Comparing User Interfaces for Customizing Multi-Objective Recommender Systems

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216208%3A11320%2F24%3A10494546" target="_blank" >RIV/00216208:11320/24:10494546 - isvavai.cz</a>

Výsledek na webu

<a href="https://ceur-ws.org/Vol-3815/paper2.pdf" target="_blank" >https://ceur-ws.org/Vol-3815/paper2.pdf</a>

DOI - Digital Object Identifier

—

Jazyk výsledku

angličtina

Název v původním jazyce

Comparing User Interfaces for Customizing Multi-Objective Recommender Systems

Popis výsledku v původním jazyce

The goal of Multi-Objective Recommender Systems (MORSs) is to adapt to the needs and preferences of the usersfrom different beyond-accuracy perspectives. When a MORS operates at the local level, it tailors its results tothe needs of each individual user. Recent studies have highlighted that, however, the self-declared propensityof the users towards the different objectives does not always match with the characteristics of the acceptedrecommendations. Therefore, in this study, we delve into different ways for users to express their preferencetoward multi-objective goals and observe whether they have some impact on declared propensities and overalluser satisfaction. In particular, we explore four different user interface (UI) designs and perform a user studyfocused on the interactions with both the UI and the recommendations. Results show that multiple UIs leadto similar results w.r.t. usage statistics, but users&apos; perceptions of these UIs often differ. These results highlightthe importance of examining MORSs from multiple perspectives to accommodate the users&apos; actual needs whenproducing recommendations. Study data and detailed results are available from https://osf.io/pbd54/.

Název v anglickém jazyce

Comparing User Interfaces for Customizing Multi-Objective Recommender Systems

Popis výsledku anglicky

The goal of Multi-Objective Recommender Systems (MORSs) is to adapt to the needs and preferences of the usersfrom different beyond-accuracy perspectives. When a MORS operates at the local level, it tailors its results tothe needs of each individual user. Recent studies have highlighted that, however, the self-declared propensityof the users towards the different objectives does not always match with the characteristics of the acceptedrecommendations. Therefore, in this study, we delve into different ways for users to express their preferencetoward multi-objective goals and observe whether they have some impact on declared propensities and overalluser satisfaction. In particular, we explore four different user interface (UI) designs and perform a user studyfocused on the interactions with both the UI and the recommendations. Results show that multiple UIs leadto similar results w.r.t. usage statistics, but users&apos; perceptions of these UIs often differ. These results highlightthe importance of examining MORSs from multiple perspectives to accommodate the users&apos; actual needs whenproducing recommendations. Study data and detailed results are available from https://osf.io/pbd54/.

Druh

O - Ostatní výsledky

CEP obor

—

OECD FORD obor

10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

Projekt

<a href="/cs/project/GA22-21696S" target="_blank" >GA22-21696S: Hluboké vizuální reprezentace nestrukturovaných dat</a><br>

Návaznosti

P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)

Rok uplatnění

2024

Kód důvěrnosti údajů

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