Explaining content-based recommendations with topic models

Gustavo Padilha Polleti; Fabio Gagliardi Cozman

doi:10.1109/BRACIS.2019.00143

Explaining content-based recommendations with topic models

Gustavo Padilha Polleti, Fabio Gagliardi Cozman

Resultado de la investigación: Contribución a una conferencia › Artículo de conferencia

Resumen

© 2019 IEEE. Recommendation systems play a key role in current online commerce enterprises. Despite their success, they usually behave like black-boxes from the user perspective, typically failing to produce high quality human-computer interactions; interpretability is thus a major concern for the next generation of recommendation systems. In this paper we propose a model-agnostic method based on topic models that generates explanations for content-based recommendation systems.

Idioma original	Inglés estadounidense
Páginas	800-805
Número de páginas	6
DOI	https://doi.org/10.1109/BRACIS.2019.00143
Estado	Publicada - 1 oct 2019
Publicado de forma externa	Sí
Evento	Proceedings - 2019 Brazilian Conference on Intelligent Systems, BRACIS 2019 - Duración: 1 oct 2019 → …

Conferencia

Conferencia	Proceedings - 2019 Brazilian Conference on Intelligent Systems, BRACIS 2019
Período	1/10/19 → …

Acceder al documento

10.1109/BRACIS.2019.00143

Otros archivos y enlaces

Huella Profundice en los temas de investigación de 'Explaining content-based recommendations with topic models'. En conjunto forman una huella única.

Citar esto

@conference{0f777dc08e354a939e5e04b87f8dc14f,

title = "Explaining content-based recommendations with topic models",

abstract = "{\textcopyright} 2019 IEEE. Recommendation systems play a key role in current online commerce enterprises. Despite their success, they usually behave like black-boxes from the user perspective, typically failing to produce high quality human-computer interactions; interpretability is thus a major concern for the next generation of recommendation systems. In this paper we propose a model-agnostic method based on topic models that generates explanations for content-based recommendation systems.",

author = "{Padilha Polleti}, Gustavo and {Gagliardi Cozman}, Fabio",

year = "2019",

month = oct,

day = "1",

doi = "10.1109/BRACIS.2019.00143",

language = "American English",

pages = "800--805",

note = "Proceedings - 2019 Brazilian Conference on Intelligent Systems, BRACIS 2019 ; Conference date: 01-10-2019",

}

TY - CONF

T1 - Explaining content-based recommendations with topic models

AU - Padilha Polleti, Gustavo

AU - Gagliardi Cozman, Fabio

PY - 2019/10/1

Y1 - 2019/10/1

N2 - © 2019 IEEE. Recommendation systems play a key role in current online commerce enterprises. Despite their success, they usually behave like black-boxes from the user perspective, typically failing to produce high quality human-computer interactions; interpretability is thus a major concern for the next generation of recommendation systems. In this paper we propose a model-agnostic method based on topic models that generates explanations for content-based recommendation systems.

AB - © 2019 IEEE. Recommendation systems play a key role in current online commerce enterprises. Despite their success, they usually behave like black-boxes from the user perspective, typically failing to produce high quality human-computer interactions; interpretability is thus a major concern for the next generation of recommendation systems. In this paper we propose a model-agnostic method based on topic models that generates explanations for content-based recommendation systems.

UR - https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=85077076334&origin=inward

UR - https://www.scopus.com/inward/citedby.uri?partnerID=HzOxMe3b&scp=85077076334&origin=inward

U2 - 10.1109/BRACIS.2019.00143

DO - 10.1109/BRACIS.2019.00143

M3 - Conference Paper

SP - 800

EP - 805

T2 - Proceedings - 2019 Brazilian Conference on Intelligent Systems, BRACIS 2019

Y2 - 1 October 2019

ER -