search

ai-se / BUBBLE_TSE

BUBBLE for TSE submission
0 stars 2 forks source link

Reviewer 2,Q3: Question Regarding the task of the model #10

Open Suvodeep90 opened 4 years ago

Suvodeep90 commented 4 years ago

[Sec. 1] “when new projects appear, their quality can be evaluated even before there is an extensive experience base within that particular project (again, just by studying the bellwether).” You take a set of projects…select one project (the “bellwether”)…then use that project to build a model that can—for instance—estimate defect rate. So, for the defect estimation case, the model learned from the bellwether won’t tell you where the defects may be (i.e., fault localization), it will just estimate how buggy a new project is. Is all of this right?

1) The model learned from the bellwether won’t tell you where the defects may be (i.e., fault localization), it will just estimate how buggy a new project is. Is all of this right?
Suvodeep90 commented 4 years ago

The model learned from the bellwether won’t tell you where the defects may be (i.e., fault localization), it will just estimate how buggy a new project is. Is all of this right?

The model learned from this task is about defect prediction, where we try to localize defects on defective class modules. This project doesn't estimate how buggy a new project is it estimates which of the modules of a new project is buggy.