Probing hate speech and misinformation detection on the shoulder of affective information and multitask learning

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

Abstract

Hate speech and misinformation are two most critical issues in today's world.  Moderators often face a double challenge regarding reducing offensive and harmful content in social media. Despite the need to prevent the free circulation of such content, strict censorship on social media cannot be implemented due to a tricky dilemma - preserving free speech on the Internet while limiting them and how not to overreact. Affective information such as emotion, and sentiment can provide important clues for hate speech and misinformation detection. Most of the existing systems do not essentially exploit the correlatedness of hate-offensive content, aggressive posts and emotional content ; instead, they attend to the tasks individually. As a result, the need for cost-effective, sophisticated multi-task systems to effectively detect aggressive and offensive content on social media is highly critical in recent times.  Promoting #gandhigiri is also important to sensitize people against spreading hate messages in social media. Relevant literature reveals that one major characteristic of the virality of fake news is the presence of an element of surprise in the story, which attracts immediate attention and invokes strong emotional stimuli in the reader. We leverage this idea and propose textual novelty detection and emotion prediction as the two tasks relating to automatic misinformation detection. The talk will cover some of the recent research that we have been doing in our research group.  

About this Lecture

Number of Slides:  70
Duration:  90 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.