2020
DOI: 10.1007/s13278-020-00696-x
|View full text |Cite
|
Sign up to set email alerts
|

Deep learning for misinformation detection on online social networks: a survey and new perspectives

Abstract: Recently, the use of social networks such as Facebook, Twitter, and Sina Weibo has become an inseparable part of our daily lives. It is considered as a convenient platform for users to share personal messages, pictures, and videos. However, while people enjoy social networks, many deceptive activities such as fake news or rumors can mislead users into believing misinformation. Besides, spreading the massive amount of misinformation in social networks has become a global risk. Therefore, misinformation detectio… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1
1

Citation Types

4
96
0
1

Year Published

2020
2020
2024
2024

Publication Types

Select...
6
2
1
1

Relationship

1
9

Authors

Journals

citations
Cited by 196 publications
(101 citation statements)
references
References 144 publications
4
96
0
1
Order By: Relevance
“…Training interventions could entail fact-checking strategies and nudging to attend to diagnostic features (e.g., news source credibility; Pehlivanoglu et al, under review) and/or to consider news veracity during news consumption. Again, natural-language and imagebased machine-learning (deep learning) feature extraction, as already in place for fake image detection (e.g., deepfake; Islam, Liu, Wang, & Xu, 2020;Westerlund, 2019) could be particularly informative for designing effective decision-supportive intervention. Additionally, "inoculation" against false information (Van Bavel et al, 2020) could be achieved by ensuring that older adults are equipped with solid base knowledge before they encounter fake news that they may be particularly susceptible to.…”
Section: Analytical Reasoning Enhanced Non-covid Fake News Detection mentioning
confidence: 99%
“…Training interventions could entail fact-checking strategies and nudging to attend to diagnostic features (e.g., news source credibility; Pehlivanoglu et al, under review) and/or to consider news veracity during news consumption. Again, natural-language and imagebased machine-learning (deep learning) feature extraction, as already in place for fake image detection (e.g., deepfake; Islam, Liu, Wang, & Xu, 2020;Westerlund, 2019) could be particularly informative for designing effective decision-supportive intervention. Additionally, "inoculation" against false information (Van Bavel et al, 2020) could be achieved by ensuring that older adults are equipped with solid base knowledge before they encounter fake news that they may be particularly susceptible to.…”
Section: Analytical Reasoning Enhanced Non-covid Fake News Detection mentioning
confidence: 99%
“…(Islam et al , 2020) present a state-of-the-art systematic review of the existing problem solutions and validation of Minimal Infectious Dose (MID) (Fake news detection) in online social networks based on various deep learning techniques. To identify the latest and future trends of MID research, they analyze the key strengths and limitations of the various existing techniques and describe state-of-the-art deep learning as an emerging technique on massive social network data.…”
Section: Related Workmentioning
confidence: 99%
“…It can rather be seen as an integral approach to make decision, combining visualization with DL models, human factors and data analysis [144]. Both visualization and DL helps to get deeper insights from multivariate sectors and enhance further development of human-centered tools using advanced technologies [51]. Nowadays, DL models are most useful for decision making as well as providing as many accurate predictions as possible [42].…”
Section: Why Deep Learning For Visual Analyticsmentioning
confidence: 99%