How Do Visual Explanations Foster End Users' Appropriate Trust in Machine Learning?

Mapping Intimacies ◽

10.31219/osf.io/s9q8t ◽

2021 ◽

Author(s):

Fumeng Yang

Keyword(s):

Machine Learning ◽

Performance Feedback ◽

User Study ◽

Visual Representation ◽

Spatial Layout ◽

End Users ◽

Classification Algorithm ◽

Learning Classifier ◽

Spatial Layouts ◽

And Performance

We investigated the effects of example-based explanations for a machine learning classifier on end users' appropriate trust. We explored the effects of spatial layout and visual representation in an in-person user study with 33 participants. We measured participants' appropriate trust in the classifier, quantified the effects of different spatial layouts and visual representations, and observed changes in users' trust over time. The results show that each explanation improved users' trust in the classifier, and the combination of explanation, human, and classification algorithm yielded much better decisions than the human and classification algorithm separately. Yet these visual explanations lead to different levels of trust and may cause inappropriate trust if an explanation is difficult to understand. Visual representation and performance feedback strongly affect users' trust, and spatial layout shows a moderate effect. Our results do not support that individual differences (e.g., propensity to trust) affect users' trust in the classifier. This work advances the state-of-the-art in trust-able machine learning and informs the design and appropriate use of automated systems.

Download Full-text

I Like Myself, I Really Do (at Least Right Now)

European Journal of Psychological Assessment ◽

10.1027/1015-5759/a000501 ◽

2020 ◽

Vol 36 (1) ◽

pp. 196-206 ◽

Cited By ~ 1

Author(s):

Almut Rudolph ◽

Michela Schröder-Abé ◽

Astrid Schütz

Keyword(s):

Construct Validity ◽

Performance Feedback ◽

Repeated Measures ◽

Temporal Stability ◽

Social Feedback ◽

Student Sample ◽

Empirically Supported ◽

Good Internal Consistency ◽

And Performance ◽

Induced Changes

Abstract. In five studies, we evaluated the psychometric properties of a revised German version of the State Self-Esteem Scale (SSES; Heatherton & Polivy, 1991 ). In Study 1, the results of a confirmatory factor analysis on the original scale revealed poor model fit and poor construct validity in a student sample that resembled those in the literature; thus, a revised 15-item version was developed (i.e., the SSES-R) and thoroughly validated. Study 2 showed a valid three-factor structure (Performance, Social, and Appearance) and good internal consistency of the SSES-R. Correlations between subscales of trait and state SE empirically supported the scale’s construct validity. Temporal stability and intrapersonal sensitivity of the scale to naturally occurring events were investigated in Study 3. Intrapersonal sensitivity of the scale to experimentally induced changes in state SE was uncovered in Study 4 via social feedback (acceptance vs. rejection) and performance feedback (positive vs. negative). In Study 5, the scale’s interpersonal sensitivity was confirmed by comparing depressed and healthy individuals. Finally, the usefulness of the SSES-R was demonstrated by assessing SE instability as calculated from repeated measures of state SE.

Download Full-text

The Influence of Cognitive and Affective Reactions to Feedback on Subsequent Goals

European Psychologist ◽

10.1027/1016-9040/a000011 ◽

2010 ◽

Vol 15 (2) ◽

pp. 121-131 ◽

Cited By ~ 20

Author(s):

Remus Ilies ◽

Timothy A. Judge ◽

David T. Wagner

Keyword(s):

Performance Feedback ◽

Business School ◽

Structural Equation ◽

Emotional Reactions ◽

Equation Model ◽

Proposed Model ◽

And Performance ◽

Dispositional Measure ◽

The Relationship ◽

Reactions To Feedback

This paper focuses on explaining how individuals set goals on multiple performance episodes, in the context of performance feedback comparing their performance on each episode with their respective goal. The proposed model was tested through a longitudinal study of 493 university students’ actual goals and performance on business school exams. Results of a structural equation model supported the proposed conceptual model in which self-efficacy and emotional reactions to feedback mediate the relationship between feedback and subsequent goals. In addition, as expected, participants’ standing on a dispositional measure of behavioral inhibition influenced the strength of their emotional reactions to negative feedback.

Download Full-text

Financial incentives and performance feedback to physicians may not increase cancer screening for Medicaid enrollees

PsycEXTRA Dataset ◽

10.1037/e556992006-014 ◽

1999 ◽

Keyword(s):

Cancer Screening ◽

Performance Feedback ◽

Financial Incentives ◽

And Performance

Download Full-text

Toward Generating a new Video Education Lectures Dataset and Performance Comparison with Various Machine Learning Algorithms

10.36295/asro.2019.221230 ◽

2019 ◽

Vol 22 (12) ◽

pp. 279-298

Author(s):

M Maysaa H. Abdulameer ◽

Mahmood Z. Abdullah

Keyword(s):

Machine Learning ◽

Learning Algorithms ◽

Performance Comparison ◽

Machine Learning Algorithms ◽

And Performance ◽

Video Education

Download Full-text

Development and Performance Assessment of Novel Machine Learning Models to Predict Postoperative Pneumonia After Liver Transplantation

SSRN Electronic Journal ◽

10.2139/ssrn.3667645 ◽

2020 ◽

Author(s):

Chaojin Chen ◽

Dong Yang ◽

Shilong Gao ◽

Yihan Zhang ◽

Liubing Chen ◽

...

Keyword(s):

Machine Learning ◽

Liver Transplantation ◽

Performance Assessment ◽

Postoperative Pneumonia ◽

Learning Models ◽

And Performance ◽

Machine Learning Models

Download Full-text

Check-In/Check Out: Electronic Adaptation and Individual Progress Monitoring

Journal of Special Education Technology ◽

10.1177/0162643421994107 ◽

2021 ◽

pp. 016264342199410

Author(s):

Jordan Yassine ◽

Leigh Ann Tipton-Fisler

Keyword(s):

Performance Feedback ◽

Differential Reinforcement ◽

Research Evidence ◽

Progress Monitoring ◽

Middle School Student ◽

Teacher Ratings ◽

Ease Of Use ◽

Electronic Application ◽

Long Line ◽

And Performance

Check-in/Check-Out (CICO) has a long line of research evidence demonstrating its effectiveness in increasing prosocial behavior. The current paper demonstrated an electronic application of CICO utilizing Google Sheets® with teacher feedback. Google Sheets® offers an inexpensive, collaborative, and remote method for tracking behaviors. In the first study, 2,322 teacher ratings (from 38 teachers) were compared between traditional paper CICO forms or electronic Google Sheets®. Results found that teacher ratings were significantly more complete with the use of the electronic forms. In the second study, an electronic CICO form was used for progress monitoring and performance feedback with a middle school student. Through the form we were able to successfully track our participant’s behavior change in response to CICO with the combination of feedback and a differential reinforcement intervention. Social validity showed that overall teacher ratings were high with respect to ease of use, usefulness, cost-effectiveness, and convenience of the electronic Google Sheets®.

Download Full-text

Paper2Wire – A Case Study of User-Centred Development of Machine Learning Tools for UX Designers

i-com ◽

10.1515/icom-2021-0002 ◽

2021 ◽

Vol 20 (1) ◽

pp. 19-32

Author(s):

Daniel Buschek ◽

Charlotte Anlauff ◽

Florian Lachner

Keyword(s):

Machine Learning ◽

Development Process ◽

User Study ◽

Concept Development ◽

Lessons Learned ◽

Design Tool ◽

Learning Tools ◽

Interface Elements ◽

Industry Partner

Abstract This paper reflects on a case study of a user-centred concept development process for a Machine Learning (ML) based design tool, conducted at an industry partner. The resulting concept uses ML to match graphical user interface elements in sketches on paper to their digital counterparts to create consistent wireframes. A user study (N=20) with a working prototype shows that this concept is preferred by designers, compared to the previous manual procedure. Reflecting on our process and findings we discuss lessons learned for developing ML tools that respect practitioners’ needs and practices.

Download Full-text

Location Detection Method of Detector in Pipeline Using VMD Algorithm and Machine Learning Classifier

Electronics ◽

10.3390/electronics10121436 ◽

2021 ◽

Vol 10 (12) ◽

pp. 1436

Author(s):

Tuoru Li ◽

Senxiang Lu ◽

Enjie Xu

Keyword(s):

Machine Learning ◽

Magnetic Flux ◽

Magnetic Flux Leakage ◽

Intrinsic Mode Functions ◽

Detection Range ◽

Vibration Signals ◽

Feature Vectors ◽

Learning Classifier ◽

Mode Decomposition ◽

Flux Leakage

The internal detector in a pipeline needs to use the ground marker to record the elapsed time for accurate positioning. Most existing ground markers use the magnetic flux leakage testing principle to detect whether the internal detector passes. However, this paper uses the method of detecting vibration signals to track and locate the internal detector. The Variational Mode Decomposition (VMD) algorithm is used to extract features, which solves the defect of large noise and many disturbances of vibration signals. In this way, the detection range is expanded, and some non-magnetic flux leakage internal detectors can also be located. Firstly, the extracted vibration signals are denoised by the VMD algorithm, then kurtosis value and power value are extracted from the intrinsic mode functions (IMFs) to form feature vectors, and finally the feature vectors are input into random forest and Multilayer Perceptron (MLP) for classification. Experimental research shows that the method designed in this paper, which combines VMD with a machine learning classifier, can effectively use vibration signals to locate the internal detector and has the characteristics of high accuracy and good adaptability.

Download Full-text