English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

The introduction of social media technologies has fostered the diffusion of misinformation. The speed and format with which misinformation is created and the pace at which it diffuses poses new challenges for practitioners and policy-makers alike. In this paper, we show that a simple network using characterlevel inputs given to a CNN is well suited to detect misinformation. We believe the effectiveness of such a simple architecture is because the CNN can exploit morphological differences between misinformation and other types of information. To test our intuition, we compare the character CNN inputs to different others like word embeddings. We find that the network using character CNN outperforms models that do not take into consideration morphologies and matches the performance of others that consider it to some extent. We argue that the nature of misinformation, the low availability of training data and the multidisciplinary background of individuals implementing misinformation detection algorithms make simple, easy-to-implement networks such as the character CNN good alternatives to other models.

Towards easy-to-implement misinformation automatic detection for online social media