Fake News Detection Using Deep Learning
1
조회
0
다운로드
4
인용
0
참고문헌
키워드
초록
With the wide spread of Social Network Services (SNS), fake news—which is a way of disguising false informationas legitimate media—has become a big social issue. This paper proposes a deep learning architecture fordetecting fake news that is written in Korean. Previous works proposed appropriate fake news detection modelsfor English, but Korean has two issues that cannot apply existing models: Korean can be expressed in shortersentences than English even with the same meaning; therefore, it is difficult to operate a deep neural networkbecause of the feature scarcity for deep learning. Difficulty in semantic analysis due to morpheme ambiguity. We worked to resolve these issues by implementing a system using various convolutional neural network-baseddeep learning architectures and “Fasttext” which is a word-embedding model learned by syllable unit. Aftertraining and testing its implementation, we could achieve meaningful accuracy for classification of the bodyand context discrepancies, but the accuracy was low for classification of the headline and body discrepancies.
Abstract
With the wide spread of Social Network Services (SNS), fake news—which is a way of disguising false informationas legitimate media—has become a big social issue. This paper proposes a deep learning architecture fordetecting fake news that is written in Korean. Previous works proposed appropriate fake news detection modelsfor English, but Korean has two issues that cannot apply existing models: Korean can be expressed in shortersentences than English even with the same meaning; therefore, it is difficult to operate a deep neural networkbecause of the feature scarcity for deep learning. Difficulty in semantic analysis due to morpheme ambiguity. We worked to resolve these issues by implementing a system using various convolutional neural network-baseddeep learning architectures and “Fasttext” which is a word-embedding model learned by syllable unit. Aftertraining and testing its implementation, we could achieve meaningful accuracy for classification of the bodyand context discrepancies, but the accuracy was low for classification of the headline and body discrepancies.
참고문헌 (19)
- Y. Yoon, "Survey of fake news detection technology", IITP Weekly Trend, 1816, pp.12~23 (2017)
- "This analysis shows how viral fake election news stories outperformed real news On Facebook" (2016)[URL]
- "News with integrity"[URL]
- S. Kwon, "Prominent features of rumor propagation in online social media", Proceedings of 2013 IEEE 13th International Conference on Data Mining, pp.1103~1108 (2013)
- "Talos targets disinformation with fake news challenge victory" (2017)[URL]
- "Team Athene on the fake news challenge" (2017)[URL]
- "Enriching word vectors with subword information" (2016)[URL]
- "Convolutional neural networks for sentence classification" (2014)[URL]
- "Efficient estimation of word representations in vector space" (2013)[URL]
- 김우주, "Word2vec을 활용한 문서의 의미 확장 검색방법", 한국콘텐츠학회 논문지, 16(10), pp.687~692 (2016), 한국콘텐츠학회[DOI]
- T. Mikolov, "Distributed representations of words and phrases and their compositionality", Advances in Neural Information Processing Systems, 26, pp.3111~3119 (2013)
- "Attentive pooling networks" (2016)[URL]
- K. Xu, "Show, attend and tell: neural image caption generation with visual attention", Proceedings of the 32nd International Conference on Machine Learning, pp.2048~2057 (2015)
- D. Bahdanau, "Neural machine translation by jointly learning to align and translate", Proceedings of the 3rd International Conference on Learning Representations (ICLR) (2015)
- M. Maimaiti, "Bidirectional long short-term memory network with a conditional random field layer for Uyghur part-of-speech tagging", Information, 8(4) (2017)
- A. Graves, "Speech recognition with deep recurrent neural networks", Proceedings of 2013 IEEE International Conference on Acoustics, Speech and Signal Processing, pp.6645~6649 (2013)
- W. T. Yih, "Semantic parsing for single-relation question answering", Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers), pp.643~648 (2014)
- K. A. Spackman, "Signal detection theory: Valuable tools for evaluating inductive learning", Proceedings of the 6th International Workshop on Machine Learning, pp.160~163 (1989)
- "Twitter sentiment analysis using combined LSTM-CNN models" (2018)[URL]