Analisis Sentimen Evaluasi Terhadap Pengajaran Dosen di Perguruan Tinggi Menggunakan Metode LSTM

Authors

  • Muhammad Afrizal Amrustian Institut Teknologi Telkom Purwokerto, Purwokerto
  • Widi Widayat Institut Teknologi Telkom Purwokerto, Purwokerto
  • Arif Muhammad Wirawan Institut Teknologi Telkom Purwokerto, Purwokerto

DOI:

https://doi.org/10.30865/mib.v6i1.3527

Keywords:

Sentiment Analysis, Learning Evaluation, LSTM, University Education, Text Mining

Abstract

Education in Indonesia is divided into several levels, from elementary education to university education. At the university education level, lecturers are asked to not only teach material but also emphasize to students that students have an important role for the future.  Due the students are considered as adults to make the decisions and take a responsibility for those decisions. During a pandemic, teaching activities are carried out online, in order the teaching activities run well, the evaluation from students is needed. Considering that students are one of the important elements in university education. In this study, sentiment analysis was carried out on the evaluation of teaching by students. The data used in this study amounted to 2280 data with the number of words in the evaluation text ranging from 3 to 50 words. The LSTM method is the method used in this study, and the results of the accuracy of using the LSTM method are 91.08%. With the analysis carried out, lecturers can improve their teaching methods based on the results of the evaluation analysis.

References

W. Wahyudi, “Kinerja Dosen: Kontribusinya Terhadap Akreditasi Perguruan Tinggi,†Sci. J. Reflect. Econ. Accounting, Manag. Bus., vol. 3, no. 4, pp. 401–410, 2021, doi: 10.37481/sjr.v3i4.241.

N. Aisyah, B. Ambarita, and A. M. Sibuea, “Significance between Organizational Culture and Lecturer Performance of Private Universities in Medan,†Budapest Int. Res. Critics Inst. Humanit. Soc. Sci., vol. 2, no. 2, pp. 75–88, 2019, doi: 10.33258/birci.v2i2.239.

K. S. Na and Z. Tasir, “Identifying at-risk students in online learning by analysing learning behaviour: A systematic review,†2017 IEEE Conf. Big Data Anal. ICBDA 2017, vol. 2018-Janua, pp. 118–123, 2018, doi: 10.1109/ICBDAA.2017.8284117.

A. N. Bahasoan, Wulan Ayuandiani, Muhammad Mukhram, and Aswar Rahmat, “Effectiveness of Online Learning In Pandemic Covid-19,†Int. J. Sci. Technol. Manag., vol. 1, no. 2, pp. 100–106, 2020, doi: 10.46729/ijstm.v1i2.30.

R. Hamid, I. Sentryo, and S. Hasan, “Online learning and its problems in the Covid-19 emergency period,†J. Prima Edukasia, vol. 8, no. 1, pp. 86–95, 2020, doi: 10.21831/jpe.v8i1.32165.

E. Hussein, S. Daoud, H. Alrabaiah, and R. Badawi, “Exploring undergraduate students’ attitudes towards emergency online learning during COVID-19: A case from the UAE,†Child. Youth Serv. Rev., vol. 119, p. 105699, 2020, doi: 10.1016/j.childyouth.2020.105699.

M. W. Novita, “Pendidikan Orang Dewasa,†pp. 107–135, 2019, doi: 10.31227/osf.io/b6hsq.

D. T. Hermanto, A. Setyanto, and E. T. Luthfi, “Algoritma LSTM-CNN untuk Binary Klasifikasi dengan Word2vec pada Media Online,†Creat. Inf. Technol. J., vol. 8, no. 1, p. 64, 2021, doi: 10.24076/citec.2021v8i1.264.

Y. Astari and R. Wahib, “Analisis Sentimen Multi-Class pada Sosial Media menggunakan metode Long Short-Term Memory (LSTM),†J. Linguist. Komputasional, vol. 4, no. 1, pp. 8–12, 2021, [Online]. Available: http://inacl.id/journal/index.php/jlk/article/view/43.

M. A. Nurrohmat and A. SN, “Sentiment Analysis of Novel Review Using Long Short-Term Memory Method,†IJCCS (Indonesian J. Comput. Cybern. Syst., vol. 13, no. 3, p. 209, 2019, doi: 10.22146/ijccs.41236.

W. Widayat, “Analisis Sentimen Movie Review menggunakan Word2Vec dan metode LSTM Deep Learning,†J. Media Inform. Budidarma, vol. 5, no. 3, p. 1018, 2021, doi: 10.30865/mib.v5i3.3111.

D. J. M. Pasaribu, K. Kusrini, and S. Sudarmawan, “Peningkatan Akurasi Klasifikasi Sentimen Ulasan Makanan Amazon dengan Bidirectional LSTM dan Bert Embedding,†Inspir. J. Teknol. Inf. dan Komun., vol. 10, no. 1, pp. 9–20, 2020, doi: 10.35585/inspir.v10i1.2568.

J. Nurvania and K. M. Lhaksamana, “Analisis Sentimen Pada Ulasan di TripAdvisor Menggunakan Metode Long Short-Term Memory ( LSTM ),†e-Proceeding Eng., vol. 8, no. 4, pp. 4124–4135, 2021.

R. Cahyadi, A. Damayanti, and D. Aryadani, “Recurrent Neural Network (RNN) dengan Long Short Term Memory (LSTM) untuk Analisis Sentimen data instagram,†J. Inform. dan Komput., vol. 5, no. 1, pp. 1–9, 2020, [Online]. Available: https://ejournal.akakom.ac.id/index.php/jiko/article/view/407.

C. Naury, D. H. Fudholi, and A. F. Hidayatullah, “Topic Modelling pada Sentimen Terhadap Headline Berita Online Berbahasa Indonesia Menggunakan LDA dan LSTM,†J. Media Inform. Budidarma, vol. 5, no. 1, p. 24, 2021, doi: 10.30865/mib.v5i1.2556.

A. Srivastava, V. Singh, and G. S. Drall, “Sentiment analysis of twitter data: A hybrid approach,†Int. J. Healthc. Inf. Syst. Informatics, vol. 14, no. 2, pp. 1–16, 2019, doi: 10.4018/IJHISI.2019040101.

I. N. F. Astuti, I. Darmawan, and D. Pramesti, “ANALISIS SENTIMEN PADA DATA KUESIONER EVALUASI DOSEN OLEH MAHASISWA (EDOM) PRODI SISTEM INFORMASI TELKOM UNIVERSITY MENGGUNAKAN ALGORITMA SUPPORT,†in e-Proceeding of Engineering, 2020, vol. 29, no. 9, p. 7018.

A. Hanifa, S. A. Fauzan, M. Hikal, and ..., “Perbandingan Metode LSTM dan GRU (RNN) untuk Klasifikasi Berita Palsu Berbahasa Indonesia,†Din. Rekayasa, vol. 17, no. 1, pp. 33–39, 2021, [Online]. Available: http://dinarek.unsoed.ac.id/jurnal/index.php/dinarek/article/view/436.

A. Hanifa and S. Akbar, “Detection of unstable approaches in flight track with recurrent neural network,†in 2018 International Conference on Information and Communications Technology (ICOIACT), 2018, pp. 735–740, doi: 10.1109/ICOIACT.2018.8350754.

Downloads

Published

2022-01-25

Issue

Vol. 6 No. 1 (2022): Januari 2022

Section

Articles

License

Creative Commons License
This work is licensed under a Creative Commons Attribution 4.0 International License

Authors who publish with this journal agree to the following terms:

  1. Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under Creative Commons Attribution 4.0 International License that allows others to share the work with an acknowledgment of the work's authorship and initial publication in this journal.
  2. Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgment of its initial publication in this journal.
  3. Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (Refer to The Effect of Open Access).