Seasonal evaluation of glacier dynamics and risk analysis using remote sensing techniques in the Buni Zom Valley, Chitral River Basin, Northern Pakistan

Environmental Earth Sciences, Год журнала: 2025, Номер 84(4)

Опубликована: Фев. 1, 2025

Язык: Английский

In-depth Urdu Sentiment Analysis Through Multilingual BERT and Supervised Learning Approaches

IECE transactions on intelligent systematics., Год журнала: 2024, Номер 1(3), С. 161 - 175

Опубликована: Ноя. 9, 2024

Sentiment analysis is the process of identifying and categorizing opinions expressed in a piece text. It has been extensively studied for languages like English Chinese but still needs to be explored such as Urdu Hindi. This paper presents an in-depth text using state-of-the-art supervised learning techniques transformer-based technique. We manually annotated preprocessed dataset from various blog websites categorize sentiments into positive, neutral, negative classes. utilize five machine classifiers: Support Vector Machine (SVM), K-nearest neighbor (KNN), Naive Bayes, Multinomial Logistic Regression (MLR), multilingual BERT (mBERT) model. model was fine-tuned capture deep contextual embeddings specific The mBERT pre-trained on 104 optimized Urdu-specific sentiment classification by fine-tuning it dataset. Our results demonstrated that significantly outperformed traditional classifiers, achieving accuracy 96.5% test set. study highlights effectiveness transfer via low-resource Urdu, making highly promising approach analysis.

Язык: Английский

Enhancing Fake News Detection with a Hybrid NLP-Machine Learning Framework

IECE transactions on intelligent systematics., Год журнала: 2024, Номер 1(3), С. 203 - 214

Опубликована: Дек. 12, 2024

The increasing prevalence of fake news on social media has become a significant challenge in today’s digital landscape. This paper proposes hybrid framework for detection, combining Natural Language Processing (NLP) techniques and machine learning algorithms. Using Term Frequency-Inverse Document Frequency (TF-IDF) feature extraction, classifiers such as Logistic Regression (LR), Naïve Bayes (NB), Support Vector Machines (SVM), the model integrates Maximum Likelihood Estimation (MLE) with to achieve 95% accuracy 93% precision Kaggle dataset. results highlight potential statistical NLP approaches improve detection accuracy.

Язык: Английский