NewsBank Text Analysis \(-\) Serbia

Section 1: China - Serbia News Articles

Keywords

1. “Confucius Institute|Confucius Classroom”
2. “Huawei”
3. “Hesteel Group”
4. “University Of Belgrade”
5. “Sinovac|Sinopharm”
6. “China|Chinese”

Frequency by Year

	2014	2015	2016	2017	2018	2019	2020	2021	2022
Chinese Media	9118	9992	6019	10452	11825	12321	8635	7983	3144
Domestic Media	47	27	11	0	0	0	0	0	0
Western Media	19030	21896	17838	20823	28642	25154	26958	20315	8769

20 Most Common Words

Sentiment Analysis: Time-Series Plots

Both of these plots show same information. Pick one:

Sentiment Analysis: Box Plots

Sentiment Analysis: Density Plots

Sentiment Analysis: Regression

	Dependent variable:
	sentiment
chn	0.030***
	(0.004)
wst	-0.002
	(0.004)
Constant	-0.005
	(0.004)
Observations	268,999
R2	0.142
Adjusted R2	0.142
Residual Std. Error	0.035 (df = 268996)
F Statistic	22,226.864*** (df = 2; 268996)
Note:	*p<0.1; **p<0.05; ***p<0.01

Interpretation:

chn = coefficient for Chinese sources
wst = coefficient for Western sources
Constant = Intercept, which is the coefficient for Domestic sources

It shows that the sentiment score for CHN-SRB articles in domestic sources is close to zero, while Chinese sources are significantly more positive.

We can also see the same results in the boxplot and density plot above.

We can plot the above results in a coefficient plot below:

Sentiment Analysis: Coefficient Plot

Sentiment Analysis: Keywords

Both the boxplots below convey the same information. Pick one or both:

Section 2: Russia - Serbia News Articles

Keywords

1. “Rosatom”
2. “Eskom”
3. “Gazprom|Gasprom”
4. “Rostec”
5. “Russia Health Pharmaceuticals”
6. “Sputnik V”
7. “Russia|Russian”

Frequency by Year

	2014	2015	2016	2017	2018	2019	2020	2021	2022
Domestic Media	184	142	62	0	0	0	0	0	1
Russian Media	556	375	270	80	63	197	190	165	55
Western Media	11310	10426	10724	12577	14773	11824	12716	10317	9639

20 Most Common Words

Sentiment Analysis: Time-Series Plots

Both of these plots show same information. Pick one:

Sentiment Analysis: Box Plots

Sentiment Analysis: Density Plots

Sentiment Analysis: Regression

	Dependent variable:
	sentiment
rus	0.0002
	(0.002)
wst	-0.004**
	(0.002)
Constant	-0.010***
	(0.002)
Observations	106,646
R2	0.0003
Adjusted R2	0.0003
Residual Std. Error	0.031 (df = 106643)
F Statistic	17.669*** (df = 2; 106643)
Note:	*p<0.1; **p<0.05; ***p<0.01

Interpretation:

rus = coefficient for Russian sources
wst = coefficient for Western sources
Constant = Intercept, which is the coefficient for Domestic sources

We can plot the above results in a coefficient plot below:

Sentiment Analysis: Coefficient Plot

Note the difference between this coefficient plot and the coefficient plot for China - Serbia articles in the first section.

Sentiment Analysis: Keywords

Both the boxplots below convey the same information. Pick one or both:

End of File