Abstract:
Mining customer opinions from hotel reviews is useful. The results can then be used to help customers in choosing the most suitable hotel. In this research, a technique for mining opinions from big data of Indonesian hotel reviews, which is based on MapReduce, is developed. To avoid iterative computations, we adopt look-up table approach. The experiments for evaluating the performance of the technique were conducted on a Hadoop cluster with 14 clients. The results shw that the proposed technique discovers useful opinion summary and is scalable.