Recommender systems in libraries: iniciatives and proposal of a theoretical hybrid model
Recommender systems are software tools that have as a goal the generation of an estimate of usefulness of items for a certain user, as well as analyzing interactions between users and items. They are divided between classic recommender systems, which use only one type of filtering technique, and hyb...
Na minha lista:
Principais autores: | , , |
---|---|
Formato: | Online |
Idioma: | por |
Publicado em: |
Portal de Periódicos Eletrônicos da UFRN
|
Endereço do item: | https://periodicos.ufrn.br/bibliocanto/article/view/32504 |
Tags: |
Adicionar Tag
Sem tags, seja o primeiro a adicionar uma tag!
|
id |
oai:periodicos.ufrn.br:article-32504 |
---|---|
record_format |
ojs |
institution |
Periódicos UFRN |
collection |
Portal de Pediódicos Eletrônicos da UFRN |
language |
por |
format |
Online |
author |
de Moura Vieira, Bruna Beatriz Passos, Ketry Gorete Farias dos Salm, Vanessa Marie |
spellingShingle |
de Moura Vieira, Bruna Beatriz Passos, Ketry Gorete Farias dos Salm, Vanessa Marie Recommender systems in libraries: iniciatives and proposal of a theoretical hybrid model |
author_facet |
de Moura Vieira, Bruna Beatriz Passos, Ketry Gorete Farias dos Salm, Vanessa Marie |
author_sort |
de Moura Vieira, Bruna Beatriz |
title |
Recommender systems in libraries: iniciatives and proposal of a theoretical hybrid model |
title_short |
Recommender systems in libraries: iniciatives and proposal of a theoretical hybrid model |
title_full |
Recommender systems in libraries: iniciatives and proposal of a theoretical hybrid model |
title_fullStr |
Recommender systems in libraries: iniciatives and proposal of a theoretical hybrid model |
title_full_unstemmed |
Recommender systems in libraries: iniciatives and proposal of a theoretical hybrid model |
title_sort |
recommender systems in libraries: iniciatives and proposal of a theoretical hybrid model |
description |
Recommender systems are software tools that have as a goal the generation of an estimate of usefulness of items for a certain user, as well as analyzing interactions between users and items. They are divided between classic recommender systems, which use only one type of filtering technique, and hybrid, which use two or more types of filtering techniques allied to a hybrid recommendation technique. The goal of this paper is to introduce the recommender systems used in libraries and propose a theoretical hybrid recommender system model, adapted to the context and reality of libraries. For this purpose, a qualitative, exploratory, descriptive and bibliographic approach was used to explore the theme of recommender system and their use in libraries as an answer to users’ growing informational demand. A conclusion was made that most of the recommender system initiatives that are in use in libraries today are based on the classic recommender model and use only two types of filtering techniques – by content and collaborative. Therefore it is suggested that future research needs to try to comprehend the reason why the classic recommender model is used more, in detriment to hybrid recommender system, and that a bigger focus on the development and application of hybrid recommender system for libraries is needed, given its advantages when compared to the classic model. It is also suggested that further studies on other types of filtering techniques be made, given their potential to generate new recommendation strategies in libraries. |
publisher |
Portal de Periódicos Eletrônicos da UFRN |
publishDate |
2023 |
url |
https://periodicos.ufrn.br/bibliocanto/article/view/32504 |
work_keys_str_mv |
AT demouravieirabrunabeatriz recommendersystemsinlibrariesiniciativesandproposalofatheoreticalhybridmodel AT passosketrygoretefariasdos recommendersystemsinlibrariesiniciativesandproposalofatheoreticalhybridmodel AT salmvanessamarie recommendersystemsinlibrariesiniciativesandproposalofatheoreticalhybridmodel AT demouravieirabrunabeatriz sistemasderecomendacaoembibliotecasiniciativasepropostadeummodeloteoricohibrido AT passosketrygoretefariasdos sistemasderecomendacaoembibliotecasiniciativasepropostadeummodeloteoricohibrido AT salmvanessamarie sistemasderecomendacaoembibliotecasiniciativasepropostadeummodeloteoricohibrido |
_version_ |
1774866662192840704 |
spelling |
oai:periodicos.ufrn.br:article-325042023-08-10T18:53:40Z Recommender systems in libraries: iniciatives and proposal of a theoretical hybrid model Sistemas de recomendação em bibliotecas: iniciativas e proposta de um modelo teórico híbrido de Moura Vieira, Bruna Beatriz Passos, Ketry Gorete Farias dos Salm, Vanessa Marie Recommender systems Hybrid recommender systems Content filtering Collaborative filtering Information retrieval Sistemas de recomendação Sistemas de recomendação híbridos Filtragem por conteúdo Filtragem colaborativa Recuperação de informação Recommender systems are software tools that have as a goal the generation of an estimate of usefulness of items for a certain user, as well as analyzing interactions between users and items. They are divided between classic recommender systems, which use only one type of filtering technique, and hybrid, which use two or more types of filtering techniques allied to a hybrid recommendation technique. The goal of this paper is to introduce the recommender systems used in libraries and propose a theoretical hybrid recommender system model, adapted to the context and reality of libraries. For this purpose, a qualitative, exploratory, descriptive and bibliographic approach was used to explore the theme of recommender system and their use in libraries as an answer to users’ growing informational demand. A conclusion was made that most of the recommender system initiatives that are in use in libraries today are based on the classic recommender model and use only two types of filtering techniques – by content and collaborative. Therefore it is suggested that future research needs to try to comprehend the reason why the classic recommender model is used more, in detriment to hybrid recommender system, and that a bigger focus on the development and application of hybrid recommender system for libraries is needed, given its advantages when compared to the classic model. It is also suggested that further studies on other types of filtering techniques be made, given their potential to generate new recommendation strategies in libraries. Sistemas de recomendação são ferramentas de software que têm como objetivo gerar uma estimativa da utilidade que um item pode ter para um usuário, bem como analisar interações entre usuários e itens. São divididos entre sistemas de recomendação clássicos, que utilizam apenas um tipo de técnica de filtragem, e híbridos, que utilizam dois ou mais tipos de técnicas de filtragem aliados a uma técnica de recomendação híbrida. O objetivo deste artigo consiste em apresentar os sistemas de recomendação em bibliotecas e propor um modelo de recomendação híbrido teórico, adaptado ao contexto das bibliotecas. Para isto, foi utilizada uma abordagem qualitativa, exploratória, descritiva e bibliográfica para explorar o tema de sistemas de recomendação e sua aplicação em bibliotecas como uma resposta às crescentes demandas informacionais dos usuários. Foi percebido que a maioria das iniciativas de sistemas de recomendação em uso atualmente são do modelo clássico, e utilizam apenas dois tipos de filtragem – por conteúdo e colaborativa. Portanto, é necessário que pesquisas futuras tentem entender o motivo por trás da adoção dos sistemas de recomendação do modelo clássico em detrimento dos sistemas de recomendação híbridos, e que é necessário um maior enfoque no desenvolvimento e aplicação de sistemas de recomendação híbridos em bibliotecas, dado às suas vantagens em relação ao modelo clássico. Também é sugerida a realização de estudos sobre as outras diferentes técnicas de filtragem, pelo fato de possuírem o potencial de gerar novos tipos de estratégias de recomendação em bibliotecas. Portal de Periódicos Eletrônicos da UFRN 2023-08-10 info:eu-repo/semantics/article info:eu-repo/semantics/publishedVersion Texto application/pdf https://periodicos.ufrn.br/bibliocanto/article/view/32504 BiblioCanto; v. 9 n. 1 (2023); 43 - 66 2447-7842 10.21680/2427-7842.2023v9n1 por https://periodicos.ufrn.br/bibliocanto/article/view/32504/17295 Copyright (c) 2023 BiblioCanto https://creativecommons.org/licenses/by-nc-sa/4.0 |