Back to the articles list | Back to browse issues page

XML Print

Persian Rumor Detection Using a Multi-Classifier Fusion Approach
Alireza Mansouri 1, Maryam Mahmoudi2 , Mojgan Farhoodi2 , Seyed Mohammadreza Mirsarraf2
1- Faculty of Information Technology, ICT Research Institute , amansuri@itrc.ac.ir
2- Faculty of Information Technology, ICT Research Institute
Abstract:   (42 Views)
During the last few years, rumor and its rapid diffusion via social media have affected public opinions, even in some important such as presidential elections. One of the main approaches for rumor detection methods is based on content and natural language processing. Despite considerable improvement made in this regard in English language, unfortunately, we have not witnessed enough progress in Persian language, mainly due to a lack of datasets in this area. The main novelty of this paper is combining different learning methods to achieve a more performance outcome in comparison with each method. The methods we used in this study include three classifiers based on lingual-based features, word frequency-based, and word embedding-based features. The results show that combined different methods using the weighted majority fusion method, a significant improvement in the results is achieved.
Keywords: Rumor detection, Machine learning, Content-based text classification, Deep learning, Multi-classification
Full-Text [DOCX 826 kb]   (10 Downloads)    
Type of Study: Research | Subject: Information Technology
Rights and permissions
Creative Commons License This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.