A Hybrid BERT and LightGBM based Model for Predicting Emotion GIF Categories on Twitter

TL;DR

This paper introduces a hybrid model combining BERT and LightGBM to predict emotion GIF categories on Twitter, achieving competitive results in a shared challenge.

Contribution

It presents a novel learning to rank framework integrating BERT and LightGBM for GIF emotion classification on social media data.

Findings

Achieved 4th place in the EmotionGIF 2020 challenge

Attained a MAP@6 score of 0.5394

Demonstrated effectiveness of hybrid BERT-LightGBM approach

Abstract

The animated Graphical Interchange Format (GIF) images have been widely used on social media as an intuitive way of expression emotion. Given their expressiveness, GIFs offer a more nuanced and precise way to convey emotions. In this paper, we present our solution for the EmotionGIF 2020 challenge, the shared task of SocialNLP 2020. To recommend GIF categories for unlabeled tweets, we regarded this problem as a kind of matching tasks and proposed a learning to rank framework based on Bidirectional Encoder Representations from Transformer (BERT) and LightGBM. Our team won the 4th place with a Mean Average Precision @ 6 (MAP@6) score of 0.5394 on the round 1 leaderboard.