CS2125 Paper Review Form - Winter 2019

Reviewer: Mohammad Rashidujjaman Rifat

Paper Title: Why did my car just do that? Explaining semi-autonomous driving actions to improve driver understanding, trust, and performance

Author(s):

1) Is the paper technically correct?
 [ ] Yes
 [✓] Mostly (minor flaws, but mostly solid)
 [ ] No

2) Originality
 [ ] Very good (very novel, trailblazing work)
 [✓] Good 
 [ ] Marginal (very incremental)
 [ ] Poor (little or nothing that is new)

3) Technical Depth
 [ ] Very good (comparable to best conference papers)
 [✓] Good (comparable to typical conference papers)
 [ ] Marginal depth
 [ ] Little or no depth

4) Impact/Significance
 [ ] Very significant
 [✓] Significant
 [ ] Marginal significance.
 [ ] Little or no significance.

5) Presentation
 [ ] Very well written
 [✓] Generally well written
 [ ] Readable
 [ ] Needs considerable work
 [ ] Unacceptably bad

6) Overall Rating
 [ ] Strong accept (award quality)
 [ ] Accept (high quality - would argue for acceptance)
 [✓] Weak Accept (borderline, but lean towards acceptance)
 [ ] Weak Reject (not sure why this paper was published)


7) Summary of the paper's main contribution and rationale
   for your recommendation. (1-2 paragraphs)

This paper presents its findings from a controlled study to show the effectiveness of voice messages to drivers in order to measure the safety of autonomous vehicles. The result has a recommendation for designers that providing a proper reason for autonomous actions increases safety.

I appreciate that the paper mentions the limitations of the participants’ selection and method of the study. I also highlight two points here: 1) even though there are not any other methodological option for the type of question being asked here, I expected a ‘toned down’ claim in its findings. 2) I would prefer an activity-centered approach rather than the user-centered approach for this question. 

Autonomous driving is not about car learning to the environment, rather the environment also learning about the car. There are recommendations in research that argue that this mutual learning is socially constructed. As a result, while the simulation is a convincing option for conducting such research given the high ‘risk’ associated with this, it is not the best option for the type of claim the paper is making. In the wild, the emotional experience of a driver is supposed to be different from a simulation environment. 

My second concern here is the choice of ‘user-centered’ approach. While the user is historically the main actor in a driving environment, the cognition is distributed among other actors (such as the autonomous tools, environment, etc.) in a semi-automated environment. The choice of the ‘user-centered’ approach could have a more convincing reflection on user emotion.

Finally, I am a bit surprised the way the paper is making a strong claim without having given proper attention to the appropriate literature, such as emotion or cognitive behavior. In one point, the paper cited a ’well-known’ fact, which I consider very risky, especially when the paper is dealing with a domain of high risk. 

8) List 1-3 strengths of the paper.  (1-2 sentences each,
identified as S1, S2, S3.)

S1. The paper is an initiation of bringing the question of emotions in autonomous driving.
S2. Regarding the number of participants and time of the experiment, the study is rigorous for the simulation study.
S3. Even though the limitation in the method, it helps the designer with a guideline that they could extend for other design choices as well to include emotional factors.


9) List 1-3 weaknesses of the paper (1-2 sentences each,
identified as W1, W2, W3.)

W1. The paper does not have a diverse set of participants.
W2. It does not well explain its statistical analysis in the paper.
W3. The user-centred approach might not be the best choice for this paper.