ABSTRACT

Data mining is a technique of collecting, searching through, and analyzing a huge amount of data stored in a database, as to determine patterns or relationships. Sequences of challenges have emerged in data mining and in that one of the major challenges is opinion mining. Opinion mining is the field of study which works with people appraisals, opinions, sentiments and emotion towards the entities such as products, services. The main aim is to gather the opinion regarding the products from the online review websites. A real online review from different domains is selected as the evaluation datasets. This method is compared with several state-of-the-art methods on opinion target/word extraction. It is assumed that all nouns/noun phrases in sentences are opinion target candidates and all adjectives/verbs are considered as potential opinion words, which are generally adopted by earlier methods.