DocumentCode :
707491
Title :
Multimodal sentiment analysis: Sentiment analysis using audiovisual format
Author :
Yadav, Sumit K. ; Bhushan, Mayank ; Gupta, Swati
Author_Institution :
Dept. of Comput. Sci., IGDTUW, Delhi, India
fYear :
2015
fDate :
11-13 March 2015
Firstpage :
1415
Lastpage :
1419
Abstract :
Multimodal sentiment analysis is the analysis of emotions, attitude, and opinion from audiovisual format. A company can improve the quality of its product and services by analyzing the reviews about the product [5]. Sentiment analysis is widely used in managing customer relations. There are many textual reviews from which we cannot extract emotions by traditional sentiment analysis techniques. Some sentences in the textual reviews may derive deep emotions but do not contain any keyword to detect those emotions, so we used audiovisual reviews in order to detect emotions from the facial expressions of the customer. In this paper we take audiovisual input and extract emotions from video and audio in parallel from audiovisual input, finally classify the overall review as positive, negative or neutral based on the emotions detected.
Keywords :
behavioural sciences computing; emotion recognition; feature extraction; video signal processing; audiovisual format; audiovisual input; audiovisual reviews; customer relations; deep emotions; emotions extraction; multimodal sentiment analysis; textual reviews; Accuracy; Computer science; Electronic mail; Eyebrows; Feature extraction; Logic gates; Sentiment analysis; Analyzing reviews; audio features; audiovisual; facial expression;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Computing for Sustainable Global Development (INDIACom), 2015 2nd International Conference on
Conference_Location :
New Delhi
Print_ISBN :
978-9-3805-4415-1
Type :
conf
Filename :
7100481
Link To Document :
بازگشت