Results 51 to 60 of about 649 (143)

Enhancing E‐Commerce Recommendations Through Review Summarization and Multi‐Embedding Feature Fusion

Expert Systems, Volume 43, Issue 9, September 2026.
ABSTRACT With the rapid growth of e‐commerce, recommender systems have become essential tools for alleviating information overload by providing users with personalized item suggestions that match their preferences. Traditional collaborative filtering approaches have shown strong performance, while they still suffer from data sparsity since they rely ...
Haebin Lim, Seonu Park, Qinglong Li, Xinzhe Li, Jaekyeong Kim   +4 more
wiley   +1 more source

Subword Complexes and Nil-Hecke Moves

Modeling and Analysis of Information Systems, 2015
For a finite Coxeter group W, a subword complex is a simplicial complex associated with a pair (Q, ρ), where Q is a word in the alphabet of simple reflections, ρis a group element. We describe the transformations of such a complex induced by nil-moves and inverse operations on Q in the nil-Hecke monoid corresponding to W.
openaire   +5 more sources

Detecting Opioid Misuse on Social Media via Named Entity Recognition (NER) With Deep Learning

Expert Systems, Volume 43, Issue 8, August 2026.
ABSTRACT The opioid overdose epidemic constitutes a critical public health crisis, necessitating advanced surveillance tools to enable timely intervention. Social media platforms provide a real‐time source of information on drug‐related behaviours. However, extracting structured knowledge from their informal, slang‐heavy and fragmented text presents ...
Muhammad Ahmad, Rita Orji, Fida Ullah, Ildar Batyrshin, Grigori Sidorov   +4 more
wiley   +1 more source

From Language Identification to Topic Modelling: A Fully Integrated Pipeline for Multilingual Aspect‐Based Sentiment Analysis and Component‐Level Insights

Expert Systems, Volume 43, Issue 7, July 2026.
ABSTRACT The rapid expansion of multilingual digital platforms has made the accurate analysis of user‐generated content across different languages and cultural contexts increasingly essential. However, existing methods struggle to maintain consistent performance due to linguistic diversity, morphological complexity, and structural variations in text ...
Abdulkadir Şeker
wiley   +1 more source

Investigating linguistic errors in large language model generation of uzbek text

Cogent Arts & Humanities
This study examines how contemporary large language models (LLMs) generate Uzbek, an agglutinative, morphologically rich, and low-resource Turkic language.
Dilyorjon Solidjonov, Muhammadjon Najmiddinov   +1 more
doaj   +1 more source

Proper 3‐realizability and second cohomology of groups on two generators of finite order

Bulletin of the London Mathematical Society, Volume 58, Issue 7, July 2026.
Abstract Given an (infinite) finitely generated group G$G$, its first cohomology group H1(G;ZG)$H^1(G;{\mathbb {Z}}G)$ is free abelian and “counts” the number of ends of G$G$ which equals 1+rank(H1(G;ZG))$1 + rank (H^1(G;{\mathbb {Z}}G))$. The question whether or not for every finitely presented group G$G$ its second cohomology group H2(G;ZG)$H^2(G ...
Francisco F. Lasheras, R. Roy
wiley   +1 more source

A Comparative Analysis of Character and Word-Based Tokenization for Kawi-Indonesian Neural Machine Translation

Journal of Applied Informatics and Computing
Preserving regional languages ​​is a strategic step in preserving cultural heritage while expanding access to knowledge across generations. One approach that can support this effort is the application of automatic translation technology to digitize and ...
I Gede Bintang Arya Budaya, I Gede Putra Mas Yusadara   +1 more
doaj   +1 more source

User‐Based Evaluation of Explainability Techniques for Misogyny Detection in Code‐Mixed Hindi–English

Applied AI Letters, Volume 7, Issue 2, June 2026.
In this work, we have performed human‐based evaluation of three post hoc explainability techniques, Local Interpretable Model Agnostic Explanations (LIME), Shapely Additive Explanations (SHAP), and integrated Gradients (IG) for a multilingual Bidirectional Encoder Representations from Transformers (mBERT) based binary and multi‐label misogyny ...
Sargam Yadav, Abhishek Kaushik, Kevin McDaid   +2 more
wiley   +1 more source

Heterogeneous Deep‐Ensemble Framework for Sentiment Analysis of Movie Reviews Based on Stacking and Voting

Concurrency and Computation: Practice and Experience, Volume 38, Issue 11, June 2026.
ABSTRACT Sentiment analysis of movie reviews reflects users' behavioral preferences and emotional responses to films, aiding in understanding audience needs and enhancing user experience. In recent years, deep ensemble learning has significantly improved sentiment polarity prediction by combining multiple deep models.
Hanzhe Cai, Ze Wu, Seena Joseph
wiley   +1 more source

A federated deep learning framework with distributed hybrid character-level and attention mechanisms for scalable and cost-efficient fake news detection

Scientific Reports
Fake news detection is an essential task for media and news organizations to maintain the trust and reliability of the published content. Due to the rapid growth of online users and the spread of misinformation through malicious sources, the fake news ...
K. Nithya, C. R. Dhivyaa
doaj   +1 more source