Title: Comparing different classifiers and feature selection techniques for emotion classification

Authors: Satish Mahadevan Srinivasan; Prashanth Ramesh

Addresses: Penn State Great Valley, School of Graduate Professional Studies, 30 East Swedesford Road, Malvern, PA 19355-1443, USA ' Penn State Great Valley, School of Graduate Professional Studies, 30 East Swedesford Road, Malvern, PA 19355-1443, USA

Abstract: In this study, we have explored the potentiality of six different supervised machine learning approaches and feature selection filters to recognize four basic emotions (anger, happy, sadness and surprise) using three different heterogeneous emotion-annotated dataset which combines sentences from news headlines, fairy tales and blogs. For classification purpose, we have chosen the feature set to include the bag-of-words. Our study reveals the fact that the use of the resampling filter and the feature selection filters together contribute towards boosting the prediction accuracies of the classifiers. However, the boosting capabilities are more profound in the resampling filter in comparison to the use of the different feature selection filters.

Keywords: text mining; feature selection techniques; supervised classifiers; emotion classification; machine learning; WEKA; synthetic dataset; resampling; attribute selection; society systems science.

DOI: 10.1504/IJSSS.2018.095595

International Journal of Society Systems Science, 2018 Vol.10 No.4, pp.259 - 284

Received: 21 Mar 2018
Accepted: 25 Apr 2018
Published online: 11 Oct 2018 *

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