I am working for a small Stockholm-based consultancy firm. When working with clients we collect data through online questionnaires. The data is comprised of words and phrases that we manually assign to clusters and then present to customers.
Having done some basic investigation we have realized that this process could possibly be automated applying text and syntax analyses.
We already have clustered data that could be refined used as potential training and/or validation set for an ML algorithm. What we are looking for is someone versed in machine learning to help us set up a process for handling the incoming data and applying clustering algorithms onto said data.
In a first step we would like to have a conversation about our current situation as well as talk about possible implementations.