2022
Autores
Duarte, AJ; Malheiro, B; Silva, MF; Ferreira, PD; Guedes, PB;
Publicação
Handbook of Research on Improving Engineering Education with the European Project Semester - Advances in Higher Education and Professional Development
Abstract
2022
Autores
Nylund, R; Malheiro, B;
Publicação
Handbook of Research on Improving Engineering Education with the European Project Semester - Advances in Higher Education and Professional Development
Abstract
2022
Autores
Budzinska, G; Hansen, J; Malheiro, B; Fuentes-Durá, P;
Publicação
Handbook of Research on Improving Engineering Education with the European Project Semester - Advances in Higher Education and Professional Development
Abstract
2022
Autores
Malheiro, B; Fuentes-Durá, P;
Publicação
Advances in Higher Education and Professional Development
Abstract
2022
Autores
Veloso, B; Leal, F; Malheiro, B;
Publicação
Lecture Notes in Networks and Systems
Abstract
Human interaction with intelligent systems, services, and devices generates large volumes of user-related data. This multi-source information can be used to build richer user profiles and improve personalization. Our goal is to combine multi-source data to create user profiles by assigning dynamic individual weights. This paper describes a multi-source user profiling methodology and illustrates its application with a film recommendation system. The contemplated data sources include (i) personal history, (ii) explicit preferences (ratings), and (iii) social activities (likes, comments, or shares). The MovieLens dataset was selected and adapted to assess our approach by comparing the standard and the proposed methodologies. In the standard approach, we calculate the best global weights to apply to the different profile sources and generate all user profiles accordingly. In the proposed approach, we determine, for each user, individual weights for the different profile sources. The approach proved to be an efficient solution to a complex problem by continuously updating the individual data source weights and improving the accuracy of the generated personalised multimedia recommendations. © 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
2022
Autores
Leal, F; Garcia-Mendez, S; Malheiro, B; Burguillo, JC;
Publicação
INFORMATION SYSTEMS AND TECHNOLOGIES, WORLDCIST 2022, VOL 1
Abstract
Collaborative filtering is a widely used recommendation technique, which often relies on rating information shared by users, i.e., crowdsourced data. These filters rely on predictive algorithms, such as, memory or model based predictors, to build direct or latent user and item profiles from crowdsourced data. To predict unknown ratings, memory-based approaches rely on the similarity between users or items, whereas model-based mechanisms explore user and item latent profiles. However, many of these filters are opaque by design, leaving users with unexplained recommendations. To overcome this drawback, this paper introduces Explug, a local model-agnostic plug-in that works alongside stream-based collaborative filters to reorder and explain recommendations. The explanations are based on incremental user Trust & Reputation profiling and co-rater relationships. Experiments performed with crowdsourced data from TripAdvisor show that Explug explains and improves the quality of stream-based collaborative filter recommendations.
The access to the final selection minute is only available to applicants.
Please check the confirmation e-mail of your application to obtain the access code.