Authors:
Razan Masood
and
Ahmet Aker
Affiliation:
Department of Information Engineering, University of Duisburg-Essen, Duisburg and Germany
Keyword(s):
Fake News, Stance Detection, Traditional Machine Learning, Feature Engineering.
Related
Ontology
Subjects/Areas/Topics:
Artificial Intelligence
;
Knowledge Management and Information Sharing
;
Knowledge-Based Systems
;
Social Networks and the Psychological Dimension
;
Symbolic Systems
Abstract:
Fake news has caused sensation lately, and this term is the Collins Dictionary Word of the Year 2017. As the news are disseminated very fast in the era of social networks, an automated fact checking tool becomes a requirement. However, a fully automated tool that judges a claim to be true or false is always limited in functionality, accuracy and understandability. Thus, an alternative suggestion is to collaborate a number of analysis tools in one platform which help human fact checkers and normal users produce better judging based on many aspects. A stance detection tool is a first stage of an online challenge that aims to detect fake news. The goal is to determine the relative perspective of a news article towards its title. In this paper, we tackle the challenge of stance detection by utilizing traditional machine learning algorithms along with problem specific feature engineering. Our results show that these models outperform the best outcomes of the participating solutions which
mainly use deep learning models.
(More)