Deep Learning for Sentiment Analysis

Speaker:  Asif Ekbal – Jodhpur, India
Topic(s):  Artificial Intelligence, Machine Learning, Computer Vision, Natural language processing

Abstract

Sentiment Analysis is a well-established task which aims at determining the polarity of opinion expressed in a given user’s review. Most of the existing works focus on discovering sentiments at the document or sentence level. However, the techniques focused on such a coarse-level analysis (i.e. document level or sentence level) do not always satisfy the users’ needs as per their expectations. They often require more finer information from a review in terms of specific aspects (or, features or attributes) of a product or service. This fine-grained analysis of sentiment is known as Aspect based Sentiment Analysis. This talk will briefly introduce aspect based sentiment analysis, and then focus on specific methods that we have been investigating for aspect level sentiment analysis, particularly in low-resource scenarios. The later part of the talk will briefly introduce some of our recent works on multimodal sentiment and emotion analysis that investigates how more than one medium, such as text, audio and video etc influences the overall decision. 

About this Lecture

Number of Slides:  130
Duration:  150 minutes
Languages Available:  English
Last Updated: 

Request this Lecture

To request this particular lecture, please complete this online form.

Request a Tour

To request a tour with this speaker, please complete this online form.

All requests will be sent to ACM headquarters for review.