Question

如何用weka 做文本分类试验？过程怎样

我在英文论坛上搜集了20个作者，每个作者50篇评论，我选取了5个作者的评论集，进行文本分类，我用NGram提取特征，放在arff文件里，格式如下：
@relation amazonReview
@attribute "_" numeric
@attribute "e" numeric
@attribute "t" numeric
@attribute "a" numeric
@attribute "o" numeric
@attribute "i" numeric
@attribute "s" numeric
@attribute "n" numeric
416,190,160,138,134,93,107,77,83,76,83,68,62,44,67,63,42,36,44,39,49,46,42,34,31,62,31,13,20,23,22,30,26,11,20,20,31,31,32,21,24,29,27,21,15,15,14,21,12,21,12,10,20,19,20,18,18,14,20,12,20,13,19,11,27,21,11,4,7,6,11,31,7,10,15,13,10,14,17,4,11,6,9,18,7,7,10,8,6,6,13,3,12,13,7,3,7,17,7,7,7,14,2,14,10,13,14,12,4,8,8,13,18,7,8,18,3,8,3,8,8,3,6,13,9,7,12,11,14,1,3,14,5,12,3,7,11,9,11,4,10,14,1,22,3,5,10,12,9,4,10,12,10,5,4,8,8,14,15,6,5,10,5,9,9,6,10,10,10,7,7,5,3,9,7,6,5,6,1,11,6,9,6,6,6,3,6,5,3,2,2,3,8,5,5,4,5,7,6,3,3,2,7,2,5,4,6,3,6,12,3,5,7,7,7,3,7,7,5,6,3,7,4,2,2,3,6,6,6,6,0,2,5,1,1,2,6,1,7,7,5,2,6,2,8,4,5,5,2,9,5,4,9,5,1,2,5,4,0,2,4,2,9,6,3,4,8,4,6,6,4,1,6,4,9,5,4,2,3,1,6,6,1,1,7,5,4,3,7,4,1,1,1,2,5,11,2,4,2,4,0,1,6,5,2,0,2,1,3,7,4,5,1,1,5,5,5,2,2,0,1,1,2,10,1,1,5,1,4,1,2,5,2,4,5,0,5,4,0,1,2,1,4,6,5,1,3,1,1,5,0,1,3,2,7,3,3,3,1,4,2,2,4,10,10,4,0,1,1,0,1,2,1,1,8,1,4,2,7,9,8,0,3,2,0,2,3,3,4,1,2,8,2,0,1,2,4,1,2,5,Chandler
。。。。。。
下面如上，都是作者对应于上面切分特征的数据（出现的频率）的
不知道怎么在weka上进行试验，不知道怎么看试验结果

Answer 1

weka装好后就可以关联*.arff了
还有这些数据格式不太对。。。
数据部分需要有@data
属性名不用冒号
数据需要和属性对应
整理好数据后点开就可以分析了