Results 61 to 70 of about 5,471 (199)

Addressing Bias in Spoken Language Systems Used in the Development and Implementation of Automated Child Language‐Based Assessment

Journal of Educational Measurement, Volume 63, Issue 1, Spring 2026.
Abstract This article addresses bias in Spoken Language Systems (SLS) that involve both Automatic Speech Recognition (ASR) and Natural Language Processing (NLP) and reports experiments to improve the performance of SLS for automated language and literacy‐related assessments with students who are under served in the U.S. educational system.
Alison L. Bailey, Alexander Johnson, Natarajan Balaji Shankar, Hariram Veeramani, Julie A. Washington, Abeer Alwan   +5 more
wiley   +1 more source

Detection and Classification of Ideological Texts in the Kazakh Language Using Machine Learning and Transformers

Research in Language
Modern information technologies enable the automatic analysis of textual data to detect extremist and propagandistic content. This paper examines deep learning methods and transformers models for the automatic classification of ideologically charged ...
Milana Bolatbek, Shynar Mussiraliyeva, Kymbat Baisylbayeva   +2 more
doaj   +1 more source

Right on cue? Category‐switching in online marketplaces

Strategic Management Journal, Volume 47, Issue 1, Page 73-106, January 2026.
Abstract Research Summary When and why do producers change the categorization of their offerings? Prior categorization research assumes that producers engage in ongoing efforts to proactively optimize their categorical positioning, but this assumption may not hold for many producers due to their limited attentional capacity.
Karl Taeuscher, Eric Yanfei Zhao, Michael Lounsbury   +2 more
wiley   +1 more source

Towards Computationally Feasible Deep Active Learning

, 2022
Active learning (AL) is a prominent technique for reducing the annotation effort required for training machine learning models. Deep learning offers a solution for several essential obstacles to deploying AL in practice but introduces many others. One of
Avetisian, Manvel, Gusev, Gleb, Kuzmin, Gleb, Larionov, Daniil, Sanochkin, Leonid, Shelmanov, Artem, Tsvigun, Akim, Zhukov, Leonid   +7 more
core  

A New Polar Transform‐Based Network for Multi‐Lingual Handwritten Text Sentiment Analysis

IET Image Processing, Volume 20, Issue 1, January/December 2026.
This work introduces a new problem of sentiment analysis using handwritten text images. Unlike existing methods, which focus on posted text for sentiment analysis, this work shows that handwriting can also be used for sentiment analysis. For achieving our goal, the proposed work introduces a new idea of exploring polar transformation.
Chandraiah T, Prajwal Kumar P, Basavanna M, Shivakumara Palaiahnakote, Daniel P. Lopresti, Maira Alamgir   +5 more
wiley   +1 more source

A Comparative Analysis of Sentence Transformer Models for Automated Journal Recommendation Using PubMed Metadata

Big Data and Cognitive Computing
We present an automated journal recommendation pipeline designed to evaluate the performance of five Sentence Transformer models—all-mpnet-base-v2 (Mpnet), all-MiniLM-L6-v2 (Minilm-l6), all-MiniLM-L12-v2 (Minilm-l12), multi-qa-distilbert-cos-v1 (Multi-qa-
Maria Teresa Colangelo, Marco Meleti, Stefano Guizzardi, Elena Calciolari, Carlo Galli   +4 more
doaj   +1 more source

A Neural Network‐Based Decision Framework Utilizing Large Language Models and Neutrosophic Sets for Sustainable Supplier Selection

International Journal of Intelligent Systems, Volume 2026, Issue 1, 2026.
Sustainable supplier selection is a high‐impact decision problem in which organizations must jointly evaluate economic performance, environmental impact, and social responsibility under heterogeneous stakeholder preferences, asymmetric decision authority, and predominantly linguistic assessments. Conventional multiattribute group decision‐making (MAGDM)
Amirhossein Nafei, Zhi Li, S. Pourmohammad Azizi, Richard Murray   +3 more
wiley   +1 more source

LLM-as-a-judge for sarcasm detection using supervised fine-tuning of transformers

Journal of King Saud University: Computer and Information Sciences
This research conducts a systematic comparative study of large pre-trained language models (LLMs) for sarcasm and irony detection. While pretrained transformers often struggle to capture sarcastic intent, we fine-tune multiple domain-specific models and ...
Simona-Vasilica Oprea, Adela Bâra
doaj   +1 more source

A Hybrid Deep Learning Approach for Multi-Class Cyberbullying Classification Using Multi-Modal Social Media Data

Applied Sciences
Cyberbullying involves the use of social media platforms to harm or humiliate people online. Victims may resort to self-harm due to the abuse they experience on these platforms, where users can remain anonymous and spread malicious content.
Israt Tabassum, Vimala Nunavath
doaj   +1 more source

A Comprehensive Benchmarking Pipeline for Transformer-Based Sentiment Analysis using Cross-Validated Metrics [PDF]

Transformer-based models have significantly advanced sentiment analysis in natural language processing. However, many existing studies still lack robust, cross-validated evaluations and comprehensive performance reporting.
Abidin, Dodo Zaenal, Afuan, Lasmedi, Nurhadi, Nurhadi, Toscany, Afrizal Nehemia   +3 more
core   +2 more sources