Affiliation:
1. Department of Information Technology, Karpagam College of Engineering, Coimbatore Tamil Nadu 641021, India
Abstract
Contemporary research in Multimodal Sentiment Analysis (MSA) using deep learning is becoming popular in Natural Language Processing. Enormous amount of data are obtainable from social media such as Facebook, WhatsApp, YouTube, Twitter and microblogs every day. In order to deal with these large multimodal data, it is difficult to identify the relevant information from social media websites. Hence, there is a need to improve an intellectual MSA. Here, Deep Learning is used to improve the understanding and performance of MSA better. Deep Learning delivers automatic feature extraction and supports to achieve the best performance to enhance the combined model that integrates Linguistic, Acoustic and Video information extraction method. This paper focuses on the various techniques used for classifying the given portion of natural language text, audio and video according to the thoughts, feelings or opinions expressed in it, i.e., whether the general attitude is Neutral, Positive or Negative. From the results, it is perceived that Deep Learning classification algorithm gives better results compared to other machine learning classifiers such as KNN, Naive Bayes, Random Forest, Random Tree and Neural Net model. The proposed MSA in deep learning is to identify sentiment in web videos which conduct the poof-of-concept experiments that proved, in preliminary experiments using the ICT-YouTube dataset, our proposed multimodal system achieves an accuracy of 96.07%.
Publisher
World Scientific Pub Co Pte Lt
Subject
Computer Science (miscellaneous),Computer Science (miscellaneous)
Cited by
29 articles.
订阅此论文施引文献
订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献