Table 2.

Sentiment polarities in media communications (Twitter posts) analyzed using the TextBlob, VADER, and Word2Vec-BiLSTM models.

Period in 2020	TextBlob					VADERa					Word2Vec-BiLSTMb
	Positive	Negative	Neutral	Subjectivity score	Positive		Negative	Neutral	Compound score	Positive		Negative
February 2	100.00	0.00	0.00	0.92	0.17		0.00	0.83	0.70	100.00		0.00
February 9	37.50	37.50	25.00	0.34	0.12		0.09	0.79	0.15	87.50		12.50
February 16	63.64	9.09	27.27	0.27	0.09		0.05	0.85	0.12	54.55		45.45
February 23	50.00	50.00	0.00	0.37	0.17		0.04	0.79	0.48	100.00		0.00
March 1	83.33	0.00	16.67	0.59	0.14		0.03	0.83	0.36	66.67		33.33
March 8	44.44	22.22	33.33	0.32	0.14		0.03	0.83	0.38	66.67		33.33
March 15	85.71	0.00	14.29	0.52	0.05		0.02	0.92	0.16	100.00		0.00
March 22	66.67	0.00	33.33	0.40	0.12		0.02	0.86	0.49	66.67		33.33
March 29	38.57	27.14	34.29	0.37	0.08		0.12	0.80	–0.12	82.86		17.14
April 5	36.49	20.27	43.24	0.35	0.07		0.12	0.81	–0.11	82.43		17.57
April 12	33.33	41.67	25.00	0.49	0.10		0.07	0.82	0.10	83.33		16.67
April 19	66.67	6.67	26.67	0.47	0.06		0.06	0.88	–0.02	93.33		6.67
April 26	48.02	23.41	28.57	0.37	0.11		0.07	0.82	0.11	73.41		26.59
May 3	38.18	15.15	46.67	0.32	0.10		0.06	0.84	0.09	78.79		21.21
Average polarity	56.61	18.08	25.31	0.43	0.11		0.06	0.83	0.21	81.16		18.84

^aVADER: Valence Aware Dictionary and Sentiment Reasoner.

^bBiLSTM: bidirectional long short-term memory.