- Title
- Identification of fake news : a semantic driven technique for transfer domain
- Creator
- Ferdush, Jannatul; Kamruzzaman, Joarder; Karmakar, Gour; Gondal, Iqbal; Das, Raj
- Date
- 2023
- Type
- Text; Conference paper
- Identifier
- http://researchonline.federation.edu.au/vital/access/HandleResolver/1959.17/193468
- Identifier
- vital:18166
- Identifier
-
https://doi.org/10.1007/978-981-99-1645-0_47
- Identifier
- ISBN:1865-0929 (ISSN); 9789819916443 (ISBN)
- Abstract
- Fake news spreads quickly on online social media and adversely impacts political, social, religious, and economic stability. This necessitates an efficient fake news detector which is now feasible due to advances in natural language processing and artificial intelligence. However, existing fake news detection (FND) systems are built on tokenization, embedding, and structure-based feature extraction, and fail drastically in real life because of the difference in vocabulary and its distribution across various domains. This article evaluates the effectiveness of various categories of traditional features in cross-domain FND and proposes a new method. Our proposed method shows significant improvement over recent methods in the literature for cross-domain fake news detection in terms of widely used performance metrics. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
- Publisher
- Springer Science and Business Media Deutschland GmbH
- Relation
- 29th International Conference on Neural Information Processing, ICONIP 2022, Virtual, online, 22-26 November 2022, Communications in Computer and Information Science Vol. 1793 CCIS, p. 564-575
- Rights
- All metadata describing materials held in, or linked to, the repository is freely available under a CC0 licence
- Rights
- Copyright © 2023, The Author(s)
- Subject
- Bert; Fake news; Feature extraction; Tokenization; Transfer domain
- Reviewed
- Hits: 658
- Visitors: 536
- Downloads: 0
| Thumbnail | File | Description | Size | Format |
|---|