A Computational Approach of Recognizing Emotion from Bengali Texts
- 1 September 2019
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 570-574
Abstract
Emotion recognition is the task of determining distinct emotion exhibited in text. In recent year, due to the availability of enormous amount of textual data, specially dogmatic and self expressiveness of text played a significant role to lead focus in this area. This paper presents an emotion recognition technique that can identify six basic emotions from Bengali texts such as happy, sad, anger, fear, surprise, and disgust respectively. We develop a corpus consisting of 1200 emotive words that are used to train the SVM classifier for identifying different emotions. Experimental result shows that the proposed system can recognize emotions with 73% accuracy which is higher than the Naive based approach (60%).Keywords
This publication has 14 references indexed in Scilit:
- A Text-Based Chat System Embodied with an Expressive AgentAdvances in Human-Computer Interaction, 2017
- Supervised approach of sentimentality extraction from bengali facebook status2016
- Opinion mining using Naïve Bayes2015
- Multi-Class Twitter Emotion Classification: A New ApproachInternational Journal of Applied Information Systems, 2012
- An enhanced approach for classifying emotions using customized decision tree algorithm2012
- Emotions on Bengali Blog Texts: Role of Holder and Topic2011
- Identifying Expressions of Emotion in Text2007
- Expressing emotion in text-based communication2007
- Facial expression and emotion.American Psychologist, 1993
- The Cognitive Structure of Emotions1988