This thesis aims to apply machine learning models to create a Natural Language Processing (NLP) pipeline for analyzing co-worker feedback related to people planning. Text clustering and topic modeling is used to identify discussion topics, followed by sentiment analysis to assess emotions within each cluster. This approach will provide insights into co-worker experiences with workforce management, highlight potential issues, and support people planning strategies. The aim is to explore what people are talking about (topics) and how they feel about it (sentiment).