The goal of our work is to investigate best practices for integrating machine learning into human decision making. There are many different ways to incorporate machine learning in the decision making process. The above image illustrates a spectrum between full human agency, where humans make decisions entirely on their own, and full automation, where machines make decisions without human intervention. The amount of information from machine learning models gradually increases along the spectrum. Note that assistance is in the form of offering explanations and predictions. For more details on our work, please check out our papers here.
This website allows you to detect deceptive reviews with different levels of machine assistance along the spectrum. By using this website, you agree to share your responses for research purposes.
The task here is to detect deceptive reviews. By deceptive reviews, we mean reviews written by people who have never been to the hotel. In other words, these reviews describe imagined experience.
The demos for FAT* 2019 and CHI 2020 have been merged into a single website. To play around with settings from FAT* 2019 interface, proceed by selecting Predicting, and use the default explanation type. To play around with settings from CHI 2020 interface, proceed by selecting Training. You will then have options to choose from for the training and prediction phase.
If you are just here for fun, click on any button to begin the task!
The above shows a spectrum between full human agency and full automation. Various modes of machine assistance exist in the spectrum. Here the spectrum shows different modes of machine assistance in the training phase. Please select a training condition and prediction condition to begin.
The above shows a spectrum between full human agency and full automation. Various modes of machine assistance exist in the spectrum. Here the spectrum shows different modes of machine assistance in the prediction phase. Please select a prediction condition to begin.