COGAM: Measuring and Moderating Cognitive Load in Machine Learning Model Explanations

Abdul, Ashraf; Weth, Christian von der; Kankanhalli, Mohan; Lim, Brian Y.

doi:10.1145/3313831.3376615

Cited by 63 publications

(57 citation statements)

References 65 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A key challenge is how to construct and communicate the explanation in a manner that places reasonable cognitive load on the explanation consumers. To this end, techniques for presenting explanations visually, selectively, and progressively [54,62,69], and methods for incorporating the consideration of cognitive load into the explanation generation process [1] should be explored. Moreover, new approaches can be developed to increase people's ability in making full use of the information carried in AI explanations.…”

Section: Conclusion and Discussionmentioning

confidence: 99%

“…Researchers have proposed many tasks that AI explanations should assist people in. We reviewed these tasks and used two criteria to narrow down the scope of the tasks from which we extracted the desiderata of AI explanations-first, we focused on those tasks related to the ability of human decision makers in making decisions when they are assisted by an AI model; second, we required the tasks to be easily applicable to any kind of decision making context 1 . Based on tasks that satisfy these criteria, we summarized three desiderata of AI explanations as follows:…”

Section: Literature Reviewmentioning

confidence: 99%

See 1 more Smart Citation

Are Explanations Helpful? A Comparative Study of the Effects of Explanations in AI-Assisted Decision-Making

Wang

Yin

2021

26th International Conference on Intelligent User Interfaces

171

View full text Add to dashboard Cite

This paper contributes to the growing literature in empirical evaluation of explainable AI (XAI) methods by presenting a comparison on the effects of a set of established XAI methods in AI-assisted decision making. Specifically, based on our review of previous literature, we highlight three desirable properties that ideal AI explanations should satisfy-improve people's understanding of the AI model, help people recognize the model uncertainty, and support people's calibrated trust in the model. Through randomized controlled experiments, we evaluate whether four types of common model-agnostic explainable AI methods satisfy these properties on two types of decision making tasks where people perceive themselves as having different levels of domain expertise in (i.e., recidivism prediction and forest cover prediction). Our results show that the effects of AI explanations are largely different on decision making tasks where people have varying levels of domain expertise in, and many AI explanations do not satisfy any of the desirable properties for tasks that people have little domain expertise in. Further, for decision making tasks that people are more knowledgeable, feature contribution explanation is shown to satisfy more desiderata of AI explanations, while the explanation that is considered to resemble how human explain decisions (i.e., counterfactual explanation) does not seem to improve calibrated trust. We conclude by discussing the implications of our study for improving the design of XAI methods to better support human decision making. CCS CONCEPTS• Human-centered computing → Empirical studies in HCI; • Computing methodologies → Machine learning.

show abstract

Section: Conclusion and Discussionmentioning

confidence: 99%

Section: Literature Reviewmentioning

confidence: 99%

Are Explanations Helpful? A Comparative Study of the Effects of Explanations in AI-Assisted Decision-Making

Wang

Yin

2021

26th International Conference on Intelligent User Interfaces

171

View full text Add to dashboard Cite

show abstract

“…Yuan et al [ 169 ] trained a deep learning model to predict the scannability of webpage content. Cogam [ 170 ] tried to generate explanations for machine learning models by incorporating the desired cognitive load. Lai et al [ 171 ] created a technique to annotate visualizations according to text descriptions automatically.…”

Section: Classifying Hcml Researchmentioning

confidence: 99%

“…However, an attempt to build a predictable MRI classification network where a change of network’s parameters results in an expected outcome falls into interpretability research. There have been attempts [ 157 , 158 , 170 ] to develop novel interpretability algorithms using human studies to validate if those algorithms achieved the expected results. Isaac et al [ 61 ] studied what matters to the interpretability of an ML system using a human study.…”

Section: Classifying Hcml Researchmentioning

confidence: 99%

A Review of Recent Deep Learning Approaches in Human-Centered Machine Learning

Kaluarachchi

Reis

Nanayakkara

2021

Sensors

View full text Add to dashboard Cite

After Deep Learning (DL) regained popularity recently, the Artificial Intelligence (AI) or Machine Learning (ML) field is undergoing rapid growth concerning research and real-world application development. Deep Learning has generated complexities in algorithms, and researchers and users have raised concerns regarding the usability and adoptability of Deep Learning systems. These concerns, coupled with the increasing human-AI interactions, have created the emerging field that is Human-Centered Machine Learning (HCML). We present this review paper as an overview and analysis of existing work in HCML related to DL. Firstly, we collaborated with field domain experts to develop a working definition for HCML. Secondly, through a systematic literature review, we analyze and classify 162 publications that fall within HCML. Our classification is based on aspects including contribution type, application area, and focused human categories. Finally, we analyze the topology of the HCML landscape by identifying research gaps, highlighting conflicting interpretations, addressing current challenges, and presenting future HCML research opportunities.

show abstract

“…The need for understanding the inner workings of machine learning methods spurred the research field of eXplainable AI (XAI) to make such models (more) interpretable. However techniques so far are targeted primarily for experts and improving their usability for end users is an active area of research [1,2,41]. Regarding the generation of nudges, we formulate the following research questions:…”

Section: Core Tasksmentioning

confidence: 99%

Helping Users Tackle Algorithmic Threats on Social Media: A Multimedia Research Agenda

Weth

Abdul

Kankanhalli

2020

Proceedings of the 28th ACM International Conference on Multimedia

Self Cite

View full text Add to dashboard Cite

Participation on social media platforms has many benefits but also poses substantial threats. Users often face an unintended loss of privacy, are bombarded with mis-/disinformation, or are trapped in filter bubbles due to over-personalized content. These threats are further exacerbated by the rise of hidden AI-driven algorithms working behind the scenes to shape users' thoughts, attitudes, and behaviour. We investigate how multimedia researchers can help tackle these problems to level the playing field for social media users. We perform a comprehensive survey of algorithmic threats on social media and use it as a lens to set a challenging but important research agenda for effective and real-time user nudging. We further implement a conceptual prototype and evaluate it with experts to supplement our research agenda. This paper calls for solutions that combat the algorithmic threats on social media by utilizing machine learning and multimedia content analysis techniques but in a transparent manner and for the benefit of the users. CCS CONCEPTS • General and reference → Surveys and overviews; • Computing methodologies → Machine learning algorithms.

show abstract

COGAM: Measuring and Moderating Cognitive Load in Machine Learning Model Explanations

Cited by 63 publications

References 65 publications

Are Explanations Helpful? A Comparative Study of the Effects of Explanations in AI-Assisted Decision-Making

Are Explanations Helpful? A Comparative Study of the Effects of Explanations in AI-Assisted Decision-Making

A Review of Recent Deep Learning Approaches in Human-Centered Machine Learning

Helping Users Tackle Algorithmic Threats on Social Media: A Multimedia Research Agenda

Contact Info

Product

Resources

About