Abstract
Emotion detection textual content is getting popular among individuals and business companies to analyze user emotional reaction on the products they use. In this work, emotion detection from textual content is performed by using supervised learning-based Logistic Regression classifier. ISEAR dataset is used to taring the classifier, while testing dataset is used to evaluate the prediction capability of the classifier for emotion classification. The prior works used rule-based techniques, supported by lexical resources. However, limited coverage of emotional clues, was the major issue, which resulted in poor performance of system. The proposed work overcomes this limitation by proposing supervised learning technique using Logistic Regression classifier. The results obtained are encouraging and show that the proposed system performed better than the similar methods.
Reference20 articles.
1. Asghar, M. Z., Khan, A., Bibi, A., Kundi, F. M., & Ahmad, H. (2017). Sentence-level emotion detection framework using rule-based classification. Cognitive Computation, 9(6), 868-894.
2. [2] Shaila, S. G., & Vadivel, A. (2015). Cognitive based sentence level emotion estimation through emotional expressions. In Progress in Systems Engineering (pp. 707-713). Springer, Cham.
3. [3] Asghar, M. Z., Khan, A., Khan, K., Ahmad, H., & Khan, I. A. (2017). COGEMO: Cognitive-Based Emotion Detection from patient generated health reviews. Journal of Medical Imaging and Health Informatics, 7(6), 1436-1444.
4. [4] ISEAR Dataset, available at: http://emotionresearch.net/toolbox/toolboxdatabase Last accessed 10-nov-2018.
5. [5] Kaewyong, P., Sukprasert, A., Salim, N., & Phang, A. (2015). The possibility of students’ comments automatic interpret using lexicon based sentiment analysis to teacher evaluation. In 3rd International Conference on Artificial Intelligence and Computer Science (AICS2015) (pp. 179-189).
Cited by
15 articles.
订阅此论文施引文献
订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献