Table 1:
# of posts | # of comments | |
---|---|---|
Raw data (json file after removing duplicate posts) | 12614 | 43607 |
After 1st round BTM removed 6 topics | 4062 | 11858 |
After 2nd round BTM removed 2 topics | 3533 | 9545 |
After 3rd round BTM removed 1 topic | 3433 | 9274 |
Remove comments with length less than 2 | 2981 | 7491 |
Table 1 shows the number of comments and posts removed after rounds of BTM and removing clusters that did not contain signal characteristics.