Lexical Squad@Multimodal Hate Speech Event Detection 2023: Multimodal Hate Speech Detection using Fused Ensemble Approach
Mohammad Kashif, Mohammad Zohair, Saquib Ali

TL;DR
This paper introduces a novel ensemble approach combining InceptionV3, BERT, and XLNet for detecting hate speech in multimodal social media content, achieving promising accuracy and F-1 scores.
Contribution
The paper presents a new multimodal ensemble learning method for hate speech detection using fused models, which is a novel approach in this domain.
Findings
Achieved 75.21% accuracy in hate speech detection.
Attained 74.96 F-1 score, demonstrating effective classification.
Evaluated multimodal content to understand model performance.
Abstract
With a surge in the usage of social media postings to express opinions, emotions, and ideologies, there has been a significant shift towards the calibration of social media as a rapid medium of conveying viewpoints and outlooks over the globe. Concurrently, the emergence of a multitude of conflicts between two entities has given rise to a stream of social media content containing propaganda, hate speech, and inconsiderate views. Thus, the issue of monitoring social media postings is rising swiftly, attracting major attention from those willing to solve such problems. One such problem is Hate Speech detection. To mitigate this problem, we present our novel ensemble learning approach for detecting hate speech, by classifying text-embedded images into two labels, namely "Hate Speech" and "No Hate Speech". We have incorporated state-of-art models including InceptionV3, BERT, and XLNet. Our…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Code & Models
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsHate Speech and Cyberbullying Detection · Internet Traffic Analysis and Secure E-voting · Sentiment Analysis and Opinion Mining
MethodsRefunds@Expedia|||How do I get a full refund from Expedia? · Attention Is All You Need · WordPiece · Byte Pair Encoding · Linear Layer · Residual Connection · Attention Dropout · Weight Decay · Multi-Head Attention · Adam
