The Community for Technology Leaders
2016 IEEE Second International Conference on Big Data Computing Service and Applications (BigDataService) (2016)
Oxford, United Kingdom
March 29, 2016 to April 1, 2016
ISBN: 978-1-5090-2251-9
pp: 44-51
ABSTRACT
Tackling the challenges posed by Social Networkingcontent and addressing its casual nature, n-gram graphstechnique provides a language-independent supervised approach for text mining. Adopting this data analysis model, this paper provides an extended study of sentiment analysis, using a multilingual and multi-topic environment, employing and combining different classification algorithms, and attempting various configuration approaches on classification parameters to increase the efficiency. Compared to results found on big corpora used in previous studies, the outcome of the current paper implies a high classification accuracy and an enhanced validity, since the current experiments use datasets processed by human annotators.
INDEX TERMS
Twitter, Sentiment analysis, Analytical models, Training, Big data, Semantics, Dictionaries
CITATION

F. Aisopos, D. Tzannetos, J. Violos and T. Varvarigou, "Using N-Gram Graphs for Sentiment Analysis: An Extended Study on Twitter," 2016 IEEE Second International Conference on Big Data Computing Service and Applications (BigDataService)(BIGDATASERVICE), Oxford, United Kingdom, 2016, pp. 44-51.
doi:10.1109/BigDataService.2016.13
91 ms
(Ver 3.3 (11022016))