Hi All,
I am working on a text data about accident and I want to extract certain key details from the description provided about accident and put that extracted key details into new column. For example:
Description - "The person died of head injury on the spot while driving a car."
Injury - Head
Injury Place - On road
Death Place - On spot
Basis brief description, values for three new columns get captured.
I have to provide the solution using SAS tools only.
Thanks
I would have to see a lot of the description text to make any suggestion. One problem with such a short limited description is that different descriptions may not use the same phrases or words. "Road" could appear as Interstate, Highway, Lane, Street or others. "Died" could be deceased or other synonym. Your request also seems to assume a death is involved and I have no idea how many ways "on the spot" or "in transit to emergency care" or "in hospital" might be written up.
FWIW I have worked with actual traffic accident data collections. There will be one large record that basically describes the location, another that describes each vehicle involved and yet another for each person in each vehicle with details of injuries. NOT all in one file or dataset typically because of the multiple vehicle/ multiple persons per vehicle nature of the data. So things get joined together
@Dave251 wrote:
Description - "The person died of head injury on the spot while driving a car."
Injury - Head
Injury Place - On road
Death Place - On spot
It's nearly impossible to provide a solution that will work in a general situation based upon one sample sentence.
Thanks for the reply.
Yes, agree with your response. However, I was looking for some input that guide me towards possible tool or model which I can use to solve the problem.
Feels very much like a case for SAS Visual Text Analytics.
https://support.sas.com/en/software/visual-text-analytics-support.html
Hello,
If we can collect contextual patterns in which these key elements appear from the text, the Concept node in Visual Text Analytics is well-suited to address this issue.
For documentation on the Concept node in VTA, please refer to
https://go.documentation.sas.com/doc/en/capcdc/v_020/ctxtcdc/ctxtug/p0l1gb2dihm3f4n16pswu5o9z32p.htm
Are you ready for the spotlight? We're accepting content ideas for SAS Innovate 2025 to be held May 6-9 in Orlando, FL. The call is open until September 16. Read more here about why you should contribute and what is in it for you!
Use this tutorial as a handy guide to weigh the pros and cons of these commonly used machine learning algorithms.
Find more tutorials on the SAS Users YouTube channel.