Skip to main content

Table 4 Details on the datasets used

From: Analysis and classification of privacy-sensitive content in social media posts

Dataset

# posts

# sens

# ns

Avg # words

SENS2

8765

3336

5429

15.11 ± 12.58

SENS3

4046

1444

2602

15.40 ± 12.67

OMC

17,860

10,793

7067

15.58 ± 11.00

WH+TW

8765

3336

5429

13.08 ± 8.26