Aspect-based Opinion Summarization for Disparate Features

Computer Engineering

Significant advancement in e-commerce has led to the invention of several websites selling products online. These websites also facilitate the buyers to express their opinions about the products & their features in the form of reviews. Knowing these opinions and the related sentiments plays an important role in decision making processes involving regular customers to executive managers. But these reviews are available in huge numbers hence referring them becomes a practically impossible task to achieve. Thus a new orientation called Opinion Mining & Summarization has emerged to deal with the problem. Aspect-based (Feature-based) Opinion Summarization is one of these summarization techniques which provide brief yet most relevant information about different features related to the target product. Hence the approach is in great demand nowadays because it exactly shows what a customer usually tries to search while referring the reviews. This paper focuses on extraction of different kinds of features associated with a target entity. Current state of the art suggests that concrete techniques are highly required for identification of those features which are not clearly mentioned. Thus our prime target is to deliver a succinct solution for effective identification of implicit features along with the explicit ones based on the opinion words encountered in user reviews. This is achieved by first extracting and processing the explicit features and then using them for the identification of implicit features. Finally summarization of sentences containing both kinds of aspects is done.

This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.