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

Mohammad Kamrul Hasan; Shoeb Akibul Islam; Md. Sabbir Ejaz; Md. Mahbubul Alam; Nahid Mahmud; Tanvir Ahmed Rafin

doi:10.9734/ajrcos/2023/v16i4398

Research Article Open access CC BY 4.0

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

Mohammad Kamrul Hasan, Shoeb Akibul Islam, Md. Sabbir Ejaz, Md. Mahbubul Alam, Nahid Mahmud, Tanvir Ahmed Rafin

Asian Journal of Research in Computer Science · pp. 372–388 · Published 16 Dec 2023

10.9734/ajrcos/2023/v16i4398

Abstract

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.

Bengali news news classification machine learning deep learning social newspaper news headlines

References (16)

1 Bidirectional recurrent neural networks [DOI]
2 A Hierarchical Bidirectional GRU Model With Attention for EEG-Based Emotion Classification [DOI]
3 A Comparative Study on Word Embeddings in Deep Learning for Text Classification [DOI]
4 Deeplearning Model Used in Text Classification [DOI]
5 News classification based on their headlines: A review [DOI]
6 Sentiment Analysis of Bangla Language Using Deep Learning Approaches [DOI]
7 n-BiLSTM: BiLSTM with n-gram Features for Text Classification [DOI]
8 Sentiment Analysis on Bangla Text Using Long Short-Term Memory (LSTM) Recurrent Neural Network [DOI]
9 Bangla News Classification Using GloVe Vectorization, LSTM, and CNN [DOI]
10 Text Classification Using Convolution Neural Networks with FastText Embedding [DOI]
11 Detecting Fake News Using Machine Learning Algorithms [DOI]
12 Context-Based News Headlines Analysis Using Machine Learning Approach [DOI]
13 News Classification using Neural Networks [DOI]
14 Bangla News Headline Categorization [DOI]
15 Bangla News Classification Employing Deep Learning [DOI]
16 Bengali Text Classification: A New multi-class Dataset and Performance Evaluation of Machine Learning and Deep Learning Models [DOI]

Cited by 25

A Novel GRU-Augmented Time-Frequency Estimator for IGBT Remaining Useful Life Prediction

Yuan-Kuang Li, Baohua Tan, Yingjie Zhang · IEEE Access · 2025

Bi-LSTM neural network for enhanced radiotherapy: Detection of tissue parameters

J. Tayebi, Ali Rezaie, Mohammadreza Rezaie · Nuclear Engineering and Technology

An Analytical Review of Preprocessing Techniques in Bengali An Analytical Review of Preprocessing Techniques in Bengali Natural Language Processing Natural Language Processing

Sovon Chakraborty, Ieee Protiva das Member, Shakib Mahmud Dipto

An Analytical Review of Preprocessing Techniques in Bengali Natural Language Processing

Sovon Chakraborty, Protiva Das, Shakib Mahmud Dipto · IEEE Access · 2025

Showing 14 of 25 known citations — external sources report more than can currently be individually listed.

Detecting Dental Caries through Captured Images Using the Machine Learning Technology Teachable Machine — shares topic coverage
Prediction of Radiotherapy Dose Distribution for Glioblastoma Using Convolutional Neural Network Model — shares topic coverage
A Systematic Literature Review of Machine Learning Methods in Healthcare — shares topic coverage
Diagnostic Accuracy of Artificial Intelligence for Breast Cancer Detection: A Systematic Review — shares topic coverage
Artificial Intelligence in the Analysis of the Fetal Genome in Utero: A Critical Review of Current Paradigms, Clinical Utility and Future Horizons — shares topic coverage

Access this article

View at publisher

Cite this article

Mohammad Kamrul Hasan, Shoeb Akibul Islam, Md. Sabbir Ejaz, Md. Mahbubul Alam, Nahid Mahmud, Tanvir Ahmed Rafin (2023). Classifying Bengali Newspaper Headlines with Advanced Deep Learning Models: LSTM, Bi-LSTM, and Bi-GRU Approaches. Asian Journal of Research in Computer Science , 372–388. https://doi.org/10.9734/ajrcos/2023/v16i4398

Affiliations

Mohammad Kamrul Hasan — Department of Information and Communication Engineering, Noakhali Science and Technology University, Bangladesh.
Shoeb Akibul Islam — Department of Information and Communication Engineering, Noakhali Science and Technology University, Bangladesh.
Md. Sabbir Ejaz — Department of Information and Communication Engineering, Noakhali Science and Technology University, Bangladesh.
Md. Mahbubul Alam — Department of Information and Communication Engineering, Noakhali Science and Technology University, Bangladesh.
Nahid Mahmud — Department of Information and Communication Engineering, Noakhali Science and Technology University, Bangladesh.
Tanvir Ahmed Rafin — Department of Information and Communication Engineering, Noakhali Science and Technology University, Bangladesh.

Metrics

22
Views: 0
Downloads: 25
Citations: 2
Outbound

Full metrics

Article metrics

Real usage data collected on this platform.

22

Page views

0

PDF downloads

2

Outbound clicks

25

Citations

Views over time

Views by country

Approximate, from request IP at view time — not citizenship or institution. Countries with fewer than 5 views are grouped as "Other".

Traffic sources

Referring site, by host.

Views and downloads exclude known bots/crawlers. Citations combines this platform's own DOI-resolved index with each external source's own reported total — see Cited by above for individually listed citing works. Last refreshed 0 seconds ago.