FRECOMTWEET: PRODUCT RECOMMENDATION APPLICATION USING FRIENDSHIP CLOSENESS ON TWITTER

Abstract

The information and communication technology development makes someone interact with each other easier. This convenience is used to exchange ideas, like using social media Twitter for product recommendations before buying it. It brings up a trend that consumers seek product recommendations through other people on social media. Social media, especially Twitter, has several features such as tweets, ReTweet and mentions to interact with other people. Users can describe the product, attach a link, and give a positive or negative rating in a tweet. These types of tweets can be used as an alternative to product recommendations. FrecomTweet is an Android-based product recommendation application that can detect close friendships based on the user’s ReTweet and mentions. This application also detects a product recommendation that appears in a conversation between users. This detection uses the keyword filtering method, which matches the conversation content with the markers in the database. If the conversation has a positive rating, it will recommend the user’s closest friends. This research uses a crawling method with the Twitter API streaming filter built using the CodeIgniter framework. The results of the black box test show that Twitter user conversations can be used as a product recommendation with a precision and recall value of 0.94 and 0.81, respectively.