Ideal Keyword Match in a Big Data Application Using Keyword Aware Service Recommendation Method

Abstract

The big data movement additionally influenced service recommender systems. The emergence of alternative providers has created a big research issue in providing clients with relevant suggestions for services they want. Service recommender systems have proven to be helpful tools that help users manage the multitude of services at their disposal and provide pertinent recommendations. Because the quantity of customers, services, and other online information is growing exponentially, service recommender systems function in a "Big Data" context. This poses serious challenges for these systems. In this work, we address these difficulties by contributing the following: This makes use of a collaborative filtering algorithm that is user-input driven. Keywords extracted from user reviews reflect their preferences here. Additionally, we apply it to Hadoop, a distributed computing framework that builds on Map Reduce for processing. by applying a collaborative filtering process that is user-based. In the proposed system, we are using a user-based Collaborative Filtering method. It also has similarities to the existing system. We consider both customer reviews and company rankings. We provide KASR, a method for keyword-aware service recommendation. Key words in KASR serve as indicators of users' preferences, and recommendations are produced by a user-based Collaborative Filtering algorithm. A domain thesaurus and keyword-candidate list are provided to help better understand the preferences of the customers. The active user indicates their choices by selecting keywords and preferences from the keyword-candidate list.