Author details | Data type | Topic modeling used | Intended aim | Data size |
---|---|---|---|---|
DiMaggio et al. [13] | Newspapers | LDA | Identifying concepts in news coverage | 8000 |
Grimmer [18] | Press release | Own implemented method | To develop a model | 24,000 |
Koltsova and Koltcov [21] | Web posts | LDA | Explore the political agenda for live journal | 1,300,000 |
Maier et al. [25] | Web documents | LDA | Explore the validity and reliability of the LDA model | 186,557 web documents |
Quinn et al. [38] | Legislative Speech | Own implemented method | To develop a statistical learning model | 118,000 speeches (70,000,000 words) |