Sentic-Emotion Classifier on eWallet Reviews

Abstract

Emotion classification using hybrid framework using lexicon and machine learning algorithms have been proven to be more accurate. This research analyses emotions from reviews of a popular eWallet mobile application in Malaysia. The proposed Sentic-Emotion Classifier is evaluated on its performance as it analyses the code-switched reviews crawled that contain formal and informal or out-of-vocab words. The code-switched reviews are mainly made up of words and expressions in English and Malay language models. This research designs, implements, and investigates several novel techniques that have been shown to have reliable and consistent predictive outcomes, and these outcomes are validated with manually annotated reviews so that the proposed classifier can be evaluated objectively. The novel contributions of the Sentic-Emotion Classifier consist of 2-tier sentiment classification, extended emolex framework, and multi-layer discrete emotion hierarchical classes which is hypothesized to be able to yield better accuracy for emotion and intensity prediction for the proposed framework.