The information spread through the Web influences politics, stock markets, public health, people's reputation and brands. For these reasons, it is crucial to filter out false information. In this paper, we compare different automatic approaches for fake news detection based on statistical text analysis on the vaccination fake news dataset provided by the Storyzy company. Our CNN works better for discrimination of the larger classes (fake vs trusted) while the gradient boosting decision tree with feature stacking approach obtained better results for satire detection. We contribute by showing that efficient satire detection can be achieved using merged embeddings and a specific model, at the cost of larger classes. We also contribute by merging redundant information on purpose in order to better predict satire news from fake news and trusted news.
The Smart City concept is a very recent one, which, nevertheless, has already implemented in several cities around the world (for example, Dubai, Moscow, Paris). The satisfactory results are encouraging more and more cities to experiment with this concept; given that the normal city of the future will be the smart city, regardless of its size and location. We have noticed during November 2018 Sétif start-ups fair, in Algeria, the strong desire of local authorities and investors to shift to a smart management of their city (Elmoudjahid, 2019). In this article we will study the transition of an ordinary city into a smart city, whatever its socio-economic environment. The concept of a smart city will be presented, in the first instance, then we will examine various examples of cities in view of transitioning to smart city, so as to propose an application at low-cost based essentially on the collaboration of the inhabitants (which we will call "smart Citizen-centred city"), this way we will pass over the lack of developed systems benefitting from open data, sensor networks, etc. Because of this, we have selected the theme "intelligent transport", presenting a simple transport application in the Wilaya of Sétif, which will depend on the connected people.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.