Publication Type:

Journal Article

Source:

International Journal of Intelligent Systems and Applications (IJISA), Volume 10, Number 9, p.32-39 (2018)

URL:

http://www.mecs-press.org/ijisa/ijisa-v10-n9/IJISA-V10-N9-4.pdf

Keywords:

Aspect based sentiment, Kernel, Least Square Regression, Random Fourier Feature, Sentiment.

Abstract:

The objective of the paper was to show the effectiveness of using random Fourier features in detection of sentiment polarities. The method presented in this paper proves that detection of aspect based polarities can be improved by selective choice of relevant features and mapping them to lower dimensions. In this study, random Fourier features were prepared corresponding to the polarity data. A regularized least square strategy was adopted to fit a model and perform the task of polarity detection Experiments were performed with 10 cross-validations. The proposed method with random Fourier features yielded 90% accuracy over conventional classifiers. Precision, Recall, and F-measure were deployed in our empirical evaluations.

Cite this Research Publication

S. Thara and Krishna, A., “Aspect Sentiment Identification using random Fourier features”, International Journal of Intelligent Systems and Applications (IJISA), vol. 10, pp. 32-39, 2018.