With the progress and development in information technology, the Internet has become the main channel for consumers to receive information and share opinions. Review websites are the most popular platform for consumers to browse information and search. However, nowadays, consumers are accustomed to reading online reviews before they have purchase intention. In addition, most of the writings on the review websites originate from the personal experience of other consumers. Moreover, there are mixed positive and negative opinions and viewpoints. Consumers can look over the online reviews of the product to understand its characteristics and other consumers’ opinions about the purchase. Based on the theory of reasoned action, this research explores the influence of online reviews, attitudes and subjective norms on consumers purchase intention. Questionnaires were collected through the Internet to gather data. In total, 395 valid samples were collected and all hypotheses tests were performed using SPSS. The results of the research show that online reviews, attitudes and subjective norms have positive effects on consumers’ purchase intention.

Chili is one of the important horticultural plants in Indonesia. The price of chili has drastically increased in the market due to the scarcity of chili plants. The scarcity is caused by erratic weather changes, which resulted in many chili plantations experiencing crop failure, due to diseases that attack chili plants so that yields are reduced. This research will implement Deep Learning for image processing into disease detection systems. This disease detection system will be used to help users, especially chilli farmers to detect whether the leaves of their chili plants are infected by the disease or not. This system will take a picture of chili leaves using a Raspberry Pi camera and image processing on the chili leaf image to obtain important information about the image to find out whether the chili leaves are infected by disease or not. The purpose of this study is to create a desktop application for a disease detection system that has the ability to detect whether or not a chili leaf is infected by several diseases, display the condition of the chili leaves, display the type of disease that infects the chili leaves (if any), and provide a percentage probability of the system in detecting images of the chili leaves correctly (whether it is healthy chili leaves or diseased chili leaves).