Analisis Sentimen Mengenai Produk Toyota Avanza Menggunakan Metode Learning Vector Quantization Versi 3 (LVQ 3) dengan Seleksi Fitur Chi Square, Lexicon-Based Features serta Normalisasi Min-Max

Jonathan Reynaldo (Fakultas Ilmu Komputer, Universitas Brawijaya)
Putra Pandu Adikara (Fakultas Ilmu Komputer, Universitas Brawijaya)
Randy Cahya Wihandika (Fakultas Ilmu Komputer, Universitas Brawijaya)

Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer
Vol 4 No 3 (2020): Maret 2020

Car is a means of transportation used by peoples with some excellence and comfort values for better driving experience. Toyota as the manufacturer of Toyota Avanza needs people's opinions to upgrade their products. Opinions from social media need to be classified as positive, neutral or negative opinions so sentiment analysis is needed. For analyzing a sentiment, Learning Vector Quantization 3 (LVQ 3) is used in this research. Chi Square feature selection, lexicon-based features and min-max normalization are used in this research too. Evaluation using confusion matrix with 240 training data and 60 testing data results the accuracy of 38,33% using features from Chi Square feature selection, 33,33% using lexicon-based features, and 36,67% using both of Chi Square feature selection and lexicon-based features.