Abstract

Abstract - Digital platforms are growing day by day, as people invest a large time in them. So humanthoughts for any product, service, organization are easily available on this media platform. Analysis of user comments was done by text mining for understanding the status of any service or product. The sentiment of signed network video was extracted in the form of positive or negative class. This paper has proposed a signed network analysis method for Sentiment Detection in online video. Collective Volitive and Feedingoperator has increased the sentiment performance of work as well. Patterns are extractedfrom the input content, and as per the signed algorithm, the output class was assigned to the patterns. The experiment was performed on a real video (digital) having two sentiment classes. Results show that the proposed work has increased the evaluation parameter values as compared to another existing algorithm. In this paper, a novel method for extracting the hierarchical structure of Web video groups based on sentiment-aware signed network analysis is presented to realize Web video retrieval. First, the proposed method estimates latentlinks between Web videos by using multimodal features of contents and sentiment features obtained fromtexts attached to Web videos. Thus, our method enables construction ofa signed network that rejects notonly similarities but also positive and negative relations between topicsof Web videos. The first attempt to utilize sentiment analysis for Web video grouping and a novel algorithm for analyzing a weighted signednetwork derived from sentiment and multimodal features.Keywords: Web videos, Sentiment Detection, Hierarchy Structure, YouTube, Signed Network.