ONLINE REVIEW MINING FOR FORECASTING SALES

Nihalahmad R. Shikalgar, Deepak Badgujar

Abstract: The growing popularity of online product review forums invites people to express opinions and sentiments toward the products .It gives the knowledge about the product as well as sentiment of people towards the product. These online reviews are very important for forecasting the sales performance of product. In this paper, we discuss the online review mining techniques in movie domain. Sentiment PLSA which is responsible for finding hidden sentiment factors in the reviews and ARSA model used to predict sales performance. An Autoregressive Sentiment and Quality Aware model (ARSQA) also in consideration for to build the quality for predicting sales performance. We propose clustering and classification based algorithm for sentiment analysis.

Keywords: Online Review mining, Text mining,reviews, S-PLSA, ARSA, Clustering, Classification.

DOI: https://doi.org/10.15623/ijret.2013.0212009