Please use this identifier to cite or link to this item:
Title: A fuzzy logic approach for opinion mining on large scale twitter data
Authors: Bing, L
Chan, KCC 
Keywords: Big data
Data mining
Social media analytics
Issue Date: 2014
Publisher: Institute of Electrical and Electronics Engineers Inc.
Source: Proceedings - 2014 IEEE/ACM 7th International Conference on Utility and Cloud Computing, UCC 2014, 2014, 7027572, p. 652-657 How to cite?
Abstract: Recently, some efforts have been made to mine social media for the analysis of public sentiment. By means of a literature review on early works related to social media analytics especially on opinion mining, it was recognized that in the real life social media environment, the structure of the data is commonly not clear and it does not directly generate enough information to fully represent any selected target. However, most of these works were unable to accurately extract clear indications of general public opinion from the ambiguous social media data. They also lacked the capacity to summarize multi-characteristics from the scattered mass of social data and use it to compile useful models, also lacked any efficient mechanism for managing the big data. Motivated by these research problems, this paper proposes a novel matrix-based fuzzy algorithm, called the FMM system, to mine the defined multi-layered Twitter data. Through sets of comparable experiments applied on Twitter data, the proposed FMM system achieved an excellent performance, with both fast processing speeds and high predictive accuracy.
Description: 7th IEEE/ACM International Conference on Utility and Cloud Computing, UCC 2014, London, 8-11 December 2014
ISBN: 9.78E+12
DOI: 10.1109/UCC.2014.105
Appears in Collections:Conference Paper

View full-text via PolyU eLinks SFX Query
Show full item record


Last Week
Last month
Citations as of Jul 12, 2018

Page view(s)

Last Week
Last month
Citations as of Jul 16, 2018

Google ScholarTM



Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.