Application of Natural Language Processing Based on Machine Learning and IoT Data
Keywords:
IoT, Natural Language Processing, Machine Learning, Naive Bayes, TF-IDF, Real-time Monitoring, Data MultiformatAbstract
The development of the Internet of Things (IoT) and Natural Language Processing (NLP) has opened new opportunities to build intelligent monitoring systems capable of processing multiformat data simultaneously. This study aims to apply machine learning–based NLP methods to analyze IoT data in order to improve the accuracy of real-time environmental condition detection. The dataset used consists of temperature and humidity parameters collected from IoT sensors, as well as textual data in the form of environmental condition reports. The textual data are processed through tokenization, lowercasing, stopword removal, stemming, and lemmatization, followed by feature extraction using Term Frequency–Inverse Document Frequency (TF-IDF). The Naive Bayes algorithm is employed to classify conditions into Normal, Warning, and Critical based on a combination of sensor data and textual features. The experimental results show that integrating NLP with IoT data increases classification accuracy from 82% (using sensor data alone) to 91% and enables automatic, real-time condition detection. This study demonstrates that multiformat data integration through NLP and machine learning can enhance the effectiveness of intelligent monitoring systems and can be implemented in environmental, industrial, healthcare, and security domains, thereby making a significant contribution to data-driven decision-making.
References
Fathoni, F. A. Pemanfaatan Machine Learning dan Natural Language Processing (NLP) dalam Deteksi dan Mitigasi Ancaman Social Engineering.
Muzakir, A., Komari, A., & Ilham, M. (2024). Penerapan Konsep Machine Learning & Deep Learning. Asosiasi Dosen Sistem Informasi Indonesia.
Prabowo, K. M., MSi, M., Nidauddin, I., Kom, S., Kom, M., Andiono, E., & Risti, S. F. INTEGRASI IOT DAN ANALISIS SENTIMEN MEDIA SOSIAL UNTUK MANAJEMEN REPUTASI PERGURUAN TINGGI BERBASIS AI MENGGUNAKAN DEEP LEARNING DI INDONESIA.
Purwitasari, N. A., & Soleh, M. (2022). Implementasi Algoritma Artificial Neural Network Dalam Pembuatan Chatbot Menggunakan Pendekatan Natural Language Parocessing. Jurnal Ilmu Pengetahuan dan Teknologi, 6(1).
Artono, B., & Putra, R. G. (2018). Penerapan internet of things (IoT) untuk kontrol lampu menggunakan arduino berbasis web. Jurnal Teknologi Informasi Dan Terapan, 5(1), 9-16.
Tarumingkeng, R. C. (2024). Natural Language Processing (NLP). RUDYCT e-PRESS, no.
Ohyver, D. A., Sa'dianoor, S. D., Junaidi, S., & Adawiyah, R. (2024). Buku Ajar Kecerdasan Buatan. PT. Sonpedia Publishing Indonesia.
Rojabi, M. A. (2025). Pengantar Artificial Intelligence (AI). Afdan Rojabi Publisher.
Sihombing, D. O. (2022). Implementasi Natural Language Processing ( NLP ) dan Algoritma Cosine Similarity dalam Penilaian Ujian Esai Otomatis. 4, 396–406. https://doi.org/10.30865/json.v4i2.5374
Syahfitri, A. (2025). Internet of Things (IoT), Sejarah, Teknologi, dan Penerapannya. Uranus: Jurnal Ilmiah Teknik Elektro, Sains dan Informatika, 3(1), 113-120.
Wijoyo, A., Saputra, A. Y., Ristanti, S., Sya’ban, S., Amalia, M., & Febriansyah, R. (2024). Pembelajaran Machine Learning. OKTAL (Jurnal Ilmu Komput. dan Sci., vol. 3, no. 2, pp. 375–380, 2024,[Online]. Available: https://journal. mediapublikasi. id/index. php/oktal/article/view/2305.
Muflikhah, L., Mahmudy, W. F., & Kurnianingtyas, D. (2023). Machine Learning. Universitas Brawijaya Press.
Widiantoro, A. D., & Ridwan, S. (2024). PENGANTAR NLP DAN TOPIK MODEL LDA.
Rachman, A., Mumpuni, I. D., Dewa, W. A., Widarti, D. W., Islamiah, F., Kurniawan, E., ... & Atikah, L. (2025). Big Data dan Manajemen Basis Data Terdistribusi. Penerbit Mifandi Mandiri Digital, 1(02).
Septiani, D., & Isabela, I. (2022). Analisis term frequency inverse document frequency (tf-idf) dalam temu kembali informasi pada dokumen teks. Sistem dan Teknologi Informasi Indonesia (SINTESIA), 1(2), 81-88.
