期刊名称：International Journal of Innovative Research in Computer and Communication Engineering
印刷版ISSN：2320-9798
电子版ISSN：2320-9801
出版年度：2017
卷号：5
期号：5
页码：9746
DOI：10.15680/IJIRCCE.2017.0505178
出版社：S&S Publications
摘要：There has been big amount of growth of events over the internet in recent years. Google is the primesource of knowledge for any event happening over the internet. Google contains all the repositories of information.Some networking sites such as face book, Twitter contains millions of posts, tweets, images etc happening every dayover each and every day. While on E-commerce sites, description related products; their reviews are available for thecustomers for analyzing various products. Various E-commerce websites like Amazon, Ebay, Flipkart are very popularsites among the users. To model this huge amount of multi-modal data having both textual and visual contents,visualization and analysis of multi-modal data is presented in this paper. While dealing with multi-modality, study ofsemantic relationship between the images and text data is crucial part. This model also helps to study semanticrelationship between them effectively. In topic category some topics are not represented with the help images so thismodel also helps to point out those topics. On some e-commerce shopping sites fake reviews, advertises, spamspreading information is posted. So we have processed the reviews dataset for deciding the overall quality of products.We have collected some reviews and images from Amazon to summarize, analyze and visualize those reviews forbetter understanding. For event analysis the multi-modal data containing documents are downloaded from Google formapping events data. Use of JSON parsers for processing gives the fast and quick results of search in the proposedmodel.
