-
Notifications
You must be signed in to change notification settings - Fork 0
/
usnews_regression.Rmd
89 lines (67 loc) · 1.94 KB
/
usnews_regression.Rmd
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
---
title: "usnews_regression"
author: "Jonathan Ratschat"
date: "21 9 2020"
output: html_document
---
```{r setup, include=FALSE}
knitr::opts_chunk$set(echo = TRUE)
```
```{r}
library(dplyr)
library(HH)
library(sjPlot)
library(ggplot2)
library(ggeffects)
library(ggthemes)
```
```{r}
usnews <- read.csv("C:/Users/Jonathan Ratschat/Google Drive/Colab Notebooks/Scraping/usnews/data/usnews.csv")
str(usnews)
```
```{r}
usnews <- usnews %>%
mutate(NewsProvider = as.factor(NewsProvider),
Dominant_Topic = as.factor(Dominant_Topic))
```
```{r}
mod1 <- lm(Sentiment ~ Dominant_Topic + NewsProvider, data = usnews)
summary(mod1, robust=TRUE)
```
```{r}
vif(mod1)
```
```{r}
mean(vif(mod1))
```
```{r}
mod2 <- lm(Sentiment ~ Dominant_Topic * NewsProvider, data = usnews)
print(summary(mod2, robust=TRUE))
```
```{r}
vif(mod2)
```
```{r}
mean(vif(mod2), na.rm = TRUE)
```
```{r}
dat <- ggeffects::ggpredict(mod2, terms = c("Dominant_Topic", "NewsProvider"))
ggplot(data = dat, aes(x=dat$x, y= dat$predicted, color = dat$group)) +
geom_point(size = 4, position = position_dodge(.3)) +
#geom_errorbar(aes(ymin = conf.low, ymax = conf.high), position = position_dodge(.3)) +
scale_y_continuous(limits=c(-1,1)) +
scale_color_manual(values=c("#2020df", "#df9c20", "#107010", "#df2020")) +
xlab("Dominant Topic") +
ylab("Predicted Sentiment") +
labs(colour = "News Provider") +
theme(## plotregion
plot.background = element_rect(fill = "#f0f0f0", colour = "#f0f0f0"),
panel.border = element_blank(),
panel.grid.major = element_line(size = 0.5, linetype = 'solid', colour = "lightgrey"),
panel.grid.minor = element_blank(),
panel.spacing = unit(0.25, "lines"),
## axis line
axis.line = element_line(colour = "black", size = 0.5, linetype = "solid")
)
ggsave("regression_overall_effect.png", width = 20, height = 10, units = "cm")
```