Educational Bots: Learning through Chatbots

According to the market consulting firm TechNavio, during 2020-2024, the e-learning market will grow by 12% year-on-year in the United States. This figure demonstrates the strength of new technologies for the always necessary training, with a plus: cost savings in personnel and materials that should always be valued, not only in the education sector but also in companies in other sectors that offer training to their employees and can thus obtain high quality with less budget.

What is a chatbot?

A chatbot is a computer program that acts as an assistant that simulates and processes human conversations, communicating with users through text messages. This technology allows the user to have a conversation in which the bot solves their doubts without a person answering.

What is a chatbot used for

A chatbot maintains a conversation between humans and software through a web page or a messaging service (Telegram, WhatsApp, Facebook Messenger…). The software answers questions without needing a person to write or send those answers at any time or day.

While in marketing processes (one of the fields with more utilities), chatbots can improve customer service or streamline purchases; educational chatbots solve administrative doubts and help students find information for an academic paper or to take an exam. And, in addition, as with other conversational software, they relieve staff (teachers, administrative staff, etc.) of specific tasks, which in the long run means a reduction in costs for institutions. We will expand on some of these utilities later.

There is something that educational chatbots share, regardless of their purpose: they meet the needs of a new generation looking for greater flexibility to perform their tasks or procedures without fixed schedules. Likewise, they serve a more flexible type of learning, in which students receive reminders of past or future lessons (with text, videos, images, or audio) and even simulations of an exam.

How it works

For an educational chatbot to work, it is necessary to design a fluid conversation that responds to the users’ needs and that they do not feel they are wasting their time. Questions should have a few answer options (“yes,” “no,” particular words…) to prevent the ‘dialogue’ from being diluted.

Chatbots are powered by AI, automatic rules, natural language processing (NPL), and Machine Learning to process data and give answers according to the questions. They also have the advantage of being available 24/7 to resolve those user queries. Algorithms allow chatbots to learn, intuiting the habits and understanding the tastes and preferences of users.

Learning chatbots for higher education

Higher education institutions and students benefit from chatbots. Institutions can use them on their websites to provide information about their courses. Chatbots can also help students submit assignments in the run-up to online exams and help with administrative procedures such as enrollment. In addition, digital conversations would gather opinions on the quality of classes, the operation of digital platforms, or the staff’s attention, thus improving the quality of teaching.

Furthermore, chatbots in higher education (and at other educational stages) ‘collaborate’ with students when doing university work. For example, if added to school libraries, software bots would instantly deliver hard-to-find digital resources or help students learn how to access information. Similarly, they can be used to program alerts and notifications of new materials available.

Higher education is a time of much academic work, where texts’ quality and originality are significant considerations. Educational chatbots trained with thousands of readers and spelling or grammar rules also help students to assess readability or uniqueness.

Learning chatbots for early childhood education

For younger children, bots are a stimulus to want to learn and make lessons more entertaining.

As in higher education, chatbots could ‘deliver’ an exam to students in early childhood education. If the chatbot is a lovely, friendly figure, the experience of taking one of these tests is more relaxed.

At the same time, these pleasant figures can make the learning of certain complex concepts more digestible: from home, with their automatic responses, they have fun teaching while at the same time providing support materials to complement the face-to-face class.

At the same time, teachers receive information on the use of these chatbots and check the evolution of their students. They can even learn how to integrate them into the classroom: games, quizzes…

How to use chatbot for education

We have developed an educational bot using bot framework V4 with QnA, LUIS*, and Knowledge mining techniques to recover information about different courses.

The Educational bot is able to obtain the courses that one user is enrolled in because he has inferred all user metadata from the student account. We used QnA Maker to build our knowledge base about the courses. In this case, the user is asking for the current government in the Netherlands.

• When the student needs to know more about Mark Rutte, we are using LUIS (Cognitive Services) that is able to detect the “search” intent with the query “Mark Rutte”.
• Previously, we have indexed all the content related to political sciences using Azure Cognitive Search with OCR and computer vision skills. In this example, the bot calls the Azure Search API and order the results by score (TF-IDF) detecting the documents and images where the query “Mark Rutte” appears.
• In the third element of the carrousel appears and image of Mark Rutte. We used computer vision (cognitive services) during the indexing process, being able to obtain the caption of the images and the bounding boxes where the different objects can appear. In this case the persons and objected detected are Mark Rutte and tie.
• The student selects the second document. As we can see in the view of the document the query “Mark Rutte” appears selected in this one.

* Language Understanding (LUIS) is a cloud-based API service that applies customized machine learning intelligence to a user’s natural language conversation or text to predict overall meaning and extract relevant and detailed information.

In short, educational chatbots can be customized for each stage and student’s learning and working rhythms, whether in early childhood or higher education.

At this time of expansion of e-learning, chatbots are a great ally to achieve that quality with a more affordable budget. We can help you get on board this educational revolution if you want.