I have customer text data, which includes three main cluster: "complaint", "inform" and "demand"
I want to analyze all texts via text mining packages. After the analysis, i want to use result to cluster for each new text into three main cluster ("complaint", "inform" and "demand").
How can i do that?
How can i use this result to cluster for each new customer text?
for example this is result of "rpart" algorithm:
CART
1536 samples
14427 predictors
3 classes: 'complaint', 'inform', 'demand'
No pre-processing
Resampling: Cross-Validated (10 fold, repeated 4 times)
Summary of sample sizes: 1383, 1383, 1383, 1382, 1382, 1382, ...
Resampling results across tuning parameters:
cp Accuracy Kappa
0.002941176 0.5810442 0.18144641
0.003676471 0.5826825 0.18460649
0.004411765 0.5860873 0.19006198
0.008333333 0.5935740 0.20823251
0.011764706 0.5934085 0.21113517
0.017647059 0.5940589 0.21615325
0.043382353 0.5600526 0.05856701
Accuracy was used to select the optimal model using the largest value.
The final value used for the model was cp = 0.01764706.