Data Science Mentoring Support using Neural Networks

The increased demand from people to learn Data Science, together with the arrival of the Coronavirus pandemic and the increase in home-office activities, teaching institutions in this area, has to expand online assistance systems to students. Since this assistance is not always restricted to a particular schedule, it produces instability in the daily tasks that teachers have to perform. To avoid this, this study implements a closed-domain Chatbot for Data Science that uses as a Question Answering System and works as an assistant to teachers in specific questions that students may have. In addition, it allows the students to check their knowledge in any related topic by the automatic generation of questions according to the chosen topic. The System also has an automatic correction process that compares the response given by the student with the correct one. Such features were implemented using the latest Deep Learning models oriented to Natural Language Processing (NLP), such as Transformers architectures. Although the response time is relatively long in some cases, it generated good answers as well as questions. In future works, the authors propose to optimize the system in terms of speed and quality of results. To this end, the reduction in the number of steps is required by the system, as well as finding more efficient solutions according to the research progress in NLP.