Analisis Sentimen Ulasan Penggunaan Aplikasi GetContact Menggunakan Orange Data Mining sebagai Dasar Strategi Peningkatan Kualitas Layanan
DOI:
https://doi.org/10.35473/ikn.v3i2.5563Keywords:
Analisis Sentimen, Orange Data Mining, GetContact, Ulasan Pelanggan, Strategi Bisnis.Abstract
The growth of phone number identification applications drives companies to continuously improve service quality to meet user needs and expectations. User reviews available on the Google Play Store serve as a valuable source of information for evaluating service quality. This study aims to analyze the sentiment of user reviews for the GetContact application to inform strategies for enhancing service quality. The dataset, obtained publicly from Kaggle, comprises 1,000 user reviews of the GetContact application. Analysis was conducted using Orange Data Mining, involving stages such as text preprocessing, word cloud visualization, and sentiment categorization. Sentiment labels were assigned based on user ratings: ratings of 1–2 indicated negative sentiment, a rating of 3 indicated neutral sentiment, and ratings of 4–5 indicated positive sentiment. The results show that 49.50% of the reviews reflected positive sentiment, 40.60% reflected negative sentiment, and 9.90% reflected neutral sentiment. Word cloud visualization revealed that words such as "helpful," "app," "number," and "update" frequently appeared in reviews containing complaints. These findings indicate that while the majority of users responded positively to the application's core functionality, the company still needs to improve service quality—specifically regarding system stability, the authentication process, and the development of premium features. The study's findings are expected to assist the company in formulating strategies to enhance service quality and customer satisfaction.
ABSTRAK
Perkembangan aplikas identifikasi nomor telpon mendorong perusahaan untuk terus meningkatkan kualitas layanan agar mampu memenuhi kebutuhan dan harapan pengguna.salah satu sumber informasi yang dimanfaatkan untuk mengevaluasi kualitas layanan adalah ulasan pengguna yang tersedia pada Google Play Store. Penelitian ini bertujuan untuk menganalisis sentimen ulasan pengguna aplikasi GetContact sebagai sumber dalam penyusunan strategi peningkatan kualitas layanan. Data set yang merupakan dataset publik yang di peroleh dari kaggle, terdiri atas 1.000 ulasan pengguna aplikasi GetContact. Proses analisis dilakukan menggunakan orange data mining melalui tahapan text preprocessing, visualisasi word cloud, dan pengelompokan sentimen. Label sentimen dibentuk berdasarkan nilai rating pengguna, yaitu rating 1-2 sebagai sentimen negatif, reting 3 sebagai sentimen netral, dan 4-5 sebagai sentimen positif. Hasil penelitian menunjukkan bahwa 49,50 % ulasan termasuk sentimen positif. Hasil penelitian menunjukkan bahwa 4,9 50 % ulasan termasuk sentimen positif, 40,60% sentimen negatif, dan 9,90% sentimen netral. Visualisasi word cloud menunjukkan bahwa kata kata seperti membantu, aplikasi, nomor, dan update banyak muncul pada ulasan yang mengandung keluhan. Temua ini menunjukkan bahwa meskipun mayoritas pengguna memberikan tanggapan positif terhadap fungsi utama aplikasi, perusahaan tetap perlu meningkatkan kualitas layanan, khususnya pada aspek stablilitas sistem, proses autentikasi, dan pengembangan fitur preium. Hasil penelitian diharapkan dapat menjadi bahan pertimbangan bagi perusahaan dalam merumuskan strategi peningktana kualitas layanan dan kepuasan pelanggan.
Downloads
References
Ha, J., Kambe, M., & Pe, J. (2012). Data Mining: Concepts and Techniques. In Data Mining: Concepts and Techniques. https://doi.org/10.1016/C2009-0-61819-5
Hennig-Thurau, T., Gwinner, K. P., Walsh, G., & Gremler, D. D. (2004). Electronic word-of-mouth via consumer-opinion platforms: What motivates consumers to articulate themselves on the Internet? Journal of Interactive Marketing, 18(1), 38–52. https://doi.org/10.1002/dir.10073
Kotler, P., Keller, K. L., & Chernev, A. (2022). Marketing Management (16th Global Edition). Pearson.
Liu, B. (2012). Sentiment Analysis and Opinion Mining. Morgan & Claypool Publishers.
Jalilvand, M. R., & Samiei, N. (2012). The effect of electronic word of mouth on brand image and purchase intention: An empirical study in the automobile industry in Iran. Marketing Intelligence & Planning, 30(4), 460-476. https://doi.org/10.1108/02634501211231946
Fauzi, A., & Anjani, S. (2022). Pemanfaatan aplikasi crowdsourced caller id dalam perlindungan data privasi dan pencegahan penipuan digital. Jurnal Teknologi Informasi dan Komunikasi, 11(2), 145-156.
McLean, G., Al-Nabhani, K., & Wilson, A. (2018). Developing a Mobile Applications Customer Experience Model (MACE) - Implications for Retailers. Journal of Business Research, 85, 325-336.
Buntoro, G. A. (2017). Analisis Sentimen Calon Gubernur DKI Jakarta 2017 di Twitter. Jurnal Edukasi dan Penelitian Informatika (JEPIN), 3(1), 32-41.
Sharda, R., Delen, D., & Turban, E. (2018). Business Intelligence, Analytics, and Data Science: A Managerial Perspective (4th ed.). Pearson.
Heimerl, F., Lohmann, S., Lange, S., & Ertl, T. (2014). Word cloud explorer: Text analytics based on word clouds. 2014 47th Hawaii International Conference on System Sciences (pp. 1833-1842). IEEE.
