Multi-input ensemble models for multilingual Covid19 fake news Detection | |
| Author | Wasakorn Yousub |
| Call Number | AIT RSPR no.IM-22-03 |
| Subject(s) | Disinformation--Prevention--Data processing Deep learning (Machine learning) |
| Note | A research submitted in partial fulfillment of the requirements for the degree of Master of Science in Information Management |
| Publisher | Asian Institute of Technology |
| Abstract | The COVID-19 epidemic has wreaked havoc on many aspects of human life. Consequently, coronavirus outbreak has become more widespread and its ramifications are frequently men tioned in the press. However, not all reporting is accurate. Several of them spread erroneous information, instilling terror among their viewers, misinforming people, and therefore exac erbating the pandemic’s effects. We provide our findings on the dataset MM-COVID (Li et al., 2020) in this study. Detection of fake news in six languages. To improve the accuracy, we strive to utilize a news photograph. We present a model based on transformer-based and deep learning-based ensemble models in particular. We go through the models that were employed, as well as the methods for text preparation and data addition. As a consequence, our top model on the test set received an accuracy of 96.07%. |
| Year | 2022 |
| Type | Research Study Project Report (RSPR) |
| School | School of Engineering and Technology |
| Department | Department of Information and Communications Technologies (DICT) |
| Academic Program/FoS | Information Management (IM) |
| Chairperson(s) | Chaklam Silpasuwanchai |
| Examination Committee(s) | Dailey, Matthew N.;Attaphongse Taparugssanagorn |
| Scholarship Donor(s) | Royal Thai Government Fellowship |
| Degree | Research studies project report (M. Sc.) - Asian Institute of Technology, 2022 |