AI vs. Karen: Real-Time Customer Sentiment Detection at Scale
Talk (60 min)
In this talk, we'll explore how to build AI-powered real-time streaming pipelines. Whether it’s for fun, profit, or simply seeking revenge on the Karens of the world.
We will discuss the architecture, libraries, and tools you need to perform real-time sentiment analysis on live unstructured user data coming from your own system or even social media, using Apache Kafka and Apache Flink. You'll learn about the challenges of integrating AI models into these technologies, and we'll walk through a practical, real-world example.
Finally, we'll break down the differences between using powerful large language models (LLMs) and lightweight small language models (SLMs), understand the pros and cons of each and how to pick the best one for your specific scenario.
Whether you are experienced in streaming systems and data engineering, or just curious about applying AI to solve real-world problems, this session will give you the foundation, insights, and inspiration to try it out yourself.
Josef Goldstein
The data and culture guy. Currently leading the Big Data Platform R&D at Wix.
Josef has over 15 years of experience building data intensive SaaS applications and growing the awesome teams that make them.
He believes that the secret sauce for creating sustainable complex systems is good design practices, effective communication between people, and automating everything. In his day to day he works tirelessly on building the culture necessary to support these values and propagate them to others, one pep-talk at a time.