التفاصيل البيبلوغرافية
| العنوان: |
ELAINE: rELiAbility and evIdence-aware News vErifier |
| المؤلفون: |
Badenes-Olmedo, Carlos, Saquete Boró, Estela, Sepúlveda-Torres, Robiert, Bonet-Jover, Alba |
| المساهمون: |
Universidad de Alicante. Departamento de Lenguajes y Sistemas Informáticos, Procesamiento del Lenguaje y Sistemas de Información (GPLSI) |
| بيانات النشر: |
CEUR |
| سنة النشر: |
2023 |
| المجموعة: |
RUA - Repositorio Institucional de la Universidad de Alicante |
| مصطلحات موضوعية: |
Disinformation, Reliability, Question Answering, Knowledge Graphs |
| الوصف: |
Disinformation is one of the main problems of today’s society, and specifically the viralization of fake news. This research presents ELAINE, a hybrid proposal to detect the veracity of news items that combines content reliability information with external evidence. The external evidence is extracted from a scientific knowledge base that contains medical information associated with coronavirus, organized in a knowledge graph created from a CORD-19 corpus. The information is accessed using Natural Language Question Answering and a set of evidences are extracted and their relevance measured. By combining both reliability and evidence information, the veracity of the news items can be predicted, improving both accuracy and F1 compared with using only reliability information. These results prove that the approach presented is very promising for the veracity detection task. |
| نوع الوثيقة: |
conference object |
| اللغة: |
English |
| تدمد: |
1613-0073 |
| Relation: |
https://ceur-ws.org/Vol-3525/; NLP-MisInfo 2023: SEPLN 2023 Workshop on NLP applied to Misinformation, held as part of SEPLN 2023: 39th International Conference of the Spanish Society for Natural Language Processing, September 26th, 2023, Jaen, Spain. CEUR Workshop Proceedings, Vol-3525; http://hdl.handle.net/10045/138198 |
| الاتاحة: |
http://hdl.handle.net/10045/138198 |
| Rights: |
© 2023 Copyright for this paper by its authors. Use permitted under Creative Commons License Attribution 4.0 International (CC BY 4.0). ; info:eu-repo/semantics/openAccess |
| رقم الانضمام: |
edsbas.D75DC594 |
| قاعدة البيانات: |
BASE |
Full Text Finder