Read Email Body

cancel
Showing results for 
Show  only  | Search instead for 
Did you mean: 

Read Email Body

L1 Bithead

I am trying to write a playbook that will read the email body and understand what the email is related to base on keywords or patterns. Is there a script or integration that could do that? My best idea is to use Machine Learning for it, but I am not sure it will work. Thank you 

1 accepted solution

Accepted Solutions

L5 Sessionator

Hi @axespera, the ML model for email body analysis works best if there is existing classified content for it to learn from. Refer - https://docs.paloaltonetworks.com/cortex/cortex-xsoar/6-9/cortex-xsoar-admin/machine-learing-models/... to see how it works once configured correctly.

 

If you want to do this without ML. I have previously done this with the help of a tags fields and playbook. The playbook checked the emails body for a list of keyword matches. Ex. if it contained un-subscribe the playbook would add "newsletter" to the tags fields. We had conditional check for multiple keywords with tags added for promotional, offer, financial, credential and newsletter. We then had a secondary playbook that checked for combination of tags. We also had tags added from the other parts of the email like the header.

Screen Shot 2022-11-11 at 12.55.30 pm.pngIncident_Tagging_-_Email_Header_Fri_Nov_11_2022.png

View solution in original post

2 REPLIES 2

L5 Sessionator

Hi @axespera, the ML model for email body analysis works best if there is existing classified content for it to learn from. Refer - https://docs.paloaltonetworks.com/cortex/cortex-xsoar/6-9/cortex-xsoar-admin/machine-learing-models/... to see how it works once configured correctly.

 

If you want to do this without ML. I have previously done this with the help of a tags fields and playbook. The playbook checked the emails body for a list of keyword matches. Ex. if it contained un-subscribe the playbook would add "newsletter" to the tags fields. We had conditional check for multiple keywords with tags added for promotional, offer, financial, credential and newsletter. We then had a secondary playbook that checked for combination of tags. We also had tags added from the other parts of the email like the header.

Screen Shot 2022-11-11 at 12.55.30 pm.pngIncident_Tagging_-_Email_Header_Fri_Nov_11_2022.png

Hi @jfernandes1 Thank you, my understanding is that with machine learning it would check for malicious words to make the decision, would you know if with the classifier I could make it just check if the words are business related or not instead of malicious or not? Also, I liked what you did with the tags. 

  • 1 accepted solution
  • 1820 Views
  • 2 replies
  • 0 Likes
Like what you see?

Show your appreciation!

Click Like if a post is helpful to you or if you just want to show your support.

Click Accept as Solution to acknowledge that the answer to your question has been provided.

The button appears next to the replies on topics you’ve started. The member who gave the solution and all future visitors to this topic will appreciate it!

These simple actions take just seconds of your time, but go a long way in showing appreciation for community members and the LIVEcommunity as a whole!

The LIVEcommunity thanks you for your participation!