Inspired by a two-level theory from political science that unifies agenda setting and ideological framing, we propose supervised hierarchical latent Dirichlet allocation (ShLda), which jointly captures documents' multi-level topic structure and their polar response variables. Our model extends the nested Chinese restaurant processes to discover tree-structured topic hierarchies and uses both per-topic hierarchical and per-word lexical regression parameters to model response variables. ShLda improves prediction on political affiliation and sentiment tasks in addition to providing insight into how topics under discussion are framed.
展开▼
