Main Article Content
Abstract
For semantic analysis, various natural language processing processes are used as sub tasks and main aim to find positive and negative sentiment in text, audio or video data. To understand the opinion of person in effective manner, vocal modulations and facial expressions can be merged to extract the features. Thus, by using multimodal methods i.e. combining text, audio and video, the performance of the system can be enhanced. In this paper, a method is proposed which uses audio and visual data to analyse semantics.