Pembentukan Dataset Token Sentimen Berdasarkan Akun Instagram Brand Elektronik Menggunakan K-Nearest Neighbors
DOI:
https://doi.org/10.24002/jbi.v12i1.4472Abstract
Abstract. Generating Sentiment Token Dataset Based on Electronics Brand Instagram Account using K-Nearest Neighbors. Instagram is currently one of the most popular social media platforms for businesses and brand owners to promote their products. Because Instagram is a two-way communication platform, people can respond to any promotional content posted on Instagram. People's reactions come in a variety of form, and frequently include both positive and negative sentiment. This study aims to identify the words used in one type of sentiment, then use the K-NN approach to construct a token dataset by summarizing the phrases in many labels according to the sentiment type. The total accuracy value of the dataset for K = 1 is 33.38% (positive), 59.96% (negative), and 56.60% (neutral) based on the results of the tests performed.
Keywords: sentiment analysis, K-Nearest Neighbors, dataset, Instagram
Abstrak. Instagram saat ini menjadi salah satu media sosial yang banyak digunakan oleh perusahaan atau pemilik brand untuk melakukan promosi terhadap produk-produk yang dimilikinya. Karena bersifat dua arah, masyarakat dapat memberikan respon terhadap aktivitas promosi yang dilakukan oleh sebuah perusahaan melalui Instagram. Respon dari masyarakat memiliki varian yang beragam dan seringkali mengandung unsur sentimen baik positif maupun negatif. Penelitian ini mencoba untuk mengidentifikasi kata-kata yang digunakan dalam satu jenis sentimen, kemudian membuat dataset token dengan cara merangkum kata-kata tersebut dalam beberapa label sesuai jenis sentimen masing-masing menggunakan metode K-NN. Berdasarkan hasil pengujian yang dilakukan, didapatkan nilai akurasi dari dataset sebesar 33.38% (positif), 59.96% (negatif), dan 56.60% (netral) untuk K = 1.
Kata Kunci: analisis sentimen, K-Nearest Neighbors, dataset, Instagram
References
M. Iqbal, “Instagram Revenue and Usage Statistics (2021),” Business of Apps, 8 Maret 2021. [Online]. Available: https://www.businessofapps.com/data/instagram-statistics/. [Diakses 14 Maret 2021].
H. Tankovska, “Distribution of Instagram users worldwide as of January 2021, by age group,” Statista, 10 Februari 2021. [Online]. Available: https://www.statista.com/statistics/325587/instagram-global-age-group/. [Diakses 12 Maret 2021].
Y. Yao, J. Zhang, F. Shen, L. Liu, F. Zhu, D. Zhang dan H. T. Shen, “Towards Automatic Construction of Diverse, High-Quality Image Datasets,” IEEE Transactions on Knowledge and Data Engineering, vol. 32, no. 6, pp. 1199 - 1211, 2019.
V. Vonikakis, R. Subramanian dan S. Winkler, “Shaping datasets: Optimal data selection for specific target distributions across dimensions,” dalam 2016 IEEE International Conference on Image Processing (ICIP), Phoenix, AZ, USA, 2016.
X. Tang, Z. Huang, D. Eyers, S. Mills dan M. Guo, “Scalable Multicore k-NN Search via Subspace Clustering for Filtering,” IEEE Transactions on Parallel and Distributed Systems, vol. 26, no. 12, pp. 3449 - 3460, 2014.
K. A. Nugraha dan D. Sebastian, “Analisis Trend Akun Media Sosial Twitter Menggunakan TF-IDF dan Cosine Similarity,” dalam Seminar Nasional ReTII ke-13, Yogyakarta, Indonesia, 2018.
H. T. Phan, V. C. Tran, N. T. Nguyen dan D. Hwang, “Improving the Performance of Sentiment Analysis of Tweets Containing Fuzzy Sentiment Using the Feature Ensemble Model,” IEEE Access, vol. 8, pp. 14630 - 14641, 2020.
L. Yang, Y. Li, J. Wang dan R. S. Sherratt, “Sentiment Analysis for E-Commerce Product Reviews in Chinese Based on Sentiment Lexicon and Deep Learning,” IEEE Access, vol. 8, no. IEEE, pp. 23522 - 23530, 2020.
S. Zhang, D. Zhang, H. Zhong dan G. Wang, “A Multiclassification Model of Sentiment for E-Commerce Reviews,” IEEE Access, vol. 8, pp. 189513 - 189526, 2020.
S. Aloufi dan A. E. Saddik, “Sentiment Identification in Football-Specific Tweets,” IEEE Access, vol. 6, pp. 78609 - 78621, 2018.
P.-H. Lin, A. Wooders, J. T.-Y. Wang dan W. M. Yuan, “Artificial Intelligence, the Missing Piece of Online Education?,” IEEE Engineering Management Review, vol. 46, no. 3, pp. 25 - 28, 2018.
J. Kong, M. Chen, M. Jiang, J. Sun dan J. Hou, “Face Recognition Based on CSGF(2D)2PCANet,” IEEE Access, vol. 6, pp. 45153 - 45165, 2018.
M. C. Canellas, K. M. Feigh dan Z. K. Chua, “Accuracy and Effort of Decision-Making Strategies With Incomplete Information: Implications for Decision Support System Design,” IEEE Transactions on Human-Machine Systems , vol. 45, no. 6, pp. 686 - 701, 2015.
X. Wang dan H. Ji, “Semi-Supervised Hyperspectral Image Classification Based on Label Propagation via Selected Path,” IEEE Access , vol. 8, pp. 221225 - 221234, 2020.
K. A. Nugraha, W. Hapsari dan N. A. Haryono, “Analisis Tekstur Pada Citra Motif Batik Untuk Klasifikasi Menggunakan K-NN,” Informatika: Jurnal Teknologi Komputer dan Informatika, vol. 10, no. 2, pp. 135-140, 2014.
L. A. Sunjoyo, R. G. Santosa dan K. A. Nugraha, “Implementasi Transformasi Haar Wavelet untuk Deteksi Citra Jeruk Nipis yang Busuk,” Informatika: Jurnal Teknologi Komputer dan Informatika, vol. 12, no. 2, pp. 165-173, 2016.
K. A. Nugraha dan Herlina, “Klasifikasi Pertanyaan Bidang Akademik Berdasarkan 5W1H menggunakan K-Nearest Neighbors,” JEPIN (Jurnal Edukasi dan Penelitian Informatika), vol. 7, no. 1, pp. 44-51, 2021.
K. A. Nugraha, “Deteksi Area Parkir Mobil Berbasis Marker Menggunakan Moment Invariants dan K-NN,” Jurnal Teknik Informatika dan Sistem Informasi (JuTISI), vol. 5, no. 1, pp. 112-121, 2019.
F. Wang, Z. Liu dan C. Wang, “An improved kNN text classification method,” International Journal of Computational Science and Engineering (IJCSE), vol. 20, no. 3, 2019.
K. A. Nugraha dan D. Sebastian, “Pembentukan Dataset Topik Kata Bahasa Indonesia pada Twitter Menggunakan TF-IDF & Cosine Similarity,” Jurnal Teknik Informatika dan Sistem Informasi (JuTISI), vol. 4, no. 3, pp. 376-386, 2018.
Downloads
Published
Issue
Section
License
Copyright of this journal is assigned to Jurnal Buana Informatika as the journal publisher by the knowledge of author, whilst the moral right of the publication belongs to author. Every printed and electronic publications are open access for educational purposes, research, and library. The editorial board is not responsible for copyright violation to the other than them aims mentioned before. The reproduction of any part of this journal (printed or online) will be allowed only with a written permission from Jurnal Buana Informatika.
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
