Sign inSubmit
Tips: “quotes” for a phrase · author:Lee · a DOI goes straight to its article

54 articles for “BERT”
Set a search alert
Research ArticleOpen accessIn the keywordsEnhancing Sentiment Analysis for Malayalam With mBERT: A Profoundly Transparent and Accurate Approach Using LIMEAnitha R., K. S. Anil Kumar, Rajeev R. R. et al.The overlapping sentiment boundaries, intensifiers, and intricate morphological structures in Malayalam present particular difficulties for sentiment analysis, making it hard for traditional machine learning techniques to produce consistent results. We present an explainable sentiment analysis framework in this paper that refines a Multilingual Bidirectional Encoder Representations from Transformers (mBERT) model on a novel constituency-level dataset that has been manually curated … …Journal of Computer Science, Vol. 22, Issue 5 · 2 Jun 2026 · 1,061 accessesView PDFCite
Research ArticleOpen accessIn the keywordsHybrid Deep Learning Models for Text Classification: Performance Evaluation of TriDistilBERT and BiGRU ArchitecturesAmira Samy TalaatText can be a valuable source of information, but its unstructured nature makes analysis challenging and time-consuming. Machine Learning (ML) algorithms can efficiently analyze and structure text, enabling organizations to automate processes and uncover insights that support better decision-making. This study focuses on applying ML to a classification problem using two datasets. Four deep learning models are introduced, combining Bi … …Journal of Computer Science, Vol. 21, Issue 9 · 10 Oct 2025 · 2,792 accessesView PDFCite
Research ArticleOpen accessIn the keywordsDiverse Trajectory on Consumer’s Product Feedback Analysis by Confidence IntervalVithya Ganesan, Kirubakaran Namaskaram, Viriyala Sri Anima Padmini et al.The current investigation addresses the possibilities and limitations of the sentiment analysis of consumer remarks in the context of economic needs. It makes it easier for businesses to comprehend how the public's opinion shapes their abilities to satisfy clientele. Sentiment analysis concerns the assessment and interpretation of various forms of evaluation, such as product ratings, reviewer responses, and question-and-answer sessions. … …Journal of Computer Science, Vol. 21, Issue 5 · 28 Apr 2025 · 5,140 accessesView PDFCite
Research ArticleOpen accessIn the keywordsSmart Talent Sourcing Through Advanced Skill Profiling TechniqueAmey Krishnanath Shet Tilve, Gaurang Sitaram Patkar, Vadiraj Gururaj Inamdar et al.The hiring process often struggles with aligning job seekers' skills to employers' requirements, leading to inefficiencies and mismatches. To address this challenge, a dual-functionality system is proposed that leverages Natural Language Processing (NLP) techniques, including BERT for embedding textual information and cosine similarity to rank resumes according to their alignment with job descriptions and to recommend suitable candidates to employers … …Journal of Computer Science, Vol. 21, Issue 2 · 18 Jan 2025 · 4,967 accessesView PDFCite
Research ArticleOpen accessIn the keywordsValidation of MIKE 11 Model Simulated Data for Biochemical and Chemical Oxygen Demands TransportMahdieh Eisakhani, Md. Pauzi Abdullah, Othman Abd Karim, Amirhossein MalakahmadProblem statement: The aim of the study was to model the discharge, biochemical and chemical oxygen demands (BOD and COD) loads in each cross section of Bertam River in Cameron Highlands, Malaysia. Cameron Highlands form the headwater catchment for two major rivers of the lowlands; Pahang River and Perak River. On the other hand, Cameron Highlands is undergoing rapid development … …American Journal of Applied Sciences, Vol. 9, Issue 3 · 27 Jan 2012 · 7,686 accessesView PDFCite
Research ArticleOpen accessIn the keywordsHybrid Pipelines for Intelligent Human Resources Text Classification: LLMs, RAG, and Generative AISoumia Chafi, Mustapha Kabil, Abdessamad KamoussThe digital transformation of Human Resources Information Systems (HRIS) requires advanced approaches to process unstructured textual data originating from Curriculum Vitae (CVs), cover letters, and job postings. Traditional text classification methods exhibit limitations when faced with current needs for contextual understanding and fine-grained skill detection. This paper proposes a hybrid pipeline combining advanced text classification, contrastive learning (SimCSE, Contriever), Retrieval-Augmented … …Journal of Computer Science, Vol. 22, Issue 4 · 22 Apr 2026 · 1,509 accessesView PDFCite
Research ArticleOpen accessIn the keywordsPsychological Behavior Prediction through Sentiment Analysis Technics: Transformers and ML ApproachMaryame Naji, Najima Daoudi, Rachida AjhounIn the era of the COVID-19 epidemic, governmentshave imposed nationwide lockdowns, which make a huge change to people's dailyroutines. This last impacts indirectly the well-being of people's mentalhealth. And due to social media, many conversations about these phenomena occuronline, especially those related to people's emotions. Which brought challengesand opportunities for sentiment analysis researchers. In this article, we areinterested in extracting … …Journal of Computer Science, Vol. 18, Issue 9 · 14 Sep 2022 · 5,753 accessesView PDFCite
Research ArticleOpen accessIn the keywordsDeveloping a System for Antibacterial Treatment of Dental Caries using Culture Based ApproachM. Mishra, S. Ghosh, L. E. Alex et al.Problem statement: Dental caries is a chronic disease worldwide, caused mainly by microbes. The orthograde approaches still remain the only option of treatment. Lack of rapid antibiotic sensitivity determination of the dental pathogen is a rate limiting step in the field of Dental Microbiology. Approach: The culture dependent analysis was used for the study of oral microflora from five healthy … …OnLine Journal of Biological Sciences, Vol. 12, Issue 2 · 18 May 2012 · 9,061 accessesView PDFCite
Research ArticleOpen accessIn the keywordsA Cyanobacterium Synechocystis sp. PCC 6803 Glutaredoxin Gene (slr1562) Protects Escherichia coli against Abiotic StressesAhmed Gaber, Salah El-Din El-AssalProblem statement: Glutaredoxins (GRXs) are ubiquitous small heat stable glutathione-dependent oxidoreductase enzymes that play a crucial role in plant development and response to oxidative stress. Approach: Cyanobacterium Synechocystis strain PCC 6803 contains two genes (slr1562 and ssr2061) encoding glutaredoxins. In the present investigation the slr1562 gene (grxC) was isolated and characterized. Results: The results revealed that the amino acid sequence … …American Journal of Agricultural and Biological Sciences, Vol. 7, Issue 1 · 5 Mar 2012 · 7,582 accessesView PDFCite
Literature ReviewOpen accessIn the author namesExtraction Performance of Essential Oils by Hydrodistillation Using Mathematical Models: A Systematic ReviewLenin Quiñones Huatangari, Frank Fernandez Rosillo, Eliana Milagros Cabrejos Barrios et al.Essential oils are complex mixtures of volatile organic compounds valued for their antimicrobial and antioxidant properties, with widespread applications in the food, pharmaceutical, and cosmetic industries. Among the various extraction techniques employed, hydrodistillation remains one of the most widely used methods. The extraction yield of essential oils by hydrodistillation is influenced by multiple factors, and quantifying these through mathematical modelling … …OnLine Journal of Biological Sciences, Vol. 26, Issue 1 · 25 Mar 2026 · 2,508 accessesView PDFCite