Sentiment analysis (SA) is a greater part of Natural Language Processing (NLP) in the research field. Previously a lot of work was done by SA in various languages. Most of the work was done in the English language. A little work was done in the Bengali language and it's increasing day by day. Nowadays, Bangla News comments are very demanding for research work in the Bangla language. The procedures of text categorization, classifying, and different techniques for extracting features in textual information were discussed in this paper. Some Bangla newspaper dataset is currently available in online platforms. This research study has analyzed Bangla news comments sentiment using a hybrid approach and a pre-trained deep learning classifier. The proposed hybrid model utilizes an optimizer function “Adam” along with a word embedding “Glove”. The dataset utilized in the proposed model is collected from online platform Kaggle, the largest data science forum on the world. This dataset contains 13802 data. Using five different classes to our dataset. For building a model, this research study has applied preprocessing techniques, which makes a significant contribution in cleaning our dataset. This leads to get a well formed dataset. The proposed hybrid model has been combined with two familiar deep learning methods, namely BiLSTM and CNN. By comparing these two methods, the proposed hybrid model has gained better accuracy than the FastText model. The accuracy of hybrid model is about 89.89%. 

Sentiment Classification in Bengali News Comments using a hybrid approach with Glove

Bengali News Headline Categorization Using Machine Learning aims to categorize Bengali online news headlines into six distinct categories using Natural Language Processing. Researchers in different application fields have recently paid great attention to the fantastic accomplishments of Machine Learning Models in Natural Language Processing. Several machine learning algorithms categorize Bengali news headlines, including Logistic Regression, Random Forest Classifier, Multinomial Naive Bayes, and RBF Support Vector Machine. Also, deep learning models like LSTM, Bi-LSTM, GRU, Bi-GRU, and CNN, and the Bangla-BERT and XLM-RoBERTa transformer learning models are presented in this research. This paper’s primary purpose is to provide a comparative observation of several machine learning models, deep learning models, and transformer learning methods in Bengali news headline classification. We used 1,36,811 text data of Bengali news headlines for evaluation, and our dataset had an accuracy of 86.50% with XLM-RoBERTa.

An Empirical Study on Bengali News Headline Categorization Leveraging Different Machine Learning Techniques

Bengali News Headline Categorization Using Machine Learning aims to categorize Bengali online news headlines into six distinct categories using Natural Language Processing. Researchers in different application fields have recently paid great attention to the fantastic accomplishments of Machine Learning Models in Natural Language Processing. Several machine learning algorithms categorize Bengali news headlines, including Logistic Regression, Random Forest Classifier, Multinomial Naive Bayes, and RBF Support Vector Machine. Also, deep learning models like LSTM, Bi-LSTM, GRU, Bi-GRU, and CNN, and the Bangla-BERT and XLM-RoBERTa transformer learning models are presented in this research. This paper’s primary purpose is to provide a comparative observation of several machine learning models, deep learning models, and transformer learning methods in Bengali news headline classification. We used 1,36,811 text data of Bengali news headlines for evaluation, and our dataset had an accuracy of 86.50% with XLM-RoBERTa. 

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.

A Comprehensive Roadmap on Bangla Text-based Sentiment Analysis

Online and offline newspaper articles have become an integral phenomenon to our society. News articles have a significant impact on our personal and social activities but picking a piece of an appropriate news article is a challenging task for users from the ocean of sources. Recommending the appropriate news category helps find desired articles for the readers but categorizing news article manually is laborious, sluggish and expensive. Moreover, it gets more difficult when considering a resource-insufficient language like Bengali which is the fourth most spoken language of the world. However, very few approaches have been proposed for categorizing Bangla news articles where few machine learning algorithms were applied with limited resources. In this paper, we accentuate multiple machine learning approaches including a neural network to categorize Bangla news articles for two different datasets. News articles have been collected from the popular Bengali newspaper Prothom Alo to build Dataset I and dataset II has been gathered from the famous machine learning competition platform Kaggle. We develop a modified stop-word set and apply it in the preprocessing stage which leads to significant improvement in the performance. Our result shows that the Multi-layer Neural network, Naive Bayes and support vector machine provide better performance. Accuracy of 94.99%, 94.60%, 95.50% has been achieved for SVM, Logistic regression and Multi-layer dense Neural network, respectively.

/pdf/multi-category-bangla-news-classification-using-machine-k13ak4vk4l.pdf

Ashraf Uddin

Papers

Multi-category Bangla News Classification using Machine Learning Classifiers and Multi-layer Dense Neural Network