Effects of data ambiguity and cognitive biases on the interpretability of machine learning models in humanitarian decision making

David Paulus; Gerdien de Vries; Bartel van de Walle

Effects of data ambiguity and cognitive biases on the interpretability of machine learning models in humanitarian decision making

David Paulus, Gerdien de Vries, Bartel van de Walle

Research output: Chapter in Book/Conference proceedings/Edited volume › Conference contribution › Scientific › peer-review

60 Downloads (Pure)

Abstract

The effectiveness of machine learning algorithms depends on the quality and amount of data and the operationalization and interpretation by the human analyst. In humanitarian response, data is often lacking or overburdening, thus ambiguous, and the time-scarce, volatile, insecure environments of humanitarian activities are likely to inflict cognitive biases. This paper proposes to research the effects of data ambiguity and cognitive biases on the interpretability of machine learning algorithms in humanitarian decision making.

Original language	English
Title of host publication	AI for Social Good - AAAI Fall Symposium 2019
Publisher	Association for the Advancement of Artificial Intelligence (AAAI)
Publication status	Published - 2019
Event	AI for Social Good - AAAI Fall Symposium 2019 - Arlington, United States Duration: 7 Nov 2019 → 9 Nov 2019

Conference

Conference	AI for Social Good - AAAI Fall Symposium 2019
Country/Territory	United States
City	Arlington
Period	7/11/19 → 9/11/19

Access to Document

1911.04787Final published version, 194 KBLicence: CC BY-NC-SA

Cite this

@inproceedings{eb18e2ca57834b77884c283822b86cb0,

title = "Effects of data ambiguity and cognitive biases on the interpretability of machine learning models in humanitarian decision making",

abstract = "The effectiveness of machine learning algorithms depends on the quality and amount of data and the operationalization and interpretation by the human analyst. In humanitarian response, data is often lacking or overburdening, thus ambiguous, and the time-scarce, volatile, insecure environments of humanitarian activities are likely to inflict cognitive biases. This paper proposes to research the effects of data ambiguity and cognitive biases on the interpretability of machine learning algorithms in humanitarian decision making.",

author = "David Paulus and {de Vries}, Gerdien and {van de Walle}, Bartel",

year = "2019",

language = "English",

booktitle = "AI for Social Good - AAAI Fall Symposium 2019",

publisher = "Association for the Advancement of Artificial Intelligence (AAAI)",

address = "United States",

note = "AI for Social Good - AAAI Fall Symposium 2019 ; Conference date: 07-11-2019 Through 09-11-2019",

}

Paulus, D, de Vries, G & van de Walle, B 2019, Effects of data ambiguity and cognitive biases on the interpretability of machine learning models in humanitarian decision making. in AI for Social Good - AAAI Fall Symposium 2019. Association for the Advancement of Artificial Intelligence (AAAI), AI for Social Good - AAAI Fall Symposium 2019, Arlington, United States, 7/11/19.

Effects of data ambiguity and cognitive biases on the interpretability of machine learning models in humanitarian decision making. / Paulus, David; de Vries, Gerdien; van de Walle, Bartel.
AI for Social Good - AAAI Fall Symposium 2019. Association for the Advancement of Artificial Intelligence (AAAI), 2019.

Research output: Chapter in Book/Conference proceedings/Edited volume › Conference contribution › Scientific › peer-review

TY - GEN

T1 - Effects of data ambiguity and cognitive biases on the interpretability of machine learning models in humanitarian decision making

AU - Paulus, David

AU - de Vries, Gerdien

AU - van de Walle, Bartel

PY - 2019

Y1 - 2019

N2 - The effectiveness of machine learning algorithms depends on the quality and amount of data and the operationalization and interpretation by the human analyst. In humanitarian response, data is often lacking or overburdening, thus ambiguous, and the time-scarce, volatile, insecure environments of humanitarian activities are likely to inflict cognitive biases. This paper proposes to research the effects of data ambiguity and cognitive biases on the interpretability of machine learning algorithms in humanitarian decision making.

AB - The effectiveness of machine learning algorithms depends on the quality and amount of data and the operationalization and interpretation by the human analyst. In humanitarian response, data is often lacking or overburdening, thus ambiguous, and the time-scarce, volatile, insecure environments of humanitarian activities are likely to inflict cognitive biases. This paper proposes to research the effects of data ambiguity and cognitive biases on the interpretability of machine learning algorithms in humanitarian decision making.

UR - https://arxiv.org/abs/1911.04787

M3 - Conference contribution

BT - AI for Social Good - AAAI Fall Symposium 2019

PB - Association for the Advancement of Artificial Intelligence (AAAI)

T2 - AI for Social Good - AAAI Fall Symposium 2019

Y2 - 7 November 2019 through 9 November 2019

ER -

Effects of data ambiguity and cognitive biases on the interpretability of machine learning models in humanitarian decision making

Abstract

Conference

Access to Document

Other files and links

Fingerprint

Cite this