Page 190 - The-5th-MCAIT2021-eProceeding

Behind the various advantages of Bi-LSTM, there is still a problem where the complex Bi-LSTM algorithm
architecture becomes one of the high computational burdens when applied to large-scale cases.

4. Conclusions

Literature studies of the previous researches obtained seven pieces of literature published from 2018 to 2020
with the research theme of the introduction of named-entity that can use 3 approaches, namely: 1) Machine
learning, 2) Deep learning, and 3) A combination of machine learning with deep learning. The combination of
machine learning and deep learning was used in 4 studies from 7 analyzed pieces of literature, namely the
combination of Bidirectional Long Short-Term Memory (Bi-LSTM) deep learning with Conditional Random
Field (CRF) machine learning. CRF with its probabilistic model can be used for pattern recognition because it
is able to consider word order labels while the two layers of Bi-LSTM can handle sequential data to improve
prediction accuracy by moving forward and backward. Currently, we are interested in exploring the topic of
fake news detection but have not conducted any specific experiments related to NER. After conducting this
literature study, we plan to explore NER using a fake news dataset that researchers have not been done before.

Acknowledgements

The authors wish to thank the Faculty of Engineering and Computer Science Universitas Komputer
Indonesia for technical support. The Research presented in this paper has been done in the Laboratory of
Accounting Information Systems, Universitas Komputer Indonesia.

References

Casillas, A., Ezeiza, N., Goenaga, I., Pérez, A., & Soto, X. (2019). Measuring the effect of different types of
unsupervised word representations on Medical Named Entity Recognition. International Journal of Medical
Informatics, 129, 100–106. https://doi.org/10.1016/j.ijmedinf.2019.05.022
Cho, M., Ha, J., Park, C., & Park, S. (2020). Combinatorial feature embedding based on CNN and LSTM for
biomedical named entity recognition. Journal of Biomedical Informatics, 103, 103381.
https://doi.org/10.1016/j.jbi.2020.103381
Chukwuocha, C., Mathu, T., & Raimond, K. (2018). Design of an interactive biomedical text mining
framework to recognize real-time drug entities using machine learning algorithms. Procedia Computer
Science, 143, 181–188. https://doi.org/10.1016/j.procs.2018.10.374
Fisch, C., & Block, J. (2018). Six tips for your (systematic) literature review in business and management
research. Management Review Quarterly, 68(2), 103–106. https://doi.org/10.1007/s11301-018-0142-x
Giarsyani, N. (2020). Komparasi Algoritma Machine Learning dan Deep Learning untuk Named Entity
Recognition : Studi Kasus Data Kebencanaan. Indonesian Journal of Applied Informatics, 4(2), 138.
https://doi.org/10.20961/ijai.v4i2.41317
Gligic, L., Kormilitzin, A., Goldberg, P., & Nevado-Holgado, A. (2019). Named entity recognition in
electronic health records using transfer learning bootstrapped neural networks. ArXiv, 121, 132–139.
Phan, R., Luu, T. M., Davey, R., & Chetty, G. (2019). Biomedical named entity recognition based on hybrid
multistage cnn-rnn learner. Proceedings - International Conference on Machine Learning and Data
Engineering, ICMLDE 2018, 136–141. https://doi.org/10.1109/iCMLDE.2018.00032
Suárez-Paniagua, V., Rivera Zavala, R. M., Segura-Bedmar, I., & Martínez, P. (2019). A two-stage deep

E- Proceedings of The 5th International Multi-Conference on Artificial Intelligence Technology (MCAIT 2021) [177]
Artificial Intelligence in the 4th Industrial Revolution