Table 5.

Correlations of daily bullish sentiment across sentiment measures (unique cashtags)

Panel A: Twitter
	(1)	(2)	(3)	(4)	(5)	(6)	(7)	(8)	(9)
Harvard-IV (1)	1.00	0.26	0.24	0.29	0.41	0.12	0.11	0.12	0.23
LM (2)		1.00	0.21	0.31	0.33	0.11	0.12	0.20	0.17
L1 (3)			1.00	0.53	0.30	0.35	0.34	0.11	0.45
L2 (4)				1.00	0.32	0.38	0.38	0.16	0.47
VADER (5)					1.00	0.20	0.18	0.16	0.30
Naive Bayes (6)						1.00	0.73	0.08	0.46
Max. entropy (7)							1.00	0.08	0.45
Deep-MLSA (8)								1.00	0.10
DeepMoji (9)									1.00

Panel B: StockTwits
	(1)	(2)	(3)	(4)	(5)	(6)	(7)	(8)	(9)
Harvard-IV (1)	1.00	0.28	0.21	0.33	0.40	0.18	0.18	0.14	0.21
LM (2)		1.00	0.20	0.27	0.34	0.16	0.17	0.25	0.20
L1 (3)			1.00	0.52	0.21	0.35	0.37	0.15	0.38
L2 (4)				1.00	0.31	0.48	0.53	0.17	0.54
VADER (5)					1.00	0.21	0.20	0.19	0.22
Naive Bayes (6)						1.00	0.81	0.12	0.55
Max. entropy (7)							1.00	0.13	0.60
Deep-MLSA (8)								1.00	0.13
DeepMoji (9)									1.00

Panel C: correlation between Twitter and StockTwits
	(1)	(2)	(3)	(4)	(5)	(6)	(7)	(8)	(9)
StockTwits-Twitter	0.28	0.32	0.25	0.32	0.33	0.20	0.20	0.26	0.30

Note: This table reports correlations between daily bullish sentiment scores estimated from short messages that contain a unique cashtag published on Twitter and StockTwits based on different approaches (dictionary-based and machine learning techniques). Panel A and B report correlations between daily bullish sentiment scores estimated from Twitter and StockTwits short messages, respectively. Panel C reports correlations between daily bullish sentiment scores estimated from Twitter short messages with those estimated from StockTwits short messages