An Introduction to the Weka Data Mining System (Abstract Only)
Ingrid Russell, Zdravko Markov · 2017
The workshop introduces participants to Weka, an open source Data Mining software package written in Java and available from www.cs.waikato.ac.nz/~ml/weka/. The goal of the workshop is to present the basic functionality of Weka that may be used in the undergraduate computer science and engineering curricula. The Weka system provides a rich set of powerful Machine Learning algorithms for Data Mining tasks, along with a comprehensive set of tools for data pre-processing, statistics and visualization, all available through an easy to use graphical user interface. Weka is widely used for educational purposes. Recently, with the increasing popularity of Big Data, it becomes a popular tool for Analytics and Data Science. Weka's rich functionality also allows its use for Text and Web document pre-processing and mining. All this makes it a suitable platform for enhancing the CS curriculum with hands-on exercises and practical projects. The workshop will present examples of such projects and exercises in the area of Web document classification and clustering. The basic steps of document collection, creating the vector space model, data preprocessing, attribute selection, and applying classification and clustering algorithms will be discussed. These topics will be covered in a way that will allow participants with no particular background in machine learning or data mining to appreciate the use of Weka in computer science education.