User Preferences for Hybrid Explanations

Kouki, Pigi; Schaffer, James; Pujara, Jay; O’Donovan, John; Getoor, Lise

doi:10.1145/3109859.3109915

Cited by 58 publications

(28 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Explanations can also be used to justify or describe [80]. While early recommender system explanation approaches provided a uniform explanation style for single-source collaborative filtering [30], more recent work explores how to derive explanations for recommender systems based on 'hybrid' multiple sources [36] and matrix factorisation [61]. However, a reported need for explanation may not always correspond to differences in behaviour or performance; in a study of news recommender systems, end-users expressed a desire for explanations, but the number of news items they opened did not change when provided with reasons for their recommendations [70].…”

Section: Interpreting Intelligent Systemsmentioning

confidence: 99%

“…> Your age (---) > Driving experience (---) > Level of adherence to speed limit (-) > Number of trips taken at night (++) > Miles per month (+) > 29% of female drivers qualified for the cheapest tier. > 31% of drivers in your age group [30][31][32][33][34][35][36][37][38][39] qualified for the cheapest tier. > 35% of drivers with 17 years of experience qualified for the cheapest tier.…”

Section: Within-subjects Studymentioning

confidence: 99%

See 1 more Smart Citation

'It's Reducing a Human Being to a Percentage'

Binns

Kleek

Veale

et al. 2018

Proceedings of the 2018 CHI Conference on Human Factors in Computing Systems

272

View full text Add to dashboard Cite

Data-driven decision-making consequential to individuals raises important questions of accountability and justice. Indeed, European law provides individuals limited rights to 'meaningful information about the logic' behind significant, autonomous decisions such as loan approvals, insurance quotes, and CV filtering. We undertake three experimental studies examining people's perceptions of justice in algorithmic decision-making under different scenarios and explanation styles. Dimensions of justice previously observed in response to human decision-making appear similarly engaged in response to algorithmic decisions. Qualitative analysis identified several concerns and heuristics involved in justice perceptions including arbitrariness, generalisation, and (in)dignity. Quantitative analysis indicates that explanation styles primarily matter to justice perceptions only when subjects are exposed to multiple different styles-under repeated exposure of one style, scenario effects obscure any explanation effects. Our results suggests there may be no 'best' approach to explaining algorithmic decisions, and that reflection on their automated nature both implicates and mitigates justice dimensions.

show abstract

Section: Interpreting Intelligent Systemsmentioning

confidence: 99%

Section: Within-subjects Studymentioning

confidence: 99%

'It's Reducing a Human Being to a Percentage'

Binns

Kleek

Veale

et al. 2018

Proceedings of the 2018 CHI Conference on Human Factors in Computing Systems

272

View full text Add to dashboard Cite

show abstract

“…The visualization of complex hybrid explanations has also been investigated in Ref. [18]. In this study, we investigate hybrids of context style with other explanation styles.…”

Section: Explanation Of Recommendationmentioning

confidence: 99%

Context Style Explanation for Recommender Systems

Sato

Nagatani

Sonoda

et al. 2019

Journal of Information Processing

View full text Add to dashboard Cite

Recommender systems support users by helping them choose items, and explanations for the recommendations further enhance such support. Previous explanation styles were based on information about users and items, such as the demographics of users and contents of items. Contexts, such as "usage scenarios" and "accompanying persons," have not been used for explanations, although they influence user's choice of items. In this paper, we propose a context style explanation method, presenting contexts suitable for consuming the recommended items. The expected impacts of context style explanations are as follows: 1) persuasiveness: recognition of a suitable context for usage motivates users to consume items, and 2) usefulness: envisioning a context helps users to make the right choices because the values of items depend on contexts. We evaluate the persuasiveness and usefulness of the context-style explanation by a crowdsourcing-based user study in a restaurant recommendation setting. The context style explanation is compared to the demographic and content style explanations. We also combine the context style and other explanation styles, confirming that hybrid styles improve the persuasiveness and usefulness of the explanation. Further, we investigate the personal preferences for explanation styles and reveal how gender and age relate to such preferences. The contributions of this paper are: the proposal of the novel context style explanation method, the demonstration of the persuasiveness and usefulness of the proposed method by a user study, and the findings of gender-and age-dependence of explanation style preferences.

show abstract

“…Com caráter experimental, o trabalho de Kouki et al (2017) criou 13 maquetes de interface diferentes para um mesmo cenário de recomendação. Dos 13 modelos, um não possuía nenhum explicação da recomendação, sete explicavam de maneira textual, uma era baseada em regras e quatro explicavam de maneira visual.…”

Section: Experimentos Sobre a Visualização De Sistemas De Recomendaçãounclassified

Quais as Melhores Maneiras de Apresentar as Recomendações para os Usuários? Um Mapeamento Sistemático da Literatura

Borba

Gasparini

2019

iSys

View full text Add to dashboard Cite

Os sistemas de recomendação utilizam de informações do usuário para gerar um conjunto de itens personalizados como sugestão e são aplicados em contextos onde existe sobrecarga de conteúdo disponível ao usuário. A maneira como a visualização dessas recomendações é realizada passou a ser foco de estudos recentes conforme a necessidade de melhorar a experiência do usuário com os sistemas de recomendação. Este trabalho apresenta um mapeamento sistemático da literatura visando identificar as melhores maneiras de apresentar as recomendações para os usuários. Um total de 434 artigos foram identificados, dos quais 27 foram selecionados para análise. Os resultados apontam uma tendência para as interfaces autoexplicativas e interativas.

show abstract

User Preferences for Hybrid Explanations

Cited by 58 publications

References 24 publications

'It's Reducing a Human Being to a Percentage'

'It's Reducing a Human Being to a Percentage'

Context Style Explanation for Recommender Systems

Quais as Melhores Maneiras de Apresentar as Recomendações para os Usuários? Um Mapeamento Sistemático da Literatura

Contact Info

Product

Resources

About