Generating Questions on the Conversational Recommender System using Semantic Reasoning and Singular Value Decomposition
Robby Dwi Harntanto, Z. K. A. Baizal, Agung Toto Wibowo · 2022
In some previous research, Conversational Recommender System (CRS) based on product functional requirements was developed. Product functional requirements are requirements from product usability point of view. For example, users want smartphones for browsing and playing games. So that users who do not understand the technical features of the product, can more easily express their needs. In this CRS, questions are generated using semantic reasoning. However, the functional requirements asked to the user are chosen from the candidate nodes randomly. The candidate nodes are a set of functional requirements questions that the user potentially likes. Thus, users will get questions about functional requirements that do not match their preferences. Thus, the system will give repeated questions and make the system inefficient. In this study, we overcome this problem by proposing a learning mechanism using Singular Value Decomposition (SVD) to generate questions. By using this SVD, we hope to shorten the number of interactions between the user and the system. The results of the evaluation show that SVD has accuracy and running time to generate questions that are more stable.