Skip to main content

Table 1 Results using k-means clustering with cosine similarity (S1)

From: Using semantic clustering to support situation awareness on Twitter: the case of world views

 

S1: k-means clustering with cosine similarity

D1: Paddington

C1.1.1: Run, Unable, Follow

C1.1.2: Station, Tube, @DailyMirror

C1.1.3: Closed, Breaking, Jump, Threatening

D2: Boston

C1.2.1: Continued, Crossed, Finish, Line

C1.2.2: Arrested, @BostonGlobe, Terror

C1.2.3: Eludes, Shuts, Hunt

D3: Ivory Coast

C1.3.1: Terrorist, @News_Executive, Seaside

C1.3.2: Guns, Machine, Gunmen, @DailyMirror

C1.3.3: Witnesses, Way, @AFP