NewsBank Text Analysis \(-\) Pakistan

Section 1: China - PAK News Articles

Keywords

1. Belt and Road
2. CPEC
3. Confucius Institute/Classroom
4. Quadrilateral Security Dialgoue/Consultative Group
5. Huawei
6. Gwadar
7. Beidou
8. Sinovac/Sinopharm
9. Pakistan Army/Military
10. Shanghai Cooperation Organization

Frequency by Year

	2014	2015	2016	2017	2018	2019	2020	2021	2022
Chinese Media	909	2495	2409	5746	6429	6245	2798	2829	1070
Pakistani Media	5975	11596	16514	17787	14711	10810	9846	8705	3799
Western Media	3490	4099	3856	5855	9461	9037	8557	5857	2276

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	0.026***
	(0.0003)
wst	-0.014***
	(0.0002)
Constant	0.009***
	(0.0001)
Observations	183,161
R2	0.095
Adjusted R2	0.095
Residual Std. Error	0.040 (df = 183158)
F Statistic	9,587.835*** (df = 2; 183158)
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-PAK 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 - PAK News Articles

Keywords

1. Pakistan army/military
2. Shanghai Cooperation Organization
3. Rosatom
4. Gazprom
5. Rostec
6. Sputnik V

Frequency by Year

	2014	2015	2016	2017	2018	2019	2020	2021	2022
Russian Media	131	118	84	20	16	58	97	81	5
Pakistani Media	5117	6290	5393	5965	4819	4623	4743	3944	1685
Western Media	2833	2778	2809	2665	3342	2795	4458	3160	1701

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	-0.009***
	(0.002)
wst	-0.012***
	(0.0003)
Constant	-0.0004*
	(0.0002)
Observations	69,730
R2	0.018
Adjusted R2	0.018
Residual Std. Error	0.042 (df = 69727)
F Statistic	654.405*** (df = 2; 69727)
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 - PAK articles in the first section.

Sentiment Analysis: Keywords

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

End of File