Does image sentiment of major public emergency affect the stock market performance? New insight from deep learning techniques

被引：0
作者：
Liu, Yun [1 ,2 ]
Huang, Dengshi [1 ,2 ]
Zhou, Jianan [1 ,2 ]
Wang, Sirui [1 ,2 ]
机构：
[1] Southwest Jiaotong Univ, Sch Econ & Management, Chengdu, Peoples R China
[2] Serv Sci & Innovat Key Lab Sichuan Prov, Chengdu, Peoples R China
来源：
ACCOUNTING AND FINANCE | 2024年 / 64卷 / 04期
基金：
中国国家自然科学基金;
关键词：
COVID-19; deep learning technique; image sentiment; stock market; INVESTOR SENTIMENT; NEWS; VOLATILITY; ATTENTION; DECISION; RETURNS; PICTURE; NOISE; TALK; TEXT;
D O I：
10.1111/acfi.13313
中图分类号：
F8 [财政、金融];
学科分类号：
0202 ;
摘要：
Leveraging deep learning to analyse COVID-19 image sentiment, this study reveals its significant impact on stock market dynamics. It highlights how vivid imagery prompts marked emotional responses, altering market performance and how news sentiment can modulate this effect. Further, it underscores the pivotal role of forum-based investor sentiment, particularly affecting small-minus-big stocks during downturns and trading week commencements. This research not only advances behavioural finance understanding but also informs management and regulatory strategies.
引用
收藏
页码：4447 / 4472
页数：26
相关论文
共 59 条
123456