that create an infodemic. Thus, Covid text identification is essential for controlling societal distrust and panic. Though very little Covid-related research (such as Covid disinformation, misinformation and fake news) has been reported in high-resource languages (e.g. English), CTI in low-resource languages (like Bengali) is in the preliminary stage to date. However, automatic CTI in Bengali text is challenging due to the deficit of benchmark corpora, complex linguistic constructs, immense verb inflexions and scarcity of NLP tools. On the other hand, the manual processing of Bengali Covid texts is arduous and costly due to their messy or unstructured forms. This research proposes a deep learning-based network (CovTiNet) to identify Covid text in Bengali. The CovTiNet incorporates an attention-based position embedding feature fusion for text-to-feature representation and attention-based CNN for Covid text identification. Experimental results show that the proposed CovTiNet achieved the highest accuracy of 96.61±.001% on the developed dataset (BCovC) compared to the other methods and baselines (i.e. BERT-M, IndicBERT, ELECTRA-Bengali, DistilBERT-M, BiLSTM, DCNN, CNN, LSTM, VDCNN and ACNN).