New App Uses Machine Learning to Detect Twitter Bots in Any Language - jacksondebefors

Researchers have developed a new application that uses Machine Learning (ML) to discover Twitter bots in any language.

The study presented at the fourth conference of Digital Humanistic discipline in the Nordic Countries shows that the application is able to detect auto-generated tweets independent of the language used.

"This enhances the quality of data and paints a more accurate picture of the reality," said Mikko Laitinen, Professor at the University of Eastern Finland.

In recent years, enlarged data from different social media applications have turned the web into a user-generated repository of information in the ever-multiplicative phone number of areas, said the researchers.

Twitter has become a popular source of data for investigations of a number of phenomena Because of the relatively tardily access to tweets and their meta-information.

Chitter Bots are non-grammatical category and automated accounts that Emily Price Post content to online social networks.

It has been estimated that around 5 to 10 per cent of all users are bots and these accounts generate near 20-25 per cent of all tweets posted.

For the study, the researchers analysed 15,000 tweets in Finnish, Swedish and English. European country and Scandinavian nation were mainly used for breeding, whereas tweets in English were used to evaluate the language independence of the application.

Reported to the researchers, the app is illuminate, making it possible to relegate immense amounts of data quickly and comparatively efficiently.

"Bots are relatively harmless, whereas trolls do harm as they spread fake news program and come up with made-upbound stories. This is wherefore there's a deman for increasingly advanced tools for ethnical media monitoring", said Laitinen.