Survey Maps How Narrative Theory Shapes LLM Story Generation and Understanding
A survey in Artificial Intelligence Review categorises narrative theory-driven large language model methods and finds generation tasks lag behind understanding ...
Tag: Natural Language Processing
DeBERTa-v3 and Aspect Attention Decode Mixed Sentiment in Amazon Reviews
A dual-track AI framework reads Amazon reviews with DeBERTa-v3 encoders and aspect-specific attention, assigning sentiment to product, delivery, and service ...
Hybrid Transformer Model Reads Text and Images Together to Flag Hate Speech
A new hybrid multimodal transformer framework combines contrastive annotation, cross-modal attention, graph-based lexical expansion, and ordinal hate-intensity scoring, reporting 91.8 ...
Knowledge Graph Boosts AI Extraction of Drug Side Effects from Patient Narratives
GraphRAG-ADR combines a knowledge graph with a large language model to extract adverse drug reactions from informal patient narratives, reaching ...
NLP analysis of student feedback reveals teaching quality concerns in the DRC
Researchers applied sentiment analysis and topic modeling to survey responses from 378 computer science students at 18 institutions in the ...
Stigmatizing language found in over half of primary care patient records
A retrospective analysis of primary care electronic health records found stigmatizing language in 45.3 percent of clinical notes, with higher ...
AI Reads the News: Large Language Models Decode Public Health Policy Debates
Researchers show that GPT-5 and Gemini can extract and classify policy framing quotes from German news articles with F1-scores near ...
New AI model reads text, images and social networks to spot cyberbullying
A new multimodal AI system called HMTF-Net combines text, conversation context, user interaction graphs, images and metadata to detect cyberbullying, ...
Fewer than half of incidental lung nodules get recommended follow-up in New York study
A retrospective study of 1,266 patients at two New York hospitals found only 41.3 percent of incidental lung nodules received ...
Simple Machine Learning Outperforms Deep Models in Somali Dialect Test
A new study reports that a simple Naive Bayes classifier reached 99.05 percent accuracy in distinguishing Somali's MAXAA TIRI and ...
AI Research on Eating Disorders Is Booming, but Almost Nothing Reaches the Clinic
A scoping review of 66 studies finds artificial intelligence research on eating disorders has grown rapidly since 2016, yet 77 ...
Structured Memory Scheduling Helps Large Language Models Reason Beyond Retrieval
A new framework called SMS-RAG schedules semantic, structural, and episodic memory during reasoning, outperforming existing retrieval-augmented methods on multi-hop QA ...
AI Model Predicts Secondary-School English Performance With Built-In Uncertainty
A new computational framework claims the best mean predictive performance across four English learner corpora, forecasting writing scores and speaking-proficiency ...
AI Models Trained on Old Rumour Data Falter on Irish Rumours, New Dataset Shows
A new study finds that rumour stance classification models trained on RumourEval data degrade considerably on a new Irish rumour ...
Retrieval-augmented LoRA-tuned language model writes structured software test cases
A FLAN-T5 model combining retrieval augmentation and parameter-efficient fine-tuning achieved high-quality structured test-case generation with measurable latency costs.
AI deception detectors stumble when synthetic training meets real-world stress
A study of military training interviews found that machine learning models trained on synthetic deception data collapsed on real-world speech, ...
Computational Genotoxicity Takes Center Stage at JEMS 2024 Symposium
A JEMS 2024 symposium report outlines how (Q)SAR modeling, machine learning, and error-corrected sequencing are shaping the emerging field of ...
Bibliometric Map Traces Computational Social Science From Big Data to Generative AI
A bibliometric analysis of 861 Scopus-indexed articles traces how computational social science evolved from agent-based modelling to generative artificial intelligence ...
Six AI models read thousands of cancer narratives and mostly disagree on what they feel
A multi-model NLP study of more than 200 online cancer narrative sources found negative sentiment dominated diagnosis and treatment discourse, ...
Emotion-aware multi-agent reinforcement learning boosts customer service dialogue performance in new study
A new open-access study reports that a multi-agent reinforcement learning framework combined with bio-inspired hyperparameter optimization outperformed comparison models on ...
POPULAR NEWS
-
CRISPR Beta-Cell Regeneration Shows Early Promise for Long-Term Diabetes Management
-
Sudan Study Reveals Gaps in Kidney Stone Prevention Care
-
Machine Learning Model Predicts Pediatric Sepsis Risk Using Routine Clinical Indicators
-
ChatMPC Integrates Natural Language Processing with Predictive Control for Autonomous Driving