World PulseNow
Newsletter

BanglaASTE: A Novel Framework for Aspect-Sentiment-Opinion Extraction in Bangla E-commerce Reviews Using Ensemble Deep Learning

arXiv — cs.LG•Thursday, November 27, 2025 at 5:00:00 AM
PositiveArtificial Intelligence
  • The introduction of BanglaASTE marks a significant advancement in Aspect-Based Sentiment Analysis (ABSA) for Bangla e-commerce reviews, addressing the lack of specialized frameworks and datasets in this area. This novel framework enables the extraction of aspect terms, opinion expressions, and sentiment polarities from product reviews, utilizing a hybrid classification approach that combines graph-based matching and semantic similarity techniques.
  • This development is crucial as it fills a gap in Bangla sentiment analysis, providing researchers and businesses with the tools necessary to derive nuanced insights from user-generated content. The creation of the first annotated Bangla ASTE dataset, comprising 3,345 reviews from major platforms like Daraz and Facebook, enhances the potential for improved customer understanding and targeted marketing strategies.
  • The emergence of frameworks like BanglaASTE reflects a growing trend in natural language processing (NLP) to develop language-specific tools that cater to underrepresented languages. This aligns with ongoing efforts to enhance text normalization and classification capabilities in Bangla, as seen in other recent initiatives aimed at improving NLP applications in the region.
— via World Pulse Now AI Editorial System
Read Original

Was this article worth reading? Share it

Recommended apps based on your readingExplore all apps

Sellm

Track brand mentions across ChatGPT, Perplexity, and other AI platforms.

Marketing & CommerceTry the app

Supametas.AI

Extract and structure unstructured data for seamless LLM RAG integration.

AI & DataTry the app

Prdkit

AI-powered PRDs to capture and analyze user feedback efficiently.

Marketing & CommerceTry the app
Continue Readings
Bangla Hate Speech Classification with Fine-tuned Transformer Models
arXiv — cs.CLa day ago
Bangla Hate Speech Classification with Fine-tuned Transformer Models
PositiveArtificial Intelligence
A recent study has focused on hate speech classification in the Bangla language, which is spoken by over 230 million people in Bangladesh and India. The research, part of the BLP 2025 Shared Task, utilized various machine learning models, including transformer-based models like BanglaBERT and XLM-RoBERTa, achieving significant improvements in hate speech detection compared to traditional baseline methods.
Read full article
via arXiv — cs.CL
An Improved Ensemble-Based Machine Learning Model with Feature Optimization for Early Diabetes Prediction
arXiv — cs.LGa day ago
An Improved Ensemble-Based Machine Learning Model with Feature Optimization for Early Diabetes Prediction
PositiveArtificial Intelligence
A new machine learning model has been developed for early diabetes prediction, utilizing the BRFSS dataset, which includes over 253,680 records. The model employs various supervised learning techniques, including ensemble methods like stacking, achieving a strong ROC-AUC performance of approximately 0.96 with models such as Random Forest, XGBoost, CatBoost, and LightGBM.
Read full article
via arXiv — cs.LG
Hybrid(Penalized Regression and MLP) Models for Outcome Prediction in HDLSS Health Data
arXiv — cs.LGa day ago
Hybrid(Penalized Regression and MLP) Models for Outcome Prediction in HDLSS Health Data
PositiveArtificial Intelligence
A recent study introduced a hybrid machine learning model combining penalized regression and a multilayer perceptron (MLP) for predicting diabetes status using NHANES health survey data. This model outperformed traditional methods like logistic regression and random forest in terms of area under the curve (AUC) and balanced accuracy, showcasing its effectiveness in handling high-dimensional low-sample-size (HDLSS) data.
Read full article
via arXiv — cs.LG
Rep3Net: An Approach Exploiting Multimodal Representation for Molecular Bioactivity Prediction
arXiv — cs.LG2 days ago
Rep3Net: An Approach Exploiting Multimodal Representation for Molecular Bioactivity Prediction
PositiveArtificial Intelligence
A new deep learning architecture named Rep3Net has been proposed to enhance molecular bioactivity prediction in early-stage drug discovery. This model integrates traditional molecular descriptor data with spatial and relational information through graph-based representations and contextual embeddings generated by ChemBERTa from SMILES strings. The model has shown reliable predictions on the Poly [ADP-ribose] polymerase 1 (PARP-1) dataset, which is vital for DNA damage repair in cancer therapies.
Read full article
via arXiv — cs.LG
Optimizing Stroke Risk Prediction: A Machine Learning Pipeline Combining ROS-Balanced Ensembles and XAI
arXiv — cs.LG2 days ago
Optimizing Stroke Risk Prediction: A Machine Learning Pipeline Combining ROS-Balanced Ensembles and XAI
PositiveArtificial Intelligence
A new machine learning framework has been developed to optimize stroke risk prediction, utilizing ensemble modeling and explainable AI techniques. This framework achieved an impressive accuracy of 99.09% on the Stroke Prediction Dataset through a comprehensive evaluation of various models and data preprocessing methods, including Random Over-Sampling to address class imbalance.
Read full article
via arXiv — cs.LG