User modeling and user adapted interaction

  title={User modeling and user adapted interaction},
  author={Peter Brusilovsky},

Framework para sistema tutor adaptativo ao raciocínio crítico em contabilidade - STARCC

Souza, M. C. (2018). Framework for Adaptive Tutoring System for Critical Thinking in Accounting STARCC. Tese de Doutorado, Faculdade de Economia, Administração e Contabilidade, Universidade de São

Comparing Objective and Subjective Measures of Usability in a Human-Robot Dialogue System

A human-robot dialogue system that enables a robot to work together with a human user to build wooden construction toys is presented and a method based on the PARADISE evaluation framework is used to derive a performance function from data.

Funktionen zur Orientierung in einem virtuellen, kollaborativen Wörterbuch (ENFORUM) - theoretische Grundlagen und Implementierung

In dieser Arbeit werden nach der grundlegenden Erörterung kognitiver Aspekte and der Ableitung of Erkenntnissen aus der Orientierung and Navigation in der Realwelt, mögliche Ausprägungen von Orientieringssmitteln in einer Taxonomie gegenübergestellt and eingeordnet.

Streaming Session-Based Recommendation: When Graph Neural Networks meet the Neighborhood

This work reproduces the results of the mentioned GNN method and shows that simpler methods are able to outperform this complex state-of-the-art neural method on two datasets, and points to continued methodological issues in the academic community, e.g., in terms of the choice of baselines and reproducibility.

Modelling Users with Item Metadata for Explainable and Interactive Recommendation

This work proposes a linear collaborative filtering recommendation model that builds user profiles within the domain of item metadata, which is arguably the most interpretable domain for end users and which seamlessly supports interactive recommendation.

Comprehensive Empirical Evaluation of Deep Learning Approaches for Session-Based Recommendation in E-Commerce

This study suggests that using the hybrid models of different approaches combined with baseline algorithms could lead to substantial results in session-based recommendations based on dataset characteristics, and finds that these models suffer more in the case of long sessions when there exists drift in user interests.


This project aims to develop and design a Machine Learning model which can be integrated into an Android application to help recommend music for the app user.

Balancing Multi-level Interactions for Session-based Recommendation

This paper proposes a novel method, namely Intra-and Inter-session Interaction-aware Graph-enhanced Network, to take inter-session item-level interactions into account, and demonstrates that this method outperforms other state-of-the-art methods.

On the Importance of News Content Representation in Hybrid Neural Session-based Recommender Systems

This work analyzes the importance of considering content information in a hybrid neural news recommender system, contrasts content-aware and content-agnostic techniques and also explores the effects of using different content encodings.

A general graph-based framework for top-N recommendation using content, temporal and trust information

GraFC2T2 is a general graph-based framework to easily combine various kinds of information for top-N recommendation that encodes content-based features, temporal and trust information into a graph model and uses personalized PageRank on this graph to perform recommendation.