logo
ResearchBunny Logo
Emotion classification for short texts: an improved multi-label method

Computer Science

Emotion classification for short texts: an improved multi-label method

X. Liu, T. Shi, et al.

Discover how Xuan Liu and colleagues have revolutionized multi-label emotion classification for short texts like tweets. Their cutting-edge MLkNN classifier leverages in-sentence, adjacent sentence, and full-text features for unparalleled accuracy and recall. Dive into the iterative correction methods that drive their findings!

00:00
00:00
Playback language: English
Abstract
This study proposes an improved Multi-label K-Nearest Neighbors (MLkNN) classifier for multi-label emotion classification of short texts, particularly tweets. The improvement involves considering in-sentence features, adjacent sentence features, and full-text features to iteratively refine emotion classifications. Experiments on a Twitter corpus compare the base MLkNN, a sample-based version (S-MLkNN), and a label-based version (L-MLkNN). Results demonstrate that the improved L-MLkNN achieves superior accuracy and recall, especially with K=8 and α=0.7, showcasing the effectiveness of the iterative correction method.
Publisher
Humanities and Social Sciences Communications
Published On
Jun 08, 2023
Authors
Xuan Liu, Tianyi Shi, Guohui Zhou, Mingzhe Liu, Zhengtong Yin, Lirong Yin, Wenfeng Zheng
Tags
Multi-label classification
emotion classification
MLkNN
short texts
Twitter corpus
iterative correction
accuracy and recall
Listen, Learn & Level Up
Over 10,000 hours of research content in 25+ fields, available in 12+ languages.
No more digging through PDFs, just hit play and absorb the world's latest research in your language, on your time.
listen to research audio papers with researchbunny