Enhanced Collaborative Filtering for Personalized E-Government Recommendation

Abstract

The problems with the information overload of e-government websites have been a big obstacle for users to make decisions. One promising approach to solve this problem is to deploy an intelligent recommendation system on e-government platforms. Collaborative filtering (CF) has shown its superiority by characterizing both items and users by the latent features inferred from the user–item interaction matrix. A fundamental challenge is to enhance the expression of the user or/and item embedding latent features from the implicit feedback. This problem negatively affected the performance of the recommendation system in e-government. In this paper, we firstly propose to learn positive items’ latent features by leveraging both the negative item information and the original embedding features. We present the negative items mixed collaborative filtering (NMCF) method to enhance the CF-based recommender system. Such mixing information is beneficial for extending the expressiveness of the latent features. Comprehensive experimentation on a real-world e-government dataset showed that our approach improved the performance significantly compared with the state-of-the-art baseline algorithms.

Learning-Based Matched Representation System for Job Recommendation

“…The latter case does require jobs to be categorized, such that they can serve as discrete items in the rating matrix. For simplicity, we will refer to the entries in the rating matrix as ratings, irrespective of the exact type of behavioral feedback (e.g., [14,15]).…”

New Trends in Artificial Intelligence for Recommender Systems and Collaborative Filtering

“…In the same spirit of democratizing access to online resources for the population, in [9], the authors propose Negative-items Mixed Collaborative Filtering (NMCF), a method to improve accessibility to e-government resources. By emphasizing the learning of positive items' latent features, the system is able to outperform the state-of-the-art algorithms on a real e-government dataset.…”

Sistema de Recomendação do Portal gov.br

“…As ondas de transformação digital que tem informatizado serviços públicos em Governos de todo o mundo cria um cenário de sobrecarga informacional para cidadãos e empresas, que, diante de processos de caráter naturalmente burocráticos, enfrentam dificuldades práticas no acesso e realização desses serviços [Sun et al, 2021]. Sistemas de recomendação podem, nesse cenário, se tornar ferramentas efetivas que ajudam a disponibilizar aos usuários os serviços públicos de que realmente necessitam.…”

“…[Ayachi et al, 2016] também propõem um arcabouço conceitual para recomendação de serviços governamentais, usando como exemplo o portal de serviços do Governo de Quebec 1 , em que serviços personalizados são ofertados aos cidadãos autenticados com base em diferentes fontes de dados. Mais recentemente, [Sun et al, 2021] apresentaram uma nova técnica de recomendação de serviços de governo (distrito de Wuhou -Chengdu, China) que leva em consideração as interações negativas dos usuários em filtragem colaborativa.…”