Klasifikasi Teks menggunakan Genetic Programming dengan Implementasi Web Scraping dan Map Reduce

Classification of text documents on online media is a big data problem and requires automation. Research has developed classification system with pre-processing using map-reduce web scraping collection. This study aims to evaluate performance by combining genetic programming algorithms, for processing large in the form text. Data collection was carried out observing web-based scraping. collected reducing 8126 duplicates. Map-reduce tokenized stopped-word removal 28507 terms 4306 unique 24201 duplication terms. Text evaluation shows that single tree produces better accuracy (0.7072) than decision (0.6874), lowest multi-tree (0.6726). For acquisition support values multi-tree, highest average 0.3854, followed 0.3584 smallest 0.3494. In general, amount not line value achieved.