Multimodal Big Data Affective Analytics

Nusrat Jahan Shoumy; Li-Minn Ang; D M Motiur Rahaman

doi:10.1007/978-3-319-97598-6_3

Back

Book chapter

Peer reviewed

Multimodal Big Data Affective Analytics

Nusrat Jahan Shoumy, Li-Minn Ang and D M Motiur Rahaman

Multimodal Analytics for Next-Generation Big Data Technologies and Applications, pp.45-72

Springer Nature

2019

DOI: https://doi.org/10.1007/978-3-319-97598-6_3

Files and links (1)

url

https://doi.org/10.1007/978-3-319-97598-6_3View

Published Version

Abstract

Big data has generated significant interest in various fields including healthcare, affective analytics, customer service, and satellite imaging. Among these fields, affective analytics has been a particularly interesting direction of research. Affective analytics refers to the automatic recognition of emotion; it aims to mine opinions, sentiments, and emotions based on observations of people’s actions that can be captured using their writings, facial expressions, speech, movements, and so on toward different events, issues, services, or other such interests. In the past, researchers focused on investigating a single modality in the form of text, speech, or facial images. However, with the advancement of computer processing power and the development of sophisticated sensors, multimodal approaches can now be used for emotion recognition that provide a more accurate and detailed result. Affective analytics is important in Big data applications due to its numerous uses in streamlining products, services, etc. This chapter presents a review of existing work for Big data affective analytics. We also propose a multimodal automatic sentiment recognition approach for video, speech, and text data that can be implemented on Big databases and validate our approach using the Youtube dataset.

Details

Title: Multimodal Big Data Affective Analytics
Authors: Nusrat Jahan Shoumy (Corresponding Author) - Charles Sturt University
Li-Minn Ang (Author) - Griffith University
D M Motiur Rahaman (Author) - Charles Sturt University
Contributors: Seng Kah Phooi (Editor) - UNSW Australia
Kenneth Ang (Editor) - Griffith University
Alan Wee-Chung Liew (Editor) - Griffith University
Junbin Gao (Editor) - University of Sydney
Publication details: Multimodal Analytics for Next-Generation Big Data Technologies and Applications, pp.45-72
Publisher: Springer Nature
DOI: 10.1007/978-3-319-97598-6_3; 10.1007/978-3-319-97598-6
ISBN: 9783319975986
Organisation Unit: Engage Research Lab; University of the Sunshine Coast, Queensland; School of Science, Technology and Engineering
Language: English
Record Identifier: 99623440602621
Output Type: Book chapter

Metrics

61 Record Views