Toward Harnessing User Feedback For Machine Learning

Stumpf, Simone; Rajaram, Vidya; Li, Lida; Burnett, M. Dallas; Dietterich, Thomas G.; Sullivan, Erin; Drummond, Russell; Herlocker, Jonathan L.

doi:10.21236/ada471484

Cited by 32 publications

(34 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Work on how people perceive explanations of ML systems is a growing area [4,20,25,32] which aims to inform the choices and design of explanations for particular systems or tasks. Recent work calls for taxonomic organizations of explanations to enable design guidelines [25].…”

Section: Explanation Of Machine Learningmentioning

confidence: 99%

Explaining models

Dodge

Liao²,

Zhang³

et al. 2019

Proceedings of the 24th International Conference on Intelligent User Interfaces

201

View full text Add to dashboard Cite

Ensuring fairness of machine learning systems is a human-in-theloop process. It relies on developers, users, and the general public to identify fairness problems and make improvements. To facilitate the process we need effective, unbiased, and user-friendly explanations that people can confidently rely on. Towards that end, we conducted an empirical study with four types of programmatically generated explanations to understand how they impact people's fairness judgments of ML systems. With an experiment involving more than 160 Mechanical Turk workers, we show that: 1) Certain explanations are considered inherently less fair, while others can enhance people's confidence in the fairness of the algorithm; 2) Different fairness problems-such as model-wide fairness issues versus casespecific fairness discrepancies-may be more effectively exposed through different styles of explanation; 3) Individual differences, including prior positions and judgment criteria of algorithmic fairness, impact how people react to different styles of explanation. We conclude with a discussion on providing personalized and adaptive explanations to support fairness judgments of ML systems. CCS CONCEPTS• Human-centered computing → Empirical studies in HCI.

show abstract

Section: Explanation Of Machine Learningmentioning

confidence: 99%

Explaining models

Dodge

Liao²,

Zhang³

et al. 2019

Proceedings of the 24th International Conference on Intelligent User Interfaces

201

View full text Add to dashboard Cite

show abstract

“…This is not to say that users will blindly trust ML systems. But, prior work suggests that evaluations of a system’s reliability are based on subjective perceptions of its output and the perceived “soundness” of its reasoning rather than on statistical evidence of its accuracy[43]. The implication for system designers is that users’ willingness to trust and ultimately adopt ML systems is dependent on perceived “legibility,” meaning, the degree to which system behavior seems to “make sense” to its users, regardless of its mechanism or statistical accuracy [19].…”

Section: Discussionmentioning

confidence: 99%

"It's hard to argue with a computer"

Hirsch

Soma

Merced

et al. 2018

Proceedings of the 2018 Designing Interactive Systems Conference

View full text Add to dashboard Cite

We present CORE-MI, an automated evaluation and assessment system that provides feedback to mental health counselors on the quality of their care. CORE-MI is the first system of its kind for psychotherapy, and an early example of applied machine-learning in a human service context. In this paper, we describe the CORE-MI system and report on a qualitative evaluation with 21 counselors and trainees. We discuss the applicability of CORE-MI to clinical practice and explore user perceptions of surveillance, workplace misuse, and notions of objectivity, and system reliability that may apply to automated evaluation systems generally.

show abstract

“…For example, [25] found strong user preference for, and trust in, models that exhibit “sound” (i.e., human comprehensible) reasoning and “clear communication” about decision making. These models were also perceived as more accurate, which did not necessarily correlate with actual or statistical accuracy.…”

Section: Design Issuesmentioning

confidence: 99%

Designing Contestability

Hirsch

Merced

Narayanan

et al. 2017

Proceedings of the 2017 Conference on Designing Interactive Systems

View full text Add to dashboard Cite

We describe the design of an automated assessment and training tool for psychotherapists to illustrate challenges with creating interactive machine learning (ML) systems, particularly in contexts where human life, livelihood, and wellbeing are at stake. We explore how existing theories of interaction design and machine learning apply to the psychotherapy context, and identify “contestability” as a new principle for designing systems that evaluate human behavior. Finally, we offer several strategies for making ML systems more accountable to human actors.

show abstract

Toward Harnessing User Feedback For Machine Learning

Cited by 32 publications

References 7 publications

Explaining models

Explaining models

"It's hard to argue with a computer"

Designing Contestability

Contact Info

Product

Resources

About