I would start by reviewing any available tools in NLP that can help you. I know two: Watson Personality Insights and Symanto thar provide API to develop this kind of solutions.
The first one was one available in the past (Watson personality Insights) but unfortunately has been discontinued.
The IBM Watson Personality Insights service enables applications to
derive insights from social media, enterprise data, or other digital
communications. The service uses linguistic analytics to infer
individuals' intrinsic personality characteristics, including Big
Five, Needs, and Values, from digital communications such as email,
text messages, tweets, and forum posts.
The service can automatically infer, from potentially noisy social
media, portraits of individuals that reflect their personality
characteristics. The service can infer consumption preferences based
on the results of its analysis and, for JSON content that is
timestamped, can report temporal behavior.
Another comercial tool is Symanto:
Symanto Insights Platform is an AI-powered analysis tool that gives
you qualitative insights about your textual data. Just upload your
data sets or crawl information from different sources such as online
review sites or online surveys, and Symanto’s AI immediately analyses
your data and provides you qualitative insights about the author.
Symanto Insights Platform reveals the opinions of your customers and
employees by analysing text data, giving you insights about current
topics, general performances or the psychographic structure of your
audience. Whether it’s psychographic marketing, customer service,
product development or employee satisfaction, Symanto Insights
Platform helps you answer a wide range of business questions.
I´m somehow working in this field in my Master thesis so if you need any further info just let me know.