Thursday, October 2, 2025
Science
No Result
View All Result
  • Login
  • HOME
  • SCIENCE NEWS
  • CONTACT US
  • HOME
  • SCIENCE NEWS
  • CONTACT US
No Result
View All Result
Scienmag
No Result
View All Result
Home Science News Technology and Engineering

De New AI learning model improves stance detection performance and efficiency

September 3, 2024
in Technology and Engineering
Reading Time: 4 mins read
0
AI low-resource stance detection requires collaborative model mechanisms to optimize accuracy
65
SHARES
591
VIEWS
Share on FacebookShare on Twitter
ADVERTISEMENT

General AI systems, like OpenAI’s GPT, depend on large amounts of training data to improve model accuracy and performance. Research or medical AI applications, which often lack both training data and computing power, can leverage a new model designed to improve the efficiency, relevance and accuracy of AI outputs for more specialized scenarios.

AI low-resource stance detection requires collaborative model mechanisms to optimize accuracy

Credit: Big Data Mining and Analytics, Tsinghua University Press

General AI systems, like OpenAI’s GPT, depend on large amounts of training data to improve model accuracy and performance. Research or medical AI applications, which often lack both training data and computing power, can leverage a new model designed to improve the efficiency, relevance and accuracy of AI outputs for more specialized scenarios.

 

Large pretrained language models (PLMs) use increasingly large datasets, like Wikipedia, to train and optimize machine learning (ML) models to perform a specific task. While the accuracy and performance of large PLMs, like ChatGPT, have improved over time, large PLMs don’t work well in situations where large datasets aren’t available or can’t be used due to computing limitations. Simply put, a new AI solution is required to effectively utilize ML in research, medical or other applications where vast amounts of information aren’t available to adequately train existing AI models.

 

To address this issue, a team of computer scientists from the Agency for Science Technology and Research (A*STAR) in Singapore recently engineered a collaborative knowledge infusion method that efficiently trains an ML model with smaller amounts of training data. In this case, the researchers created a model that more accurately determines the stance, or opinion for or against, of a specific target, such as a product or political candidate, based on the context of a Tweet, commercial review or other language data.

 

The team published their study in the journal Big Data Mining and Analytics on August 28.

 

“Stance detection is inherently a low-resource task due to the diversity of targets and the limited availability of annotated data. Despite these challenges, stance detection is critical for monitoring social media, conducting polls and informing governance strategies,” said Yan Ming, senior scientist at the Center for Frontier AI Research (CFAR) at A*STAR and first author of the paper. “Enhancing AI-based methods for low-resource stance detection is essential to ensure these tools are effective and reliable in real-world applications.”

 

Smaller training datasets can have a profound effect on the accuracy of AI prediction models. For example, the target “breaking the law” in Wikipedia links to a heavy metal song by Judas Priest rather than the true definition of the term: acting in an illegal manner. This type of erroneous training data can seriously affect the performance of ML models.

 

In order to improve the accuracy of AI stance detection that depends on smaller training datasets, the research team focused on collaborative model mechanisms to: 1) verify knowledge from different sources and 2) learn selective features more efficiently.

 

“Most AI systems rely on pre-trained models developed using massive, pre-defined datasets that can become outdated, leading to performance degradation. Our proposed method addresses this challenge by integrating verified knowledge from multiple sources, ensuring that the model remains relevant and effective,” said Ming.

 

“Pre-trained large language models additionally require extensive annotated data for training due to their large-scale parameters. Our method introduces a collaborative adaptor that incorporates a minimal number of trainable parameters, … enhancing training efficiency and improving feature learning capabilities,” said Ming.

 

The team also targeted optimization efficiency of large PLMs by staging the optimization algorithm.

 

To test their model, the researchers performed experiments on three publicly available stance-detection datasets: VAST, P-Stance and COVID-19-Stance. The performance of the team’s model was then compared to the performance achieved by the TAN, BERT, WS-BERT-Dual and other AI models.

 

Measured through F1 scores, an ML model accuracy, the research team’s new stance detection model for low-resource training data consistently scored higher than other AI models using all three datasets, with F1 scores of between 79.6% and 86.91%. An F1 score of 70% or higher is currently considered good.

 

The new stance-detection model greatly improves the practicality of AI in more specialized research settings, and provides a template for additional optimization in the future. “Our primary focus is on efficient learning within low-resource real-world applications. Unlike major AI firms that concentrate on developing general artificial intelligence (AGI) models, our objective is to create more efficient AI methods that benefit both the public and the research community,” said Joey Tianyi Zhou, principal scientist at CFAR and co-author of the paper.

 

Ivor W. Tsang from the Centre for Frontier AI Research (CFAR) and the Institute of High Performance Computing (IHPC) at the Agency for Science Technology and Research (A*STAR) in Singapore also contributed to this research.

 


About Big Data Mining and Analytics

Big Data Mining and Analytics (Published by Tsinghua University Press) discovers hidden patterns, correlations, insights and knowledge through mining and analyzing large amounts of data obtained from various applications. It addresses the most innovative developments, research issues and solutions in big data research and their applications. Big Data Mining and Analytics is indexed and abstracted in ESCI, EI, Scopus, DBLP Computer Science, Google Scholar, INSPEC, CSCD, DOAJ, CNKI, etc.

About SciOpen 

SciOpen is an open access resource of scientific and technical content published by Tsinghua University Press and its publishing partners. SciOpen provides end-to-end services across manuscript submission, peer review, content hosting, analytics, identity management, and expert advice to ensure each journal’s development. By digitalizing the publishing process, SciOpen widens the reach, deepens the impact, and accelerates the exchange of ideas.



Journal

Big Data Mining and Analytics

DOI

10.26599/BDMA.2024.9020021

Article Title

Collaborative Knowledge Infusion for Low-Resource Stance Detection

Article Publication Date

28-Aug-2024

Share26Tweet16
Previous Post

Plant proteins could be radical alternative to oil-based super lubricants

Next Post

Professor Helena Kelly appointed Head of the School of Pharmacy and Biomolecular Sciences at RCSI

Related Posts

blank
Technology and Engineering

Scientists Create Molecular Qubits for Communication at Telecom Frequencies

October 2, 2025
blank
Technology and Engineering

Revolutionizing Genome Studies with SECRET-GWAS

October 2, 2025
blank
Technology and Engineering

Advanced Composite Engineering Boosts Sodium-Ion Battery Performance

October 2, 2025
blank
Technology and Engineering

Breakthrough: Innovative Membrane Gel from UCSB Paves the Way for Advancements in Breast Cancer Research

October 2, 2025
blank
Technology and Engineering

Enhancing Biosecurity Measures for Genes Associated with High-Risk Proteins

October 2, 2025
blank
Technology and Engineering

Exploring RNA-Protein Interactions: A Pathway to Innovative Cancer and Brain Disease Therapies

October 2, 2025
Next Post
Professor Helena Kelly

Professor Helena Kelly appointed Head of the School of Pharmacy and Biomolecular Sciences at RCSI

  • Mothers who receive childcare support from maternal grandparents show more parental warmth, finds NTU Singapore study

    Mothers who receive childcare support from maternal grandparents show more parental warmth, finds NTU Singapore study

    27562 shares
    Share 11022 Tweet 6889
  • University of Seville Breaks 120-Year-Old Mystery, Revises a Key Einstein Concept

    970 shares
    Share 388 Tweet 243
  • Bee body mass, pathogens and local climate influence heat tolerance

    646 shares
    Share 258 Tweet 162
  • Researchers record first-ever images and data of a shark experiencing a boat strike

    513 shares
    Share 205 Tweet 128
  • Groundbreaking Clinical Trial Reveals Lubiprostone Enhances Kidney Function

    477 shares
    Share 191 Tweet 119
Science

Embark on a thrilling journey of discovery with Scienmag.com—your ultimate source for cutting-edge breakthroughs. Immerse yourself in a world where curiosity knows no limits and tomorrow’s possibilities become today’s reality!

RECENT NEWS

  • Atlas Reveals Testicular Aging Across Species
  • Early Onset of Neuroinflammation Observed in Individuals with Down Syndrome
  • Global Regulatory Policy Fuels Medical Education Panic
  • Urban Architecture’s Role in Climate Change Solutions

Categories

  • Agriculture
  • Anthropology
  • Archaeology
  • Athmospheric
  • Biology
  • Blog
  • Bussines
  • Cancer
  • Chemistry
  • Climate
  • Earth Science
  • Marine
  • Mathematics
  • Medicine
  • Pediatry
  • Policy
  • Psychology & Psychiatry
  • Science Education
  • Social Science
  • Space
  • Technology and Engineering

Subscribe to Blog via Email

Enter your email address to subscribe to this blog and receive notifications of new posts by email.

Join 5,186 other subscribers

© 2025 Scienmag - Science Magazine

Welcome Back!

Login to your account below

Forgotten Password?

Retrieve your password

Please enter your username or email address to reset your password.

Log In
No Result
View All Result
  • HOME
  • SCIENCE NEWS
  • CONTACT US

© 2025 Scienmag - Science Magazine

Discover more from Science

Subscribe now to keep reading and get access to the full archive.

Continue reading