11-04, 14:30–15:00 (Asia/Jerusalem), Green Track
As data analysts, we are often called to derive insights and action items from the feedback our users provide. Traditional analysis tools are great when the feedback is given to us in categorical formats - for example, yes/no or multiple choice responses, but often fall short when it comes to free-text. I will show how I used the BertTopic Python package to leverage the power of Deep Learning and Language Models in order to embed and cluster and visualise feedback texts in a way that tells a meaningful story, a story that sheds light on the pain points and desires of our end-users.
This is a beginner level lecture, focused towards data analysts and product managers without string background in data science.
We’ll start by describing the issue at hand: why traditional analysis tools are not good enough for free-text analysis tasks. Then we’ll discuss how BertTopics works and show a minimal usage example in Python. We will dive into each of the stages of the process: embedding, clustering and dimensionality reduction and explore them.
Finally, we’ll show some results using interactive visualization.
2019-2020 data science intern at CheckPoint
2020-2022 data analyst at Ebay
2022-2023 senior data analyst at Lusha