가짜뉴스 탐지를 위한 엔터티가 추가된 어텐션 네트워크 개발
조진욱, 김응범, 김한민 et al. · 대한산업공학회 추계학술대회 논문집 · 2019
With the rapid development of social networks, fake news, ich is generated maliciously is spreading rapidly online. As it easily distorts public opinion and promotes biased thinking, it has emerged as an important social issue. In this context, it is necessary to detect fake news automatically. Most of the existing methods propose fake news detection models using only news contents. However, since news contents only represent the distributional patterns, not general knowledge, there is still a limitation of reliability by bias of the dataset. To overcome the limitation, we propose a self-attention network model using the original news contents with the entities, which are derived by a knowledge graph. As a result, we can expect to detect fake news more reliably. To prove the superiority of our method, we perform the experiments.
Cited by 0 works.