Description: This workshop introduces the topic of text mining and its applications, with an added focus on how modern large language models (LLMs) are transforming the field. It covers text encoding mechanisms used to convert text into numerical representations that algorithms can process, including embeddings generated by LLMs. The session provides an overview of key text mining tasks such as de-identification, sentiment analysis, and document clustering, highlighting how these are approached both with classical methods and with LLM-based techniques. Through examples and live demos, participants will see how LLMs can enhance or streamline these tasks. The workshop also references state-of-the-art tools, libraries, and LLM frameworks used to perform a wide range of text mining applications.
Teacher: Amal Khalil (CAC, Queen's University)
Level: Intermediate
Format: Lecture + Hands-on
Certificate: Completion
Prerequisites: Basic Python