Discovering Context: Classifying Tweets Through a Semantic Transform Based on Wikipedia

FOUNDATIONS OF AUGMENTED COGNITION: DIRECTING THE FUTURE OF ADAPTIVE SYSTEMS, HCI International July 9-14, 2011, Orlando, FL

10 Pages Posted: 17 Apr 2012

See all articles by Yegin Genc

Yegin Genc

Stevens Institute of Technology - School of Business

Yasuaki Sakamoto

AXA Direct Japan

Jeffrey V. Nickerson

Stevens Institute of Technology - School of Business

Date Written: July 1, 2011

Abstract

By mapping messages into a large context, we can compute the distances between them, and then classify them. We test this conjecture on Twitter messages: Messages are mapped onto their most similar Wikipedia pages, and the distances between pages are used as a proxy for the distances between messages. This technique yields more accurate classification of a set of Twitter messages than alternative techniques using string edit distance and latent semantic analysis.

Keywords: text classification, Wikipedia, semantics, context, cognition, latent semantic analysis

Suggested Citation

Genc, Yegin and Sakamoto, Yasuaki and Nickerson, Jeffrey V., Discovering Context: Classifying Tweets Through a Semantic Transform Based on Wikipedia (July 1, 2011). FOUNDATIONS OF AUGMENTED COGNITION: DIRECTING THE FUTURE OF ADAPTIVE SYSTEMS, HCI International July 9-14, 2011, Orlando, FL. Available at SSRN: https://ssrn.com/abstract=2041399

Yegin Genc (Contact Author)

Stevens Institute of Technology - School of Business ( email )

Hoboken, NJ 07030
United States

Yasuaki Sakamoto

AXA Direct Japan ( email )

Japan

Jeffrey V. Nickerson

Stevens Institute of Technology - School of Business ( email )

Hoboken, NJ 07030
United States

Register to save articles to
your library

Register

Paper statistics

Downloads
125
rank
218,261
Abstract Views
1,237
PlumX Metrics