Leveraging chatbots to improve self-guided learning through conversational quizzes

Over 2.5 billion people have at least one messaging app installed. In 2015, messaging apps have surpassed social networks. In this context, chat-bots or bots, are a new kind of applications that leverage these messaging ecosystem advantages. They need no installation effort, they are ubiquitous and they reside in students' most valuable gadgets, their smartphones. Armed with AI techniques, machine learning algorithms and natural language processing features, bots could be an ideal teacher assistant, able to answer and propose personalized questions to the students, anywhere, anytime. But before that near future arrives, there is a need for designing a new breed of mobile learning applications that take advantage of the ubiquity of these bots for everyday use. In this article we present the design and implementation of a Telegram bot, @dawebot, for training students in any subject using multiple choice question quizzes. We also present an evaluation of @dawebot in a 15 week long subject with 23 students of Computer Science, documenting their opinion about this bot in particular and the usage of bots in the elearning area in general. Students think that using bots for practicing tests is a good idea (89%), that using testing bots could help them to engage more in the subject (72%) and and will definitely recommend to use such testing bots also in other subjects of their university grade (94%).