Bangla News Classification using Graph Convolutional Networks

Rahman, Md. Mahbubur; Khan, Md. Akib; Biswas, Al Amin

doi:10.1109/iccci50826.2021.9402567

Cited by 6 publications

(3 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Given the wide variety of approaches to categorization and presentation adopted by online Bangla news outlets [20], this research explores the difficulty of doing so on the basis of readers' preferences. The authors suggest an automated approach that employs machine learning models to address this issue, and they assess the efficacy of various models, including BiLSTM, Char-CNN, GRU-LSTM, LSTM, BERT, and Text-GCN, using a sample dataset.…”

Section: Related Workmentioning

confidence: 99%

Unifying Sentence Transformer Embedding and Softmax Voting Ensemble for Accurate News Category Prediction

2023

View full text Add to dashboard Cite

The study focuses on news category prediction and investigates the performance of sentence embedding of four transformer models (BERT, RoBERTa, MPNet, and T5) and their variants as feature vectors when combined with Softmax and Random Forest using two accessible news datasets from Kaggle. The data are stratified into train and test sets to ensure equal representation of each category. Word embeddings are generated using transformer models, with the last hidden layer selected as the embedding. Mean pooling calculates a single vector representation called sentence embedding, capturing the overall meaning of the news article. The performance of Softmax and Random Forest, as well as the soft voting of both, is evaluated using evaluation measures such as accuracy, F1 score, precision, and recall. The study also contributes by evaluating the performance of Softmax and Random Forest individually. The macro-average F1 score is calculated to compare the performance of different transformer embeddings in the same experimental settings. The experiments reveal that MPNet versions v1 and v3 achieve the highest F1 score of 97.7% when combined with Random Forest, while T5 Large embedding achieves the highest F1 score of 98.2% when used with Softmax regression. MPNet v1 performs exceptionally well when used in the voting classifier, obtaining an impressive F1 score of 98.6%. In conclusion, the experiments validate the superiority of certain transformer models, such as MPNet v1, MPNet v3, and DistilRoBERTa, when used to calculate sentence embeddings within the Random Forest framework. The results also highlight the promising performance of T5 Large and RoBERTa Large in voting of Softmax regression and Random Forest. The voting classifier, employing transformer embeddings and ensemble learning techniques, consistently outperforms other baselines and individual algorithms. These findings emphasize the effectiveness of the voting classifier with transformer embeddings in achieving accurate and reliable predictions for news category classification tasks.

show abstract

Section: Related Workmentioning

confidence: 99%

Unifying Sentence Transformer Embedding and Softmax Voting Ensemble for Accurate News Category Prediction

2023

View full text Add to dashboard Cite

show abstract

“…The respective F1-scores for the suggested system for 20-newsgroup, Reuters-21578, Watan-2004, and Khalaf-2018 were 95%, 93%, 94%, and 92%. M. Rahman, M. Khan et al (2021) [9], creating an automated system for classifying Bengali news articles and creating advanced solutions for a set of textual data. Despite limited data set, TextGCN outperformed BiLSTM, GRU-LSTM, LSTM, Char-CNN, and BERT in the online Bangla news ranking.…”

Section: Related Workmentioning

confidence: 99%

“…The experimental method using Bayesian classifier achieved an accuracy rate of 93%. M. Khan et al (2021) [11], use of online Urdu news data to train algorithms to automatically categorize the presented information. The results showed that the Bernoulli Naïve Bayes (Bernoulli NB) and Multinomial Naïve Bayes (Multinomial NB) algorithms beat the others in terms of all performance criteria.…”

Section: Related Workmentioning

confidence: 99%

News Classification by N-Gram and Machine Learning Algorithms

Farawn Ogaib,

Mahdi Hashim

2023

JEPS

View full text Add to dashboard Cite

News is information obtained from different sources such as television, internet, newspapers andmagazines. Online news is published in very large numbers, and because there are so many news, it willbe challenging for users to find the pertinent information that matches their preferences. In this paper, thenews is categorized so that a specific category can be obtained quickly and easily. The BBC's newsgroupwas used in its five categories: sports, politics, business, technology and entertainment. The classificationalgorithms Multinomial Naive Bayes (MNB) and decision tree (DT) were applied to the news data setafter extracting the features from it using n-gram method . Multinomial naïve Bayes algorithm has provensuperiority over decision tree with an accuracy 98.2%.

show abstract