Hierarchical topic modeling is a potentially powerful instrument for determining topical structures of text collections that additionally allows constructing a hierarchy representing the levels of topic abstractness. However, parameter optimization in hierarchical models, which includes finding an appropriate number of topics at each level of hierarchy, is a challenging task. Hence in this project, the team will work on exploring unsupervised learning techniques to analyze textual data, specifically emails, and generate hierarchical topics and clusters to determine the intent of the emails. The team will also work on how to generate visual representations of these generated hierarchical clusters and topics and perform evaluation on them.
- Pablo Hernandez (ph2632)(Team Captain)
- Gilberto Garcia (gg2831)
- Abel Perez (ap4015)
- Nicolo Ricca (nr2810)
- Xinyu Wang (xw2814)
- Yunchen Yao (yy2949)
- Simerjot Kaur
- Akshat Gupta
- Keshav Ramani
- Sining Chen (Instructor)
- Aayush Kumar (CA)