Hybrid Algorithm to Evaluate E-Business Website Comments

Online reviews are considered of an important indicator for users to decide on the activity theywish to do, whether it is watching a movie, going to a restaurant, or buying a product. It also servesbusinesses as it keeps tracking user feedback. The sheer volume of online reviews makes it difficultfor a human to process and extract all significant information to make purchasing choices. Asa result, there has been a trend toward systems that can automatically summarize opinions from aset of reviews. In this paper, we present a hybrid algorithm that combines an auto-summarizationalgorithm with a sentiment analysis (SA) algorithm, to offer a personalized user experiences andto solve the semantic-pragmatic gap. The algorithm consists of six steps that start with the originaltext document and generate a summary of that text by choosing the N most relevant sentences inthe text. The tagged texts are then processed and then passed to a Naive Bayesian classifier alongwith their tags as training data. The raw data used in this paper belong to the tagged corpus positiveand negative processed movie reviews introduced in [1]. The measures that are used to gaugethe performance of the SA and classification algorithm for all test cases consist of accuracy, recall,and precision. We describe in details both the aspect of extraction and sentiment detection modulesof our system.