A Framework for Adaptive Recommendation in Online Environments

Rogério Xavier de Azambuja; A. Jorge Morais; Vítor Filipe

doi:10.47852/bonviewAIA52025020

Authors

Rogério Xavier de Azambuja Instituto Federal de Educação, Ciência e Tecnologia do Rio Grande do Sul (IFRS), Brazil, Department of Science and Technology, Universidade Aberta (UAb) and School of Science and Technology, Universidade de Trás-os-Montes e Alto Douro (UTAD), Portugal
A. Jorge Morais Department of Science and Technology, Universidade Aberta (UAb) and Instituto de Engenharia de Sistemas e Computadores, Tecnologia e Ciência (INESC TEC), Portugal
Vítor Filipe School of Science and Technology, Universidade de Trás-os-Montes e Alto Douro (UTAD) and Instituto de Engenharia de Sistemas e Computadores, Tecnologia e Ciência (INESC TEC), Portugal

DOI:

https://doi.org/10.47852/bonviewAIA52025020

Keywords:

recommender systems, dynamic taste profile, deep neural networks, transformers, attention model

Abstract

Recent advancements in deep learning and large language models (LLMs) have led to the development of innovative technologies that enhance recommender systems. Different heuristics, architectures, and techniques for filtering information have been proposed to obtain successful computational models for the recommendation problem; however, several issues must be addressed in online environments. This research focuses on a specific type of recommendation, which combines sequential recommendation with session-based recommendation. The goal is to solve the complex next-item recommendation problem in Web applications, using the wine domain as a case study. This paper describes a framework developed to provide adaptive recommendations by rethinking the initial data modeling to better understand users' dynamic taste profiles. Three main contributions are presented: (a) a novel dataset of wines called X-Wines; (b) an updated recommendation model named X-Model4Rec – eXtensible Model for Recommendation, which utilizes attention and transformer mechanisms central to LLMs; and (c) a collaborative Web platform designed to support adaptive wine recommendations for users in an online environment. The results indicate that the proposed framework can enhance recommendations in online environments and encourage further scientific exploration of this topic.

Received: 15 December 2024 | Revised: 12 June 2025 | Accepted: 30 June 2025

Conflicts of Interest

The authors declare that they have no conflicts of interest to this work.

Data Availability Statement

The data that support the findings of this study are openly available in X-Wines Research Project at https://sites.google.com/farroupilha.ifrs.edu.br/xwines.

Author Contribution Statement

Rogério Xavier de Azambuja: Conceptualization, Methodology, Software, Validation, Formal analysis, Investigation, Resources, Data curation, Writing – original draft, Writing – review & editing, Visualization, and Project administration. A. Jorge Morais: Conceptualization, Methodology, Validation, Formal analysis, Data curation, Writing – review & editing, Visualization, Supervision, and Project administration. Vítor Filipe: Conceptualization, Methodology, Validation, Formal analysis, Data curation, Writing – review & editing, Visualization, and Project administration.