Related Experiment Video
Updated: Oct 26, 2025
03:14
Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness
Published on: December 6, 2024
780
Implementation of the BERT-derived architectures to tackle disinformation challenges
Sebastian Kula1,2, Rafał Kozik1, Michał Choraś1
1UTP University of Science and Technology, Kaliskiego 7, 85-976 Bydgoszcz, Poland.
Neural Computing & Applications
|July 28, 2021
Summary
This study introduces advanced artificial intelligence models, specifically BERT neural networks, to combat fake news. These intelligent systems offer a robust solution for detecting and mitigating the harmful societal impacts of misinformation.
Area of Science:
- Computer Science
- Artificial Intelligence
- Natural Language Processing
Background:
- Information is a valuable asset, but also a tool for competition and malicious use, leading to societal issues like panic and instability.
- Fake news poses a significant threat, necessitating advanced computer security tools.
- Artificial intelligence, particularly neural networks, offers intelligent solutions for complex tasks.
Purpose of the Study:
- To develop flexible and intelligent tools for detecting fake news.
- To leverage state-of-the-art neural network architectures for combating misinformation.
- To present Transformer-based hybrid architectures for fake news detection models.
Main Methods:
- Utilized artificial intelligence and neural network architectures.
- Applied BERT neural network, a state-of-the-art architecture.
- Developed Transformer-based hybrid architectures for model creation.
Main Results:
- Successfully designed models for detecting fake news.
- Demonstrated the application of advanced neural networks in NLP tasks.
- Presented effective Transformer-based hybrid architectures.
Conclusions:
- Artificial intelligence and advanced neural networks are crucial for developing effective fake news detection systems.
- Transformer-based hybrid architectures show promise in creating intelligent security tools.
- Modern computer security requires advanced AI models to address the challenges of fake news.
Related Concept Videos
01:14Understanding Deception
32
Deception is a pervasive aspect of human communication. Empirical studies have shown that most individuals engage in some form of deceit on a daily basis, with approximately 20% of social exchanges involving deceptive elements. Lying follows a developmental trajectory, peaking during adolescence and declining with age, possibly due to the maturation of cognitive control and social accountability.Cognitive and Social Factors in Deception DetectionDespite its prevalence, accurately detecting...
32
02:16Stereotype Content Model
15.0K
The Stereotype Content Model (SCM) was first proposed by Susan Fiske and her colleagues (Fiske, Cuddy, Glick & Xu, 2002; see also Fiske, 2012 and Fiske, 2017). The SCM specifies that when someone encounters a new group, they will stereotype them based on two metrics: warmth—or that group’s perceived intent, and how likely they are to provide help or inflict harm—and competence—or their ability to carry out that objective. Depending on the warmth-competence...
15.0K