Use of collaborative filters to recommend information in a chatbot system: Tecnologico de Monterrey Admissions Chatbot

Abstract

One of the main objectives of companies is to provide customers with a good customer service experience, so that customers are satisfied. Therefore, with the emergence of natural language processing techniques, companies are looking for automated solutions that provide quality services to customers. This is possible thanks to chatbots, which are helpful because they are permanently available and respond immediately. Additionally, with the use of recommendation systems, suggestions can be provided to the user, allowing a better conversation flow and reducing the response time. This research main objective is the development of a recommendation system for a conversational chatbot of online customer service of the ITESM admission department to suggest the following question to the user. In this project, a framework for a hybrid recommendation system is proposed, considering the user connection variables in each conversation, as user features, and applying an (Latent Dirichlet Allocation) LDA in the set of options provided by the chatbot to capture the context of the conversation as item features. In state-of-the-art, a problem similar to ours was found; this consists of recommending the following question that a user of the StackExchange platform can answer, using user characteristics and question labels to create different models. The results found that using a LightFM model, a maximum precision of 0.750 was obtained. In contrast, with our data set, a maximum precision of 0.787 is obtained, indicating that this model works well in our problem.