Web Content Classification
The purpose of this project is to investigate how to develop and make effective use of method and techniques of text summarization, text mining, and sentiment analysis for web content classification. Our goal is to build content classification models and deliver analytical results for online safety and security solutions. We will explore the use of n-grams models, LDA topic models, ontology and semantic resources, lexicon based sentiment analysis as well as effective machine learning methods.
Financing: Part of the Digile D2I research program, funded by Tekes, Arcada Research Foundation
Project partners: F-secure
Duration: January 2014 -
Project manager: Shuhua Liu
Participating researchers: Shuhua Liu