Research

Chatbots provide users with the ability to interact in 'conversation' mode. To do so, chatbots use visual instant messaging codes and prompt users to express themselves freely, like they would with an advisor. But chatbots do not hide their automated nature; they often explicitly introduce themselves as 'virtual assistants' or 'bots' (robots) and work alongside technological tools, interaction with which is mostly through the use of buttons, menus or written queries.
How do Internet users react to this paradoxical proposal of 'speaking' to robots? Do they address chatbots the same way they would a seller or do they ask it questions using keywords, in the same way they would with a search engine? Do exchanges remain purely linguistic or are they supplemented with other forms of screen interaction, like buttons, menus and guided tours? Lastly, what do these interactions between humans and robots look like? The study presented in this article provides some answers thanks to an analysis of interaction logs from the Djingo Pro bot, used on the Orange portal for business customers and companies since 2017.