Title :
Investor sentiment affects the trading volume: An evidence from network forums text analysis
Author :
Juanjuan Lai ; Tianlun Zheng ; Hongbo Yi ; Dayong Dong
Author_Institution :
Sch. of Econ. & Manage., Southwest Jiaotong Univ., Chengdu, China
Abstract :
By conducting a word frequency statistics in the posing on Eastmoney forum bar about SSE Composite Index from January 7, 2010 to August 30, 2013, we establish a set of keyword dictionary to measure investor sentiment effectively, and accordingly to study the mutual relations between the abnormal investor sentiment based on the network forums and the abnormal trading volume in the trading market. The empirical results show that investor sentiment of the trading day is positive correlated with abnormal trading volume of the trading day. The abnormal investor sentiment of the previous trading day is negative correlated with abnormal trading volume of the next trading day. We also take the weekly data into consideration and find that there is no significant correlation between abnormal investor sentiment and market abnormal trading volume during the same period, while investor sentiment of the previous week and abnormal trading volume of the next week are negatively correlated.
Keywords :
investment; securities trading; statistics; text analysis; word processing; Eastmoney forum bar; SSE composite index; investor sentiment; market abnormal trading volume; network forum text analysis; trading market; word frequency statistics; Correlation; Dictionaries; Frequency measurement; Indexes; Mathematical model; Reactive power; Stock markets; abnormal trading volume; investor sentiment; word frequency statistics;
Conference_Titel :
Fuzzy Systems and Knowledge Discovery (FSKD), 2014 11th International Conference on
Conference_Location :
Xiamen
Print_ISBN :
978-1-4799-5147-5
DOI :
10.1109/FSKD.2014.6980914