Aidan Randle-Conde of Hanzo continues his blog series on navigating AI success metrics with Part II on understanding conversational data!

Aidan’s post (Part II: Navigating AI Success Metrics – Understanding Conversational Data, available here) begins by briefly revisiting Part I of the series on precision, recall and rejection in email and document analysis.

Part II ventures into the more intricate realm of conversational AI, where the flow of dialogue presents unique challenges and opportunities for measuring success.

To that end, Aidan discusses a real-world scenario where a company car has been crashed in the parking garage by an employee who should not have had access to the keys, and you want to perform an investigation to find out what happened. The example conversation provides an excellent illustration of a typical conversation you would see in any messaging app between two individuals and raises the question of which messages should be marked as responsive. Some messages in the conversation appear to be clearly responsive, others appear to be clearly non-responsive, and others could be open to interpretation.

Read Aidan’s post here to learn more about counting discussions instead of messages, how conversational data makes working with TAR and CAL much more difficult and transitioning from traditional methods to LLMs for conversational data. It’s just one click! If you read it, the precision and recall will both be 100%! 😀

You can also check out this post which previews the entire navigating AI success metrics series.

So, what do you think? Does Aidan’s example provide a greater understanding of conversational data and the eDiscovery challenges associated with it? Please share any comments you might have or if you’d like to know more about a particular topic.

Disclaimer: The views represented herein are exclusively the views of the author, and do not necessarily represent the views held by my employer, my partners or my clients. eDiscovery Today is made available solely for educational purposes to provide general information about general eDiscovery principles and not to provide specific legal advice applicable to any particular circumstance. eDiscovery Today should not be used as a substitute for competent legal advice from a lawyer you have retained and who has agreed to represent you.