In rosepeglershare/TagR: SHARE's TagR package that uses machine learning to identify a comment's relevant topics

knitr::opts_chunk$set(
  collapse = TRUE,
  comment = "#>",
  fig.path = "man/figures/README-",
  out.width = "100%"
)

TagR

What is TagR?

TagR is SHARE's R package for topic tagging using machine learning. Using predefined topics and a labelled data set, it allows the user to find the probability that an unlabelled post belongs to a particular topic.

This package is used by running through the following steps:

• Pre-process the text data
• Conduct exploratory data analysis
• Create document-term matrices
• Bind any numerical variables to the document-term matrices
• Find an optimal set of parameters for the Xgboost model for each topic
• Train a model for each topic and predict the probabilities that each post in the unlabelled data set belongs to such topic
• Build an explainer that helps the user visualise how the Xgboost model makes its predictions

Installation

You can install the released version of TagR from CRAN with:

Example

This is a basic example which shows you how to solve a common problem:

library(TagR)
## basic example code

rosepeglershare/TagR documentation built on Dec. 31, 2020, 3:12 a.m.