Jodie Burchell, a developer advocate for data science at JetBrains with a PhD in clinical psychology, shares her expertise on sentiment analysis. She discusses traditional lexicon-based methods and advanced machine learning techniques, highlighting the evolution of sentiment analysis with large language models. Jodie emphasizes the challenges of linguistic nuances and context in emotional classification. From practical applications in blogging to tools for analysis like TextBlob, she provides valuable insights for anyone looking to dive deeper into this field.

Python experts Jodie Burchell, Carol Willing, and Paul Everett discuss Python's future trends, large language models' impact on science, transparency in AI, Python evolution, refactoring benefits, community inclusivity, data science challenges, and the importance of human creativity in programming.

Jodie Burchell, developer advocate for data science at JetBrains, discusses techniques and tools for evaluating large language models (LLMs) using Python. They explore measuring bias, toxicity, and truthfulness in LLMs, the challenges and limitations of AI language models, the role of Python packages like Hugging Face, and the concept of grouping and acronyms. Jodie also shares benchmarking datasets and resources available on Hugging Face for evaluating LLMs.

In this engaging discussion, Dr. Jodie Burchell, Data Science Developer Advocate at JetBrains and a former clinical psychologist, delves into the evolution of data science notebooks. She highlights how these tools transformed from local scripts to collaborative, remote environments, enhancing accessibility and efficiency. Jodie predicts future trends influenced by generative AI, emphasizing the role of ethical considerations and the human touch in data science. Her insights on the intersection of behavioral science and data advocacy are particularly enlightening!

Join Jodie Burchell, Maria Jose Molina-Contreras, and Jessica Greene as they discuss recent data science topics like model evaluations, practicality vs. complexity, bias assessment, and measuring metrics. They share insights on career transitions, challenges in the field, and the intersection of data science with other domains. The conversation covers a wide range of data science aspects and emphasizes the importance of networking and continuous learning.