Fig. 2: Graphical model of Sent-LDA.
From: What drives reputational risk? Evidence from textual risk disclosures in financial statements
The basic idea of the LDA model is that documents are represented as random mixtures over latent topics, where each topic is characterized by a distribution over words. Sent-LDA inherits the basic concept of LDA and further adjusts its bag-of-words assumption as the rule that each sentence discusses only one topic.
