Vision Zero Reporting
Learning and science
journalism analysis
SHOW HN2021
Legend
Vision Zero Reporting
Identify car crash editorial anti-patterns using NLP
visionzeroreporting.com#traffic crash reporting#news bias detection#vision zero#editorial framing#nlp
How HN took it
17 positive, 20 neutral or asking, 4 mixed, 24 critical, out of 65 comments about the project. Thread score -0.08.
Idea: 12 for, 22 againstExecution: 3 for, 1 againstDesign: 1 for, 1 against
The thread, comment by comment
Each row is a top-level comment and its replies, in HN's order. Select a cell to open that comment on HN.
positive neutral or mixed critical about another commenter or something else the maker
What HN said
What people liked
Interesting NLP application in a focused domain.
From 2 comments
I like it. I like that it tags segments of text as opposed to the document as a whole. Since it is confined to a domain and has a well-chosen problem it seems to be highly…
PaulHoule on HNHi HN, I built "Vision Zero Reporting" (https://visionzeroreporting.com), a tool to detect editorial anti-patterns in local news coverage of car crashes. Maybe you've noticed…
chiefofgxbxl on HN
Useful insight that reframing accidents as crashes matters.
From 1 comment
Here’s why the reframing matters: Accidents are “oops” that are to accepted as fact of life. The no reason to change the system. Accidents happen. Crashes are not accidents. They…
markstos on HN
Objections
Shifts blame onto drivers instead of addressing systemic road design.
From 2 comments
this seems to me like it's designed to shift the blame from unilaterally on the VRU (bad), to unilaterally on the driver (also bad). You pay lip service to systemic problems, but…
beaconstudios on HNThis is neat, but something bugs me about the framing of the intended goal versus how you propose to get there. If the intent is to raise public awareness and to put pressure on…
dymk on HN
Feels like manipulating language to push a viewpoint.
From 1 comment
I'm afraid I find this somewhere between creepy and ridiculous. On the ridiculous side: the idea that calling a car accident an "accident" is somehow wrong - as if, because I…
dash2 on HN
Calling 'accident' wrong is questionable; the term is defined as negligence-based.
From 1 comment
I like the general idea, and the use of NLP to implement it. But I am dubious about some of the principles behind it. - For example, I find it inaccurate to say "the driver hit…
fermigier on HN
Some classifications are wrong, e.g. vehicle naming and VRU detection.
From 2 comments
Thanks for linking this issue, and I'll certainly look into it. I agree with your analysis on Twitter: manually annotating the article should yield the following issues: 1.…
chiefofgxbxl on HNThanks for alerting me to this - that sentence is itself fine, and the tool is incorrectly marking it as problematic. I'll debug that!
chiefofgxbxl on HN
Requests
Better handling of thematic framing detection.
From 2 comments
This is neat, but something bugs me about the framing of the intended goal versus how you propose to get there. If the intent is to raise public awareness and to put pressure on…
dymk on HNThis is a great question and I agree with you entirely. Ultimately, Framing (thematic vs. episodic) is the most important consideration for these articles. It's important for…
chiefofgxbxl on HN
Recognize context such as road design and lighting.
From 1 comment
Respectfully, I think you're demonstrating the sort of thinking the corpus of research surrounding this seeks to shine a spotlight on: blaming the victim, rather than focusing on…
chiefofgxbxl on HN
Apply the tool to other domains like gun crime reporting.
From 1 comment
This could also be used for gun crime reporting as well.
briandear on HN
Questions
How to define counterfactual and accident in this context.
From 2 comments
Thanks for the feedback. There seems to be some conflict with how to define "counterfactual". Merriam-Webster defines it as "contrary to fact" [1], so that comes down to a…
chiefofgxbxl on HNI like the general idea, and the use of NLP to implement it. But I am dubious about some of the principles behind it. - For example, I find it inaccurate to say "the driver hit…
fermigier on HN
How to augment training data for thematic elements.
From 1 comment
This is a great question and I agree with you entirely. Ultimately, Framing (thematic vs. episodic) is the most important consideration for these articles. It's important for…
chiefofgxbxl on HN