Pengelompokan Artikel Berbahasa Indonesia Berdasarkan Struktur Laten Menggunakan Pendekatan Self Organizing Map

Abstract

Document grouping is a necessity among a large number of articles published on internet. Several attempts have been done to improve this grouping process, while majority of the efforts are based on word appearance. In order to improve its quality, the grouping of documents need to be based on topic similarity between documents, instead of the frequency of word appearance. The topic similarity could be known from its latency, since the similarity of the word interpretation are often used in the same context. In the unsupervised learning process, SOM is often used, in which this approach simplifies the mapping of multi-dimension data. This research result shows that implementation of the latent structure decreases characteristic dimension by 32% of the word appearance, hence makes this approach more time efficient than others. The latent structure, however, when implemented on SOM Algorithm, is capable to obtain good quality result compared to word appearance frequency approach. It is then proven by 5% precision improvement, recall improvement of 3%, and another 4% from F-measure. While the achievement is not quite significant, the quality improvement is able to put the dominance of grouping process, compared to the original classification defined by the content provider.

Aspect based Sentiment Analysis Aduan Mahasiswa UMSIDA Dimasa Pandemi Menggunakan LSTM

“…Analisis opini dapat dianggap sebagai bagian dari penambangan opini [8], dan banyak teknik algoritmik seperti K-NN, pohon keputusan, dan hutan acak dapat digunakan untuk analisis opini [9], yang merupakan hasil penelitian menggunakan LSTM. akurasi sangat tinggi dalam analisis opini pada SemEval 2016 menggunakan algoritma dan arsitektur deep learning [10], dan analisis opini publik yang baik pada berita kesehatan berbahasa Indonesia menggunakan model kalimat berbasis LSTM, mencapai akurasi tinggi [11].…”

Analisis Pendapat Masyarakat terhadap Berita Kesehatan Indonesia menggunakan Pemodelan Kalimat berbasis LSTM

“…Tujuan pengolahan teks yang populer saat ini adalah analisis sentimen dan kategorisasi teks [15], [16]. Namun, penerapan analisis pendapat mulai dilakukan pada berbagai bidang.…”

Self-Training Naive Bayes Berbasis Word2Vec untuk Kategorisasi Berita Bahasa Indonesia

“…Klasifikasi emosi dari teks dengan metode supervised learning, yaitu k-Nearest Neighbour (k-NN) telah dilakukan [10]. Penelitian lain melakukan kategorisasi teks dengan menggunakan struktur laten dan metode unsupervised learning dengan algoritme Self Organizing Map [11]. Klasifikasi teks dengan pendekatan semi-supervised learning Co-Training untuk dokumen website akademik dan email juga telah dilakukan [12], [13].…”