Skip to content

Check generality #2

@timm

Description

@timm
  • get text data

Repeat 20 times

  1. separate 90:10
  2. text ==> topics
  3. topics ==> classes (e.g. buggy)
    • needs some param tuning (e.g. words per topic)
  4. new data sets:
    • top top words in each topics + LDA
  5. classifying with SVM

Metadata

Metadata

Assignees

No one assigned

    Labels

    No labels
    No labels

    Projects

    No projects

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions