Title: A query expansion approach for social media data extraction

Authors: Nhung Do; Wenny Rahayu; Torab Torabi

Addresses: Department of Computer Science and Information Technology, La Trobe University, Melbourne, VIC 3068, Australia ' Department of Computer Science and Information Technology, La Trobe University, Melbourne, VIC 3068, Australia ' Department of Computer Science and Information Technology, La Trobe University, Melbourne, VIC 3068, Australia

Abstract: Social media data analysis has been a significant topic of interest in both academia and industry over the past few years. The availability of the increasingly huge amount of social media data is changing our attitude towards social media data analytics which has moved from extracting more meaningful information to predicting social trends. Recently, an increasing number of approaches have been proposed on the applications of social media data. However, they mostly focus on processing the query result data which is often inadequate as the query terms are not easily determined by the users. Taking into consideration this shortcoming, this paper aims to examine the query side in order to provide a better solution for social media data analytics. We propose a Wikipedia-based query expansion and temporal ranking technique for social media data to extract more meaningful answers.

Keywords: query expansion; wikipedia; temporal relevance; social media data; twitter; data extraction; data analytics; imprecise queries; related term detection; term candidate filtering; connection strength; term popularity.

DOI: 10.1504/IJWGS.2016.080142

International Journal of Web and Grid Services, 2016 Vol.12 No.4, pp.418 - 441

Received: 29 Apr 2016
Accepted: 29 May 2016

Published online: 03 Nov 2016 *

Full-text access for editors Access for subscribers Purchase this article Comment on this article