A Deep Learning Platform for Analyzing Social Media Contents

Speaker:  Asad Masood Khattak – Abu Dhabi, United Arab Emirates
Topic(s):  Artificial Intelligence, Machine Learning, Computer Vision, Natural language processing

Abstract

Social media has become the mainstream and one of the preferred forums to disseminate news, communicate views, express opinions and intentions about events, policies, services, and products. With the exponential growth of social medial platforms dealing with a variety of contents types is a challenging task. One key side-effect of the social media popularity is the proliferation of fake contents, opinions, or even rumors. Fake news and reviews can be used as a lethal instrument of destabilization where huge swaths of the population can be targeted and manipulated. In this research talk, we will examine news items and the review identification problem using a deep learning model with an emphasis on maintaining the sequence correlation and also to retain information for a long-time span that has possible reflection on future posts or sharing on social media. Convolutional neural network along with long short-term memory for efficient detection of intent vs non-intent, fake vs real, and offensive vs non-offensive posts. In this research talk, we will share our achievements of social network analysis for the above-mentioned topics and will share the experimental results of the proposed scheme. 

About this Lecture

Number of Slides:  30
Duration:  40 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.