Physiological Indicators for User Trust in Machine Learning with Influence Enhanced Fact-Checking - Machine Learning and Knowledge Extraction Accéder directement au contenu
Communication Dans Un Congrès Année : 2019

Physiological Indicators for User Trust in Machine Learning with Influence Enhanced Fact-Checking

Jianlong Zhou
  • Fonction : Auteur
  • PersonId : 1066995
Huaiwen Hu
  • Fonction : Auteur
  • PersonId : 1066996
Zhidong Li
  • Fonction : Auteur
  • PersonId : 1067000
Kun Yu
  • Fonction : Auteur
  • PersonId : 1067001
Fang Chen
  • Fonction : Auteur
  • PersonId : 1067003

Résumé

Trustworthy Machine Learning (ML) is one of significant challenges of “black-box” ML for its wide impact on practical applications. This paper investigates the effects of presentation of influence of training data points on machine learning predictions to boost user trust. A framework of fact-checking for boosting user trust is proposed in a predictive decision making scenario to allow users to interactively check the training data points with different influences on the prediction by using parallel coordinates based visualization. This work also investigates the feasibility of physiological signals such as Galvanic Skin Response (GSR) and Blood Volume Pulse (BVP) as indicators for user trust in predictive decision making. A user study found that the presentation of influences of training data points significantly increases the user trust in predictions, but only for training data points with higher influence values under the high model performance condition, where users can justify their actions with more similar facts to the testing data point. The physiological signal analysis showed that GSR and BVP features correlate to user trust under different influence and model performance conditions. These findings suggest that physiological indicators can be integrated into the user interface of AI applications to automatically communicate user trust variations in predictive decision making.
Fichier principal
Vignette du fichier
485369_1_En_7_Chapter.pdf (797.37 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-02520035 , version 1 (26-03-2020)

Licence

Paternité

Identifiants

Citer

Jianlong Zhou, Huaiwen Hu, Zhidong Li, Kun Yu, Fang Chen. Physiological Indicators for User Trust in Machine Learning with Influence Enhanced Fact-Checking. 3rd International Cross-Domain Conference for Machine Learning and Knowledge Extraction (CD-MAKE), Aug 2019, Canterbury, United Kingdom. pp.94-113, ⟨10.1007/978-3-030-29726-8_7⟩. ⟨hal-02520035⟩
45 Consultations
124 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More