<![CDATA[Information technology with the Internet gives the impact of the development of electronic commerce or e-commerce that gained a lot of popularity. APJII data in 2016 states as many as 130.8 million Indonesians use the internet to offer goods and services. In e-commerce management there is customer service that is tasked to handle all of questions submitted by customers. Submission of information by customer service is usually through a call center or chat application. In thrust the ability of intelligent digital assistants chatbot is widely used to help the work of customer services. It takes an analysis of the customer's language on chatbot in order to be able to recognize what information is contained in the question, so it takes the classification and extracting of information in order to get important information needed by chatbot in answering questions from customers. Named Entity Recognition (NER) is part of the extraction of information assigned to the classification of text from a document or corpus categorized into classes such as person's name, location, month, date, time and so on. Automatic name extraction can be useful for addressing some issues such as translation engines, information retrieval, frequently asked questions and text summary. In this study NER is done using the method of Hidden Markov Model and Rule Template with 6 entities i.e. BRAND, TYPE, PRICE, SPEK, N_SPEK and N_TAG. Overall introduction of entities conducted in this study resulted in the accuracy value in the Rule Template of 97.20% and the accuracy value in the Hidden Markov Model of 92.23%.]]>
Copyrights © 2018
