How to collect free-text feedback: an introduction for a data scientist

Author(s): Anil Tilbe

Originally published on Towards AI.

Understand how to develop technical learning systems to collect free-text, open-ended responses from users.

Photo by Emily Morter from Unsplash

To truly understand the type of measurement framework to implement for how to solicit feedback is to also humbly acknowledge as a data scientist the shortcomings and imprecise capabilities of natural language processing and machine learning.

Control +F the number of times I mentioned “primary source.”

Use case: analyze free-text comments; predict their binary sentiment (positive or negative); and measure the magnitude of that sentiment (e.g., polarities in TextBlob; the positive or compound score in VADER; your custom sentiment score for your custom-trained model;… Read the full blog for free on Medium.

Join thousands of data leaders on the AI newsletter. Join over 80,000 subscribers and keep up to date with the latest developments in AI. From research to projects and ideas. If you are building an AI startup, an AI-related product, or a service, we invite you to consider becoming a sponsor.

Published via Towards AI