The use of belief function theory in recommendation based on a similarity diffusion

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F60076658%3A12510%2F19%3A43899879" target="_blank" >RIV/60076658:12510/19:43899879 - isvavai.cz</a>

Výsledek na webu

—

DOI - Digital Object Identifier

—

Jazyk výsledku

angličtina

Název v původním jazyce

The use of belief function theory in recommendation based on a similarity diffusion

Popis výsledku v původním jazyce

At present, recommendation systems are integral part of recommendation systems in e-business. In these systems, collaborative filtering technology is an important method for assessing user preferences by using user feedback data and is widely used. Diffusion-based recommendation based on diffusion phenomenon is an important method in collaborative filtering recommendation for processes that can be modelled by a bipartite network, e.g., processes which can represent behavior between users and e-shops. Diffusion-based recommendation algorithms calculate the similarities between users and make recommendations only regarding implicit feedback but neglect the benefits of explicit feedback which is formed by texts written by users during feedback process next to evaluation by certain amount of points (implicit feedback). These texts can be however a significant element in recommendation systems. This paper proposes a combined diffusion similarity model for the integration of explicit feedback and implicit feedback based on Dempster-Shafer theory. The experimental results show that the proposed solution gives good results compared to other algorithms.

Název v anglickém jazyce

The use of belief function theory in recommendation based on a similarity diffusion

Popis výsledku anglicky

At present, recommendation systems are integral part of recommendation systems in e-business. In these systems, collaborative filtering technology is an important method for assessing user preferences by using user feedback data and is widely used. Diffusion-based recommendation based on diffusion phenomenon is an important method in collaborative filtering recommendation for processes that can be modelled by a bipartite network, e.g., processes which can represent behavior between users and e-shops. Diffusion-based recommendation algorithms calculate the similarities between users and make recommendations only regarding implicit feedback but neglect the benefits of explicit feedback which is formed by texts written by users during feedback process next to evaluation by certain amount of points (implicit feedback). These texts can be however a significant element in recommendation systems. This paper proposes a combined diffusion similarity model for the integration of explicit feedback and implicit feedback based on Dempster-Shafer theory. The experimental results show that the proposed solution gives good results compared to other algorithms.

Druh

D - Stať ve sborníku

CEP obor

—

OECD FORD obor

50201 - Economic Theory

Projekt

—

Návaznosti

I - Institucionalni podpora na dlouhodoby koncepcni rozvoj vyzkumne organizace

Rok uplatnění

2019

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název statě ve sborníku

Conference Proceedings of 37th International Conference on Mathematical Methods in Economics 2019

ISBN

978-80-7394-760-6

ISSN

—

e-ISSN

—

Počet stran výsledku

6

Strana od-do

356-361

Název nakladatele

University of South Bohemia in České Budějovice, Faculty of Economics

Místo vydání

České Budějovice

Místo konání akce

České Budějovice

Datum konání akce

11. 9. 2019

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

—