TY - GEN
T1 - Sentiments Affect Stock Returns
T2 - 23rd IEEE International Conference on High Performance Computing and Communications, 7th IEEE International Conference on Data Science and Systems, 19th IEEE International Conference on Smart City and 7th IEEE International Conference on Dependability in Sensor, Cloud and Big Data Systems and Applications, HPCC-DSS-SmartCity-DependSys 2021
AU - Sun, Jing
AU - Xu, Yingying
AU - Zhao, Yueqiang
AU - Zhou, Yuliang
AU - Ortiz, Jaime
AU - Chen, Weipeng
N1 - Publisher Copyright:
© 2021 IEEE.
PY - 2022
Y1 - 2022
N2 - This study provides new insights into the causality between sentiments and stock returns. Based on machine learning, we classify the blogs from Weibo into five sentiments of anger, disgust, fear, joy, and sadness. Using wavelet coherence and phase difference, we find close linkages between the number of blogs under certain sentiment and stock returns, which have both frequency and time-varying features. Over the medium horizons, the number of blogs under anger, disgust, fear, joy, and sadness lead to changes in stock returns positively. Nevertheless, over the long time horizons, stock returns lead changes in the number of blogs with a certain sentiment. We find no evidence supporting the difference between positive and negative sentiments considering their effects on stock returns.
AB - This study provides new insights into the causality between sentiments and stock returns. Based on machine learning, we classify the blogs from Weibo into five sentiments of anger, disgust, fear, joy, and sadness. Using wavelet coherence and phase difference, we find close linkages between the number of blogs under certain sentiment and stock returns, which have both frequency and time-varying features. Over the medium horizons, the number of blogs under anger, disgust, fear, joy, and sadness lead to changes in stock returns positively. Nevertheless, over the long time horizons, stock returns lead changes in the number of blogs with a certain sentiment. We find no evidence supporting the difference between positive and negative sentiments considering their effects on stock returns.
KW - Causality
KW - Sentiment
KW - Stock Return
KW - Text analysis
UR - https://www.scopus.com/pages/publications/85132418916
U2 - 10.1109/HPCC-DSS-SmartCity-DependSys53884.2021.00285
DO - 10.1109/HPCC-DSS-SmartCity-DependSys53884.2021.00285
M3 - 会议稿件
AN - SCOPUS:85132418916
T3 - 2021 IEEE 23rd International Conference on High Performance Computing and Communications, 7th International Conference on Data Science and Systems, 19th International Conference on Smart City and 7th International Conference on Dependability in Sensor, Cloud and Big Data Systems and Applications, HPCC-DSS-SmartCity-DependSys 2021
SP - 1908
EP - 1913
BT - 2021 IEEE 23rd International Conference on High Performance Computing and Communications, 7th International Conference on Data Science and Systems, 19th International Conference on Smart City and 7th International Conference on Dependability in Sensor, Cloud and Big Data Systems and Applications, HPCC-DSS-SmartCity-DependSys 2021
PB - Institute of Electrical and Electronics Engineers Inc.
Y2 - 20 December 2021 through 22 December 2021
ER -