A New Method for Mining Opinions in Online Reviews Based on Topical Relational Estimation

摘要

Data mining as a subfield of computer science, It can be defined as the computational process of discovering patterns in large data sets ("big data") involving methods at the intersection of artificial intelligence, machine learning, statistics, and database systems. The main goal is to extract information from a data set and transform it into an understandable structure for further use. The data mining involves database and data management aspects, data pre-processing, model and inference considerations, interestingness metrics, complexity considerations, post-processing of discovered structures, visualization, and online updating. The opinion mining which means extracting opinion mining from online reviews that is a quite important task. By extracting opinion targets proposes the novel approach by using partially-supervised word alignment model, on the other hand for capturing the opinion relation more efficiently than the partial supervison from partial alignment links when compared with word-alignment model, the result of mining opinions based on topical-relational estimation will provide better results.