Probabilistic Topic Models of Text and Users
Presidential Lectures are free public colloquia centered on four main themes: Biology, Physics, Mathematics and Computer Science, and Neuroscience and Autism Science. These curated, high-level scientific talks feature leading scientists and mathematicians and are intended to foster discourse and drive discovery among the broader NYC-area research community. We invite those interested in the topic to join us for this weekly lecture series.
In this talk, David Blei will review the basics of topic modeling and describe his recent research on collaborative topic models—models that simultaneously analyze documents and the corresponding reader behavior. Blei will explain how using collaborative topic models to discover patterns in how people read can help point readers to relevant new documents. Finally, he will discuss the broader field of probabilistic modeling, which gives data scientists both a rich language for expressing statistical assumptions and scalable algorithms for using those assumptions to uncover hidden patterns in massive data.