PeRView: A Framework for Personalized Review Selection Using Micro-Reviews

Abstract: In the contemporary era, social media has its influence on people in making decisions. The proliferation of online reviews with diversified and verbose content often causes problems inaccurate decision making. Since online reviews have an impact on people of all walks of life while taking decisions, choosing appropriate reviews based on the podsolization consisting is very important since it relies on using such micro-reviews consistency to evaluate the review set section. Micro-reviews are very concise and directly talk about product or service instead of having unnecessary verbose content. Thus, micro-reviews can help in choosing reviews based on their personalized consistency that is related to directly or indirectly to the main profile of the reviews. Personalized reviews selection that is highly relevant with high personalized coverage in terms of matching with micro-reviews is the main problem that is considered in this paper. Furthermore, personalization with user preferences while making review selection is also considered based on the personalized users' profile. Towards this end, we proposed a framework known as PeRView for personalized review selection using micro-reviews based on the proposed evaluation metric approach which considering two main factors (personalized matching score and subset size). Personalized Review Selection Algorithm (PRSA) is proposed which makes use of multiple similarity measures merged to have highly efficient personalized reviews matching function for selection. The experimental results based on using reviews dataset which is collected from YELP.COM while micro-reviews dataset is obtained from Foursqure.COM. show that the personalized reviews selection is a very empirical case of study.