Streetboba & Gildak Kediri outlet is a restaurant that serves a variety of Korean food menus and various kinds of drinks with boba and jelly toppings that are sold at low prices that suit the student's budget. This restaurant is located in East Java province which is precisely on Jalan Yos Sudarso No.43, Kediri City. With technological advances that continue to grow to affect various aspects, especially in the business and industrial world. Sentiment analysis is a technology that extracts or manages text to be expressed using text that can also be classified into positive and negative polarity. Consumer reviews are a form of communication that occurs in the sales process, the stage where potential buyers receive an explanation of the product posted and buyers receive reviews that explain the advantages or disadvantages of purchasing the product. In this study, sentiment analysis was conducted based on consumer opinions regarding social media accounts. The study aimed to use social media data to assess the service, cleanliness and quality of products offered by categorizing companies as having positive and negative reviews. To classify sentiment, the Naive Bayes method is used, which combines survey data collection methods, questionnaires, and observation data.

Recommendation systems provide ways of directing users to items that may be relevant to them by guiding them to relevant items that will be suitable to the users according to their profiles. Collaborative filtering is one of the most successful and mature techniques of recommender system because of its domain independent ability. Bayesian Personalized Ranking Smart Linear Model (BPRSLIM) is model-based collaborative filtering (CF) recommendation algorithm that usually reconstructs a scanty user-item matrix directly; also, using only user-rating matrix usually prevents the algorithm from accessing relevant information that could enhance its recommendation accuracy. Therefore, this work reconstructs BPRSLIM user-item rating matrix via item feature information in order to improve its performance accuracy. Comprehensive experiments were carried out on a real-world dataset using different evaluation metrics.  The performance of the model showed significant improvement in recommendation accuracy when compared with other top-N collaborative filtering-based recommendation algorithms, especially in precision and nDCG with 30.6% and 22.1% respectively.