Analisis Perbandingan Sentimen Pengguna iPusnas dan JakLITera dengan Algoritma SentiWordNet

Authors

Putri Fajar Ayu Hendrayani, Master of Library and Information Sciences, Universitas IndonesiaFollow
Rahmi Rahmi, Department of Library and Information Sciences, Universitas Indonesia

Abstract

iPusnas and JakLITera are two national digital library applications developed to enhance public access to literacy in Indonesia. This study compares user perceptions of both applications through sentiment analysis using the SentiWordNet (Sentiment WordNet) algorithm, implemented in Orange data mining software. The dataset comprises user comments from the Google Play Store, collected between 2023 and 2025. A qualitative, lexicon-based method was applied to classify sentiments into positive, neutral, and negative categories. Results show that iPusnas is dominated by negative sentiment (47%), mainly due to technical issues such as bugs, login failures, and slow performance. In contrast, JakLITera received 55% positive sentiment, largely due to the ease of reservation features, although OTP verification issues remain. The findings indicate that iPusnas is dominated by negative sentiment due to technical issues such as login failures and slow loading times, despite its strength in providing a wide range of digital collections. In contrast, JakLITera demonstrates relatively more positive responses owing to the efficiency of its reservation feature, although it remains constrained by account verification problems and limited collections.

Bahasa Abstract

Aplikasi iPusnas dan JakLITera merupakan dua platform perpustakaan digital nasional yang dikembangkan untuk memfasilitasi akses literasi masyarakat Indonesia. Penelitian ini membandingkan persepsi pengguna terhadap kedua aplikasi tersebut melalui analisis sentimen menggunakan algoritma SentiWordNet (Sentiment WordNet) yang diimplementasikan dalam perangkat lunak Orange data mining. Data berupa komentar pengguna di Google Play Store dikumpulkan selama periode 2023–2025. Pendekatan yang digunakan bersifat kualitatif dengan metode lexicon-based untuk mengelompokkan sentimen menjadi positif, netral, dan negatif. Hasil menunjukkan bahwa iPusnas didominasi oleh sentimen negatif (47%) akibat kendala teknis seperti bug, kegagalan login, dan lambatnya performa aplikasi. Sebaliknya, JakLITera menerima 55% sentimen positif, terutama karena kemudahan fitur reservasi, meskipun masih terdapat keluhan terkait verifikasi OTP. Hasil temuan menunjukkan bahwa iPusnas menghadapi dominasi sentimen negatif akibat kendala teknis seperti gagal login dan loading memakan waktu, meskipun unggul dalam ketersediaan koleksi digital. Sebaliknya, JakLITera relatif lebih positif berkat efisiensi fitur reservasi, namun masih terkendala pada proses verifikasi akun dan keterbatasan koleksi.

References

user-centered design (perancangan berbasis pengalaman pengguna) sebaiknya diterapkan secara menyeluruh dalam pengembangan UI/UX, agar antarmuka tetap ramah pengguna dan inklusif. Pengembang juga dianjurkan untuk menyediakan saluran komunikasi terbuka dengan pengguna, baik melalui fitur pelaporan di dalam aplikasi maupun forum umpan balik yang terintegrasi, sehingga setiap masukan dapat segera ditindaklanjuti dan diterjemahkan ke dalam pengembangan fitur yang lebih responsif. Dengan strategi ini, aplikasi perpustakaan digital dapat menjalankan fungsinya secara optimal dalam menyediakan layanan informasi yang berkelanjutan, inklusif, dan berbasis kebutuhan pengguna.

Daftar Pustaka

Adeleke, A. A., & Durodolu, O. O. (2025). Trends in library and information services.

Arnepalli, K., & Rao, K. S. (2020). The pace of digital libraries: Academic libraries perspective. Library Philosophy and Practice, 2020, 1–10.

B. Shelke, M., Sawant, D. D., Kadam, C. B., Ambhure, K., & Deshmukh, S. N. (2023). Marathi SentiWordNet: A lexical resource for sentiment analysis of Marathi. Concurrency and Computation: Practice and Experience, 35(2), e7497.

Becerra, B. B., Reyes, S. V., Hernández, A. G., Elizondo, P. V., & González, A. M. (2021). Good practice guide for data visualization in the area of descriptive statistics. 2021 Mexican International Conference on Computer Science (ENC), 1–8.

Bittner, D., Hauser, F., Engl, F., & Mottok, J. (2025). Eye Movement Modelling Examples on Usability Heuristics. Proceedings of the 6th European Conference on Software Engineering Education, 106–114.

Chalkias, I., Tzafilkou, K., Karapiperis, D., & Tjortjis, C. (2023). Learning analytics on YouTube educational videos: Exploring sentiment analysis methods and topic clustering. Electronics, 12(18), 3949.

Folmer. (2023). Dispusip Luncurkan Aplikasi Jaklitera dan Kukuhkan Duta Baca Jakarta 2023. Berita Jakarta.

Green, R. (2023). Descriptive statistics. In Statistical Analyses for Language Testers (pp. 41–55). Springer.

Haja, S. S., & Fauziah, K. (2022). Strategi optimalisasi layanan e-Resources Perpustakaan Nasional Republik Indonesia di masa pandemi COVID-19. BACA: Jurnal Dokumentasi Dan Informasi, 43(1), 1–14.

Holland, B., & Sinha, K. (2024). Handbook of research on innovative approaches to information technology in library and information science. IGI Global.

Hung, C., Wu, W.-R., & Chou, H.-M. (2021). Improvement of sentiment analysis via re-evaluation of objective words in SenticNet for hotel reviews. Language Resources and Evaluation, 55(2), 585–595.

Jacobs, A. M., & Kinder, A. (2019). Computing the affective-aesthetic potential of literary texts. AI, 1(1), 11–27.

Johnson, S., Baksh, F., & Zorec, M. B. (2025). Evaluating Lexicon-Based Sentiment Analysis Methods for Small Datasets on Low Compute Devices. International Conference on Human-Computer Interaction, 218–228.

Joukov, A., & Joukov, N. (2023). Six-Year Study of Emails Sent to Unverified Addresses. International Symposium on Human Aspects of Information Security and Assurance, 337–345.

Mdaka, D. R., Muchenje, T., Tshilongamulenzhe, T. M., & Mathonsi, T. E. (2024). A Multimodal Authentication Method for Electronic Exams. 2024 International Conference on Artificial Intelligence, Big Data, Computing and Data Communication Systems (IcABCD), 1–5.

Mijač, T., Jadrić, M., & Ćukušić, M. (2024). The role of user experience and co-creation in measuring the success of digital services in higher education. Behaviour & Information Technology, 43(6), 1219–1240.

Muñoz, A. Y. V., i Saltiveri, A. G., & Ordoñez, C. A. C. (2025). Analysis and Optimization of the Usability of E-Commerce Platforms through Evaluation Heuristics. CLEI Electronic Journal, 28(1), 4: 1-4: 17.

Musfiroh, D., Khaira, U., Utomo, P. E. P., & Suratno, T. (2021). Analisis Sentimen terhadap Perkuliahan Daring di Indonesia dari Twitter Dataset Menggunakan InSet Lexicon: Sentiment Analysis of Online Lectures in Indonesia from Twitter Dataset Using InSet Lexicon. MALCOM: Indonesian Journal of Machine Learning and Computer Science, 1(1), 24–33.

Padmanandam, K., Bheri, S. P. V. D. S., Vegesna, L., & Sruthi, K. (2021). A speech recognized dynamic word cloud visualization for text summarization. 2021 6th International Conference on Inventive Computation Technologies (ICICT), 609–613.

Qin, P. (2024). Processing web evaluations through sentiment analysis. IET Conference Proceedings CP895, 2024(19), 168–173.

Quiñones, D., Rusu, C., Arancibia, D., González, S., & Saavedra, M. J. (2020). SNUXH: A set of social network user experience heuristics. Applied Sciences, 10(18), 6547.

Rahayu, S., Mz, Y., Bororing, J. E., & Hadiyat, R. (2022). Implementasi Metode K-Nearest Neighbor (K-NN) untuk Analisis Sentimen Kepuasan Pengguna Aplikasi Teknologi Finansial FLIP. Edumatic J. Pendidik. Inform, 6(1), 98–106.

Ranathunga, S., & Liyanage, I. U. (2021). Sentiment analysis of sinhala news comments. Transactions on Asian and Low-Resource Language Information Processing, 20(4), 1–23.

Reis, P., Páris, C., & Gomes, A. (2020). An experimental activity to develop usability and UX heuristics. Iberoamerican Workshop on Human-Computer Interaction, 20–29.

Wang, H. (2020). Research on the integration of library e-book borrowing history data based on big data technology. Web Intelligence, 18(2), 111–120.

Wang, X., Wang, Y., Guo, L., Xu, L., Gao, B., Liu, F., & Li, W. (2021). Exploring clustering-based reinforcement learning for personalized book recommendation in digital library. Information (Switzerland), 12(5), 198.

Zhou, W. (2024). IoT-Enabled Innovative Environment with Efficient Routing for the Digital Library Services to Examine the Behavior of Users. International Journal of Maritime Engineering, 1(1), 663–674.

Recommended Citation

Hendrayani, Putri Fajar Ayu and Rahmi, Rahmi (2025) "Analisis Perbandingan Sentimen Pengguna iPusnas dan JakLITera dengan Algoritma SentiWordNet," Jurnal Ilmu Informasi, Perpustakaan dan Kearsipan: Vol. 27: No. 2, Article 2.
DOI: 10.7454/JIPK.v27i2.1132
Available at: https://scholarhub.ui.ac.id/jipk/vol27/iss2/2