Comparison Of Cbow And Skip Gram On Sentiment Analysis Of Bus Agents Reviews Using CNN

Fidelis Raymond Jose Airudin, Robertus Setiawan Aji Nugroho

Abstract


Inter-city buses are one of the most popular modes of transportation in Indonesia. Thanks to the massive development and construction of highways by the Indonesian government, today almost every city on the island of Java is connected by toll roads. This makes traveling from one city to another faster, more comfortable, and free from obstacles. This opens up great opportunities for inter-city bus entrepreneurs to attract more passengers. Currently, inter-city bus companies are aggressively rejuvenating their fleet and adding attractive facilities to passengers, so that prospective bus passengers currently have many bus options to choose from. This of course creates a problem especially for new bus users because there are too many options to choose from. If prospective bus users are wrong in choosing a bus, besides the material can be a victim, of course the experience of bus users will also be a victim. Therefore, it is necessary to create a system to detect what is the most dominant sentiment expressed by bus users who have ridden the bus before through a review. To create a system to analyze sentiment, researchers use the Convolutional Neural Network algorithm where for the input layer researchers use a matrix representation of words formed by the word embedding method using the Word2Vec algorithm. As a final result, researchers display the results of the Precision, Recall, and F1-Score calculations which show the quality of the sentiment analysis model created.

Keywords


Intercity Bus; Sentiment Analysis; Word2Vec; CNN; CBOW; Skip Gram

Full Text:

PDF

References


“Pemerintah Agar Beri Insentif Bagi Pengusaha Transportasi Umum,” Koran Jakarta, 2020. https://koran-jakarta.com/pemerintah-agar-beri-insentif-bagi-pengusaha-transportasi-umum/

B. Liu, Sentiment analysis: Mining opinions, sentiments, and emotions, 2nd ed. New York: Cambridge University Press, 2015. doi: 10.1017/CBO9781139084789.

Y. Li and T. Yang, “Word Embedding for Understanding Natural Language: A Survey,” Stud. Big Data, vol. 26, pp. 83–104, 2018, doi: 10.1007/978-3-319-53817-4_4.

T. Mikolov, K. Chen, G. Corrado, and J. Dean, “Efficient estimation of word representations in vector space,” 1st Int. Conf. Learn. Represent. ICLR 2013 - Work. Track Proc., no. October, 2013.

H. woo An and N. Moon, “Design of recommendation system for tourist spot using sentiment analysis based on CNN-LSTM,” J. Ambient Intell. Humaniz. Comput., 2019, doi: 10.1007/s12652-019-01521-w.

L. Zhang, S. Wang, and B. Liu, “Deep learning for sentiment analysis: A survey,” Wiley Interdiscip. Rev. Data Min. Knowl. Discov., vol. 8, no. 4, pp. 1–25, 2018, doi: 10.1002/widm.1253.

V. Oktaviani, B. Warsito, H. Yasin, R. Santoso, and Suparti, “Sentiment analysis of e-commerce application in Traveloka data review on Google Play site using Naïve Bayes classifier and association method,” J. Phys. Conf. Ser., vol. 1943, no. 1, 2021, doi: 10.1088/1742-6596/1943/1/012147.

N. D. Wulandari, M. H. Z. Nuri, and L. Kurniasari, “Customers’ Satisfaction and Preferences Using Sentiment Analysis on Traveloka: The Case of Yogyakarta Special Region Hotels,” Proc. 1st UMGESHIC Int. Semin. Heal. Soc. Sci. Humanit. (UMGESHIC-ISHSSH 2020), vol. 585, pp. 407–416, 2021, doi: 10.2991/assehr.k.211020.058.

F. O. Isinkaye, Y. O. Folajimi, and B. A. Ojokoh, “Recommendation systems: Principles, methods and evaluation,” Egypt. Informatics J., vol. 16, no. 3, pp. 261–273, 2015, doi: 10.1016/j.eij.2015.06.005.

J. Shen, Y. Wei, and Y. Yang, “Collaborative filtering recommendation algorithm based on two stages of similarity learning and its optimization,” in IFAC Proceedings Volumes (IFAC-PapersOnline), 2013, vol. 13, no. PART 1, pp. 335–340. doi: 10.3182/20130708-3-CN-2036.00068.

L. Jiang, Y. Cheng, L. Yang, J. Li, H. Yan, and X. Wang, “A trust-based collaborative filtering algorithm for E-commerce recommendation system,” J. Ambient Intell. Humaniz. Comput., vol. 10, no. 8, pp. 3023–3034, Aug. 2019, doi: 10.1007/s12652-018-0928-7.




DOI: https://doi.org/10.24167/proxies.v9i1.13281

Copyright (c) 2025 Proxies : Jurnal Informatika



View My Stats