Sentiment Analysis of Student Emotion During Online Learning Using Recurrent Neural Networks (RNN)

Nisa Hanum Harani(1*), Cahyo Prianto(2),

(1) Politeknik Pos Indonesia, Bandung, Indonesia
(2) Politeknik Pos Indonesia, Bandung, Indonesia
(*) Corresponding Author


There are many limitations in online learning process where communication effect student productivity, such as interpretation in the delivery of information can be different if it is in text form . The unstable internet network in some parts of Indonesia is also an obstacle in the learning process. Emotional factors are very influential on student motivation in learning, in online learning emotions can be read from textual dialogue in providing responses. We propose trainable model capable of identifying  the tendency of emotions / responses felt by students. With using natural language processing we can extract information and insights contained in conversations from WhatsApp, then organize them into their respective categories. The selection of the RNN algorithm can increase the accuracy by 75% in analyzing student emotions in online learning.

Full Text:



Eko Yulianto, Putri Dwi Cahyani, and Sofia Silvianita, “Perbandingan Kehadiran Sosial dalam Pembelajaran Daring Menggunakan Whatsapp groupdan Webinar Zoom Berdasarkan Sudut Pandang Pembelajar Pada Masa Pandemic COVID-19,” JARTIKA J. Ris. Teknol. dan Inov. Pendidik., vol. 3, no. 2, pp. 331–341, 2020, doi: 10.36765/jartika.v3i2.277.

A. Muhson, “Pengembangan Media Pembelajaran Berbasis Teknologi Informasi,” J. Pendidik. Akunt. Indones., vol. 8, no. 2, 2010, doi: 10.21831/jpai.v8i2.949.

N. E. Putri and D. Iskandar, “Analisis Preferensi Konsumen Dalam Penggunaan Social Messenger Di Kota Bandung Tahun 2014 (Studi Kasus : Line, Kakaotalk, Wechat, Whatsapp),” J. Manaj. Indones., vol. 14, no. 2, p. 110, 2017, doi: 10.25124/jmi.v14i2.356.

S. Dina, “Pemerintah ungkap tantangan pembangunan infrastruktur internet,”, 2020. .

N. Girdharwal, “Emotional intelligence and happiness,” Indian J. Public Heal. Res. Dev., vol. 10, no. 10, pp. 88–92, 2019, doi: 10.5958/0976-5506.2019.02774.8.

R. Habibi, D. B. Setyohadi, and E. Wati, “Analisis Sentimen Pada Twitter Mahasiswa Menggunakan Metode Backpropagation,” J. Inform., vol. 12, no. 1, pp. 103–109, 2016, doi: 10.21460/inf.2016.121.462.

A. Chatterjee, U. Gupta, M. K. Chinnakotla, R. Srikanth, M. Galley, and P. Agrawal, “Understanding Emotions in Text Using Deep Learning and Big Data,” Comput. Human Behav., vol. 93, pp. 309–317, 2019, doi: 10.1016/j.chb.2018.12.029.

W. Van der Aalst, “Process mining: Data science in action,” Process Min. Data Sci. Action, no. April 2014, pp. 1–467, 2016, doi: 10.1007/978-3-662-49851-4.

James F. Allen, “Natural language processing,” Encycl. Comput. Sci., pp. 1218–1222, 2003.

A. Yadollahi, A. G. Shahraki, and O. R. Zaiane, “Current state of text sentiment analysis from opinion to emotion mining,” ACM Comput. Surv., vol. 50, no. 2, 2017, doi: 10.1145/3057270.

H. Shi, M. Xu, and R. Li, “Deep Learning for Household Load Forecasting-A Novel Pooling Deep RNN,” IEEE Trans. Smart Grid, vol. 9, no. 5, pp. 5271–5280, 2018, doi: 10.1109/TSG.2017.2686012.

W. Yu, I. Y. Kim, and C. Mechefske, “An improved similarity-based prognostic algorithm for RUL estimation using an RNN autoencoder scheme,” Reliab. Eng. Syst. Saf., vol. 199, no. February, p. 106926, 2020, doi: 10.1016/j.ress.2020.106926.



  • There are currently no refbacks.

Jumlah Kunjungan:

View My Stats

Published Papers Indexed/Abstracted By: