| รหัสดีโอไอ | 10.14456/kmuttrd.2022.16 |
|---|---|
| Creator | ฐิติรัตน์ ศิริบวรรัตนกุล |
| Title | การตรวจสอบข่าวปลอมภาษาไทยด้วยเทคนิคการประมวลผลภาษาธรรมชาติ |
| Contributor | ธัชพิชญ์ ชำนาญกิจ |
| Publisher | King Mongkut’s University of Technology Thonburi |
| Publication Year | 2022 |
| Journal Title | KMUTT Research and Development Journal |
| Journal Vol. | 45 |
| Journal No. | 2 |
| Page no. | 275-287 |
| Keyword | Fake News, Fake News Detection, Thai Natural Language Processing |
| URL Website | https://journal.kmutt.ac.th/ |
| Website title | เว็บไซต์วารสารวิจัยและพัฒนา มจธ. |
| ISSN | 2697-5521 |
| Abstract | In this research, a lightweight prototype of aThai fake news detection system as an alternative for users looking for fast and accessible Thai fake news detectors is proposed. The prototype is based on a Thai fake news database (Google BigQuery) where the news is collected from online resources and communities regarding Thai fake news warnings. Using techniques based on natural language processing, each news is processed and the extracted feature is stored in the database. For each user query, the query is transformed into a feature vector; such a vector is compared to the vectors of fake news stored in the database. Top three news (in the database) with maximum matching scores are then displayed to the user. Based on the experimental results on the test set, the current prototype can identify 120 news with the precision of 91.84% and recall of 75.00%. |
| ดิจิตอลไฟล์ |
Digital File |