Skip to main content

Table 2 Performance of the top three sampling methods in capturing the most attentive hashtags during the event week (168 hours), evaluated based on Precision@100 each hour over different sampling conditions (10% and 30% of the complete user set)

From: Measuring and monitoring collective attention during shocking events

Sample

CoPerplexity_PRW ( α  = 0.4)

CoPerplexity_RW

CommonTag_RW

1st

2nd

3rd

1st

2nd

3rd

1st

2nd

3rd

Paris attacks(Paris users)

10%

51.19%

33.93%

14.88%

43.45%

43.45%

13.10%

8.33%

23.21%

68.45%

30%

46.43%

43.45%

10.12%

52.38%

39.88%

7.74%

7.14%

17.26%

75.60%

Paris attacks(London users)

10%

53.57%

36.90%

9.52%

39.88%

47.02%

13.10%

10.12%

22.66%

72.62%

30%

32.73%

49.40%

17.86%

59.52%

28.57%

11.90%

17.86%

26.79%

55.36%

Brussels bombings

10%

57.14%

25.00%

17.86%

30.95%

36.90%

32.14%

14.88%

40.48%

44.64%

30%

22.02%

44.05%

33.93%

68.45%

22.62%

8.93%

12.50%

35.12%

52.38%

San Bernardino shooting

10%

44.04%

36.31%

19.64%

21.43%

47.02%

31.55%

40.47%

19.05%

40.47%

30%

22.02%

39.29%

32.14%

33.93%

46.43%

31.55%

50.60%

23.21%

26.19%

  1. For each method, the fraction of the method ranked in the top three places are reported.