Skip to content

Weighting features' importance #2

@ShiyuZhangGH

Description

@ShiyuZhangGH

A general question I have concerns the large amount of information in the text. How do I weight and make the differentiation between more informative and less informative features?
This would be easier if only single words are involved. For example, we discussed tf-idf in previous weeks. But how to weight when there are relations between words and when data are stored in RDBMS?

Metadata

Metadata

Assignees

No one assigned

    Labels

    No labels
    No labels

    Type

    No type
    No fields configured for issues without a type.

    Projects

    No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions