-
Notifications
You must be signed in to change notification settings - Fork 0
/
data analysis.Rmd
610 lines (497 loc) · 25 KB
/
data analysis.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
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
---
title: "data analysis"
output: pdf_document
date: "2023-03-09"
---
```{r setup, include=FALSE}
#read data
data <- read.csv("/Users/yanchu/Desktop/Thesis/data.csv")
data <- data[-c(1:26), ]
#Filter out attention check question
clean_data <- subset(data, Attention.Check == 'somewhat disagree')
#filter out timeout users
clean_data <- subset(clean_data, !(ID %in% c('6159f254f81c163cda4c76a4' , '6169c01bb2f3c18f07d99b83', '604268991d1ba711e6d37831')))
#filter out duplicated users- there is 1 user who submitted twice, the second submission was removed
newdata<- clean_data[!duplicated(clean_data$ID), ]
```
```{r}
library("tidyverse")
newdata <- newdata %>%relocate(ID)
#Data exploration, demographics, count the frequency in general
count(newdata, Age)
count(newdata, Gender)
count(newdata, Education.Level)
count(newdata, Twitter.usage)
count(newdata, Twitter.Frequence)
#Check participants' Twitter usage
newdata$Following.Number <- as.numeric(newdata$Following.Number)
newdata$Following.Number[is.na(newdata$Following.Number)] <- 800
summary(newdata$Following.Number)
newdata$Follower.Number <- as.numeric(newdata$Follower.Number)
summary(newdata$Follower.Number)
```
```{r}
library(ggplot2)
library(forcats)
#Gender Pie Chart
Gender <- newdata %>%
group_by(Gender) %>%
summarise(counts = n())
ggplot(Gender, aes(x="", y=counts, fill=Gender)) +
geom_bar(stat="identity", width=1) +
coord_polar("y", start=0) +
geom_text(aes(label = paste0(round(counts/180,2)*100, "%")), position = position_stack(vjust=0.5)) +
labs(x = NULL, y = NULL) +
theme_classic() +
theme(axis.line = element_blank(),
axis.text = element_blank(),
axis.ticks = element_blank()) +
scale_fill_brewer(palette="Blues") +
labs(title="Gender Percentage Plot")+
theme(plot.title = element_text(hjust = 0.5))
#Age Pie Chart
Age <- newdata %>%
group_by(Age) %>%
summarise(counts = n())
ggplot(Age, aes(x="", y=counts, fill=Age)) +
geom_bar(stat="identity", width=1) +
coord_polar("y", start=0) +
geom_text(aes(label = paste0(round(counts/180,2)*100, "%"), x = 1.5), position = position_stack(vjust=0.5)) +
labs(x = NULL, y = NULL) +
theme_classic() +
theme(axis.line = element_blank(),
axis.text = element_blank(),
axis.ticks = element_blank()) +
scale_fill_brewer(palette="OrRd") +
labs(title="Age Percentage Plot")+
theme(plot.title = element_text(hjust = 0.5))
#Education level plot
Education_level <- newdata %>%
group_by(Education.Level) %>%
summarise(counts = n())
ggplot(Education_level, aes(x = fct_rev(fct_reorder(Education.Level,
counts)), y = counts)) +
geom_bar(stat = "identity", fill="lightblue", width=0.3) +
geom_text(aes(label = counts), vjust = -0.3) + theme_minimal() +
theme(axis.line = element_line(),
panel.grid.major = element_blank(),
panel.grid.minor = element_blank(),
panel.border = element_blank(),
panel.background = element_blank()) +
labs(title="Education Level Counts Plot",
x ="Education Level", y = "Count")+
theme(plot.title = element_text(hjust = 0.5))
#Twitter usage plot
Twitter_usage <- newdata %>%
group_by(Twitter.usage) %>%
summarise(counts = n())
ggplot(Twitter_usage, aes(x = fct_rev(fct_reorder(Twitter.usage,
counts)), y = counts)) +
geom_bar(stat = "identity", fill="lightpink", width=0.3) +
geom_text(aes(label = counts), vjust = -0.3) + theme_minimal() +
theme(axis.line = element_line(),
panel.grid.major = element_blank(),
panel.grid.minor = element_blank(),
panel.border = element_blank(),
panel.background = element_blank()) +
labs(title="Twitter Usage Counts Plot",
x ="Twitter Usage", y = "Count")+
theme(plot.title = element_text(hjust = 0.5))
#Twitter Frequency plot
Twitter_frequency <- newdata %>%
group_by(Twitter.Frequence) %>%
summarise(counts = n())
ggplot(Twitter_frequency, aes(x = fct_rev(fct_reorder(Twitter.Frequence,
counts)), y = counts)) +
geom_bar(stat = "identity", fill="#009E73", width=0.3) +
geom_text(aes(label = counts), vjust = -0.3) + theme_minimal() +
theme(axis.line = element_line(),
panel.grid.major = element_blank(),
panel.grid.minor = element_blank(),
panel.border = element_blank(),
panel.background = element_blank()) +
labs(title="Twitter Posting Frequence Counts Plot",
x ="Twitter Posting Frequence", y = "Count")+
theme(plot.title = element_text(hjust = 0.5))
```
```{r}
library(dplyr)
library(dbplyr)
#recoded measurement
newdata <- newdata %>% mutate_at(c("Pre.Tweet.1","pre.Tweet.2","Pre.Tweet.3","Dr.Female","Dr.Male","MD.Female","MD.Male","Non.Female","Non.Male","Dr.link","Dr.nolink","MD.link","MD.nolink","NoDr.link","NoDr.nolink","Irrelevant.profile", "relevant.profile"), ~as.numeric(recode(.,"strongly disagree"=-3, "disagree"=-2, "somewhat disagree"=-1, "neutral" = 0, "somewhat agree"=1, "agree"=2, "strongly agree"=3)))
```
# H1
```{r}
#Assign Lables for Hypothesis
newdata_sub1 <- newdata[,c("ID","Pre.Tweet.1", "Dr.Female", "Dr.Male", "MD.Female", "MD.Male","Non.Female", "Non.Male", "Twitter.usage", "Twitter.Frequence", "Education.Level", "Age", "Gender")]
#Assign Gender Label
newdata_sub1 <- mutate(newdata_sub1,
GenderLabel = case_when(
is.na(Dr.Male) & is.na(MD.Female) & is.na(MD.Male) & is.na(Non.Female) & is.na(Non.Male)~ 'Female',
is.na(Dr.Female) & is.na(Dr.Male) & is.na(MD.Male) & is.na(Non.Female) & is.na(Non.Male)~'Female',
is.na(Dr.Female) & is.na(Dr.Male) & is.na(MD.Male) & is.na(MD.Female) & is.na(Non.Male)~'Female',
is.na(Dr.Female) & is.na(MD.Female) & is.na(MD.Male) & is.na(Non.Male) & is.na(Non.Female)~'Male',
is.na(Dr.Female) & is.na(Dr.Male) & is.na(MD.Female) & is.na(Non.Male) & is.na(Non.Female)~'Male',
is.na(Dr.Female) & is.na(Dr.Male) & is.na(MD.Female) & is.na(MD.Male) & is.na(Non.Female)~'Male'
))
#Assign Title Label
newdata_sub1 <- mutate(newdata_sub1,
TitleLabel = case_when(
is.na(Dr.Male) & is.na(MD.Female) & is.na(MD.Male) & is.na(Non.Female) & is.na(Non.Male)~ 'Doctor',
is.na(Dr.Female) & is.na(Dr.Male) & is.na(MD.Male) & is.na(Non.Female) & is.na(Non.Male)~'MD',
is.na(Dr.Female) & is.na(Dr.Male) & is.na(MD.Male) & is.na(MD.Female) & is.na(Non.Male)~'Non title',
is.na(Dr.Female) & is.na(MD.Female) & is.na(MD.Male) & is.na(Non.Male) & is.na(Non.Female)~'Doctor',
is.na(Dr.Female) & is.na(Dr.Male) & is.na(MD.Female) & is.na(Non.Male) & is.na(Non.Female)~'MD',
is.na(Dr.Female) & is.na(Dr.Male) & is.na(MD.Female) & is.na(MD.Male) & is.na(Non.Female)~'Non title'
))
#Calculate Difference
newdata_sub1 <- mutate(newdata_sub1,
Difference = case_when(
is.na(Dr.Male) & is.na(MD.Female) & is.na(MD.Male) & is.na(Non.Female) & is.na(Non.Male)~ abs(Pre.Tweet.1-Dr.Female),
is.na(Dr.Female) & is.na(Dr.Male) & is.na(MD.Male) & is.na(Non.Female) & is.na(Non.Male)~abs(Pre.Tweet.1-MD.Female),
is.na(Dr.Female) & is.na(Dr.Male) & is.na(MD.Male) & is.na(MD.Female) & is.na(Non.Male)~abs(Pre.Tweet.1-Non.Female),
is.na(Dr.Female) & is.na(MD.Female) & is.na(MD.Male) & is.na(Non.Male) & is.na(Non.Female)~abs(Pre.Tweet.1-Dr.Male),
is.na(Dr.Female) & is.na(Dr.Male) & is.na(MD.Female) & is.na(Non.Male) & is.na(Non.Female)~abs(Pre.Tweet.1-MD.Male),
is.na(Dr.Female) & is.na(Dr.Male) & is.na(MD.Female) & is.na(MD.Male) & is.na(Non.Female)~abs(Pre.Tweet.1-Non.Male)
))
#Calculate no abs difference
newdata_sub1 <- mutate(newdata_sub1,
noabsDifference = case_when(
is.na(Dr.Male) & is.na(MD.Female) & is.na(MD.Male) & is.na(Non.Female) & is.na(Non.Male)~ Dr.Female - Pre.Tweet.1,
is.na(Dr.Female) & is.na(Dr.Male) & is.na(MD.Male) & is.na(Non.Female) & is.na(Non.Male)~MD.Female - Pre.Tweet.1,
is.na(Dr.Female) & is.na(Dr.Male) & is.na(MD.Male) & is.na(MD.Female) & is.na(Non.Male)~Non.Female - Pre.Tweet.1,
is.na(Dr.Female) & is.na(MD.Female) & is.na(MD.Male) & is.na(Non.Male) & is.na(Non.Female)~Dr.Male - Pre.Tweet.1,
is.na(Dr.Female) & is.na(Dr.Male) & is.na(MD.Female) & is.na(Non.Male) & is.na(Non.Female)~MD.Male - Pre.Tweet.1,
is.na(Dr.Female) & is.na(Dr.Male) & is.na(MD.Female) & is.na(MD.Male) & is.na(Non.Female)~Non.Male - Pre.Tweet.1
))
#not all change are positive
plot(newdata_sub1$noabsDifference)
#explore the data where is negative change
negative_change <- subset(newdata_sub1, noabsDifference < 0)
#mean and sd of the difference
summary(newdata_sub1$noabsDifference)
sd(newdata_sub1$noabsDifference)
#plot the difference1
Difference1 <- newdata_sub1 %>%
group_by(noabsDifference) %>%
summarise(counts = n())
ggplot(Difference1, aes(x = factor(noabsDifference), y = counts)) +
geom_bar(stat = "identity", fill="#663399", width=0.3) +
geom_text(aes(label = counts), vjust = -0.3) + theme_minimal() +
theme(axis.line = element_line(),
panel.grid.major = element_blank(),
panel.grid.minor = element_blank(),
panel.border = element_blank(),
panel.background = element_blank()) +
labs(title="Statement 1 Difference Counts Plot",
x ="Difference of Credibility Change Level", y = "Count of participants")+
theme(plot.title = element_text(hjust = 0.5))
```
```{r}
#Hypothesis 1 Title
newdata_title <- newdata_sub1[,c("ID","TitleLabel", "GenderLabel","Difference")]
title.anova <- aov(Difference ~ TitleLabel, data = newdata_title )
summary(title.anova)
#check anova assumption
par(mfrow=c(2,2))
plot(title.anova)
par(mfrow=c(1,1))
#To find how much is the difference between all levels by TukeyHSD
tukey.title.anova<-TukeyHSD(title.anova)
tukey.title.anova
tukey.plot.test<-TukeyHSD(title.anova, conf.level=0.95)
plot(tukey.plot.test, las=2.5 , col="brown", cex.axis=0.5, col.axis=1.0, )
```
```{r}
#Hypothesis 2 Gender
gender.anova <- aov(Difference ~ GenderLabel, data = newdata_title)
summary(gender.anova)
gender.t <- t.test(Difference ~ GenderLabel, data = newdata_title)
gender.t
title_gender <- aov(Difference ~ TitleLabel + GenderLabel, data = newdata_title)
summary(title_gender)
interaction1<- aov(Difference ~ TitleLabel * GenderLabel, data = newdata_title)
summary(interaction1)
#choose the best model
library(AICcmodavg)
library(VGAM)
model.set <- list(gender.anova, title_gender, interaction1)
model.names <- c("gender.anova", "title_gender", "interaction1")
aictab(model.set, modnames = model.names) #One way is the best
```
# H3 & H4
```{r}
newdata_usage <- newdata_sub1[,c("ID","Twitter.usage", "Twitter.Frequence","TitleLabel", "GenderLabel", "Difference")]
#usage anova
usage.anova <- aov(Difference ~ Twitter.usage, data = newdata_usage)
summary(usage.anova)
usage_title.anova <- aov(Difference ~ Twitter.usage + TitleLabel, data = newdata_usage)
summary(usage_title.anova)
interaction2 <- aov(Difference ~ Twitter.usage * TitleLabel, data = newdata_usage)
summary(interaction2)
model.set <- list(usage.anova, usage_title.anova, interaction2 )
model.names <- c("usage.anova", "usage_title.anova", "interaction2")
aictab(model.set, modnames = model.names)
#Interaction plot shows there are interaction effect between all 5 types of users. Need further test
interaction.plot(x.factor = newdata_usage$TitleLabel,
trace.factor = newdata_usage$Twitter.usage,
response = newdata_usage$Difference,
fun = mean,
type="b",
col=c("black","red","green"), ### Colors for levels of trace var.
pch=c(19, 17, 15), ### Symbols for levels of trace var.
fixed=TRUE, ### Order by factor order in data
leg.bty = "o", main = "Interaction effect plot")
library(emmeans)
library(multcomp)
library(FSA)
marginal = emmeans(interaction2, ~ Twitter.usage : TitleLabel)
pairs(marginal,adjust="tukey")
cld(marginal,alpha=0.05,Letters=letters,adjust="tukey") ### Use lower-case letters for .group
Sum = Summarize(Difference ~ Twitter.usage + TitleLabel,
data=newdata_usage,
digits=3)
# Add standard error of the mean to the Sum data frame
Sum$se = Sum$sd / sqrt(Sum$n)
Sum$se = signif(Sum$se, digits=3)
Sum$Twitter.usage = factor(Sum$Twitter.usage,
levels=unique(Sum$Twitter.usage))
pd = position_dodge(.2)
ggplot(Sum, aes(x = Twitter.usage,y = mean,color = TitleLabel)) +
geom_errorbar(aes(ymin = mean - se, ymax = mean + se), width=.2, size=0.7, position = pd) +
geom_point(shape=15, size=2, position = pd) +
theme_bw() +
theme(axis.title = element_text(face = "bold")) +
scale_colour_manual(values= c("black","red","green")) +
labs(title="Interaction effect of Twitter usage and users' title", x ="Twitter Usage", y = "Mean Difference change")+
theme(plot.title = element_text(hjust = 0.5))
#Frequence anov
frequence.anova <- aov(Difference ~ Twitter.Frequence, data = newdata_usage)
summary(frequence.anova)
frequence_title.anova <- aov(Difference ~ Twitter.Frequence + TitleLabel, data = newdata_usage)
summary(frequence_title.anova)
interaction3 <- aov(Difference ~ Twitter.Frequence * TitleLabel, data = newdata_usage)
summary(interaction3)
#model comparison
model.set <- list(frequence.anova, frequence_title.anova,interaction3 )
model.names <- c("frequence.anova", "frequence_title.anova", "interaction3")
aictab(model.set, modnames = model.names)
#to investigate what type of users are influences, aka the usage vs difference
barplot(table(newdata_usage$Twitter.usage, newdata_usage$Difference),
beside = T,
legend.text = T,
#ylab = "Difference",
main = "", col=c("#9bf6ff","#fdffb6","#bdb2ff","#ffc6ff","#b5e48c", "#9a8c98"))
```
# H5
```{r}
#Assign Lables for Hypothesis 5
newdata_sub2 <- newdata[,c("ID","pre.Tweet.2", "Dr.link", "Dr.nolink", "MD.link", "MD.nolink","NoDr.link", "NoDr.nolink", "Twitter.usage", "Twitter.Frequence", "Education.Level", "Age", "Gender")]
#Assign link Label
newdata_sub2 <- mutate(newdata_sub2,
LinkLabel = case_when(
is.na(Dr.link) & is.na(MD.link) & is.na(MD.nolink) & is.na(NoDr.link) & is.na(NoDr.nolink)~ 'No link',
is.na(Dr.link) & is.na(Dr.nolink) & is.na(MD.link) & is.na(NoDr.link) & is.na(NoDr.nolink)~'No link',
is.na(Dr.link) & is.na(Dr.nolink) & is.na(MD.link) & is.na(MD.nolink) & is.na(NoDr.link)~'No link',
is.na(Dr.nolink) & is.na(MD.link) & is.na(MD.nolink) & is.na(NoDr.link) & is.na(NoDr.nolink)~'link',
is.na(Dr.link) & is.na(Dr.nolink) & is.na(MD.nolink) & is.na(NoDr.link) & is.na(NoDr.nolink)~'link',
is.na(Dr.link) & is.na(Dr.nolink) & is.na(MD.link) & is.na(MD.nolink) & is.na(NoDr.nolink)~'link'
))
#Assign Title Label
newdata_sub2 <- mutate(newdata_sub2,
TitleLabel = case_when(
is.na(Dr.link) & is.na(MD.link) & is.na(MD.nolink) & is.na(NoDr.link) & is.na(NoDr.nolink)~ 'Doctor',
is.na(Dr.link) & is.na(Dr.nolink) & is.na(MD.link) & is.na(NoDr.link) & is.na(NoDr.nolink)~'MD',
is.na(Dr.link) & is.na(Dr.nolink) & is.na(MD.link) & is.na(MD.nolink) & is.na(NoDr.link)~'Non title',
is.na(Dr.nolink) & is.na(MD.link) & is.na(MD.nolink) & is.na(NoDr.link) & is.na(NoDr.nolink)~'Doctor',
is.na(Dr.link) & is.na(Dr.nolink) & is.na(MD.nolink) & is.na(NoDr.link) & is.na(NoDr.nolink)~'MD',
is.na(Dr.link) & is.na(Dr.nolink) & is.na(MD.link) & is.na(MD.nolink) & is.na(NoDr.nolink)~'Non title'
))
#Calculate Difference
newdata_sub2 <- mutate(newdata_sub2,
Difference = case_when(
is.na(Dr.link) & is.na(MD.link) & is.na(MD.nolink) & is.na(NoDr.link) & is.na(NoDr.nolink)~ abs(pre.Tweet.2 - Dr.nolink),
is.na(Dr.link) & is.na(Dr.nolink) & is.na(MD.link) & is.na(NoDr.link) & is.na(NoDr.nolink)~abs(pre.Tweet.2 - MD.nolink),
is.na(Dr.link) & is.na(Dr.nolink) & is.na(MD.link) & is.na(MD.nolink) & is.na(NoDr.link)~abs(pre.Tweet.2 - NoDr.nolink),
is.na(Dr.nolink) & is.na(MD.link) & is.na(MD.nolink) & is.na(NoDr.link) & is.na(NoDr.nolink)~abs(pre.Tweet.2 - Dr.link),
is.na(Dr.link) & is.na(Dr.nolink) & is.na(MD.nolink) & is.na(NoDr.link) & is.na(NoDr.nolink)~abs(pre.Tweet.2 - MD.link),
is.na(Dr.link) & is.na(Dr.nolink) & is.na(MD.link) & is.na(MD.nolink) & is.na(NoDr.nolink)~abs(pre.Tweet.2 - NoDr.link)))
summary(newdata_sub2$Difference)
sd(newdata_sub2$Difference)
#calculate the difference no absolute
newdata_sub2 <- mutate(newdata_sub2,
noabsDifference = case_when(
is.na(Dr.link) & is.na(MD.link) & is.na(MD.nolink) & is.na(NoDr.link) & is.na(NoDr.nolink)~ Dr.nolink - pre.Tweet.2 ,
is.na(Dr.link) & is.na(Dr.nolink) & is.na(MD.link) & is.na(NoDr.link) & is.na(NoDr.nolink)~ MD.nolink -pre.Tweet.2 ,
is.na(Dr.link) & is.na(Dr.nolink) & is.na(MD.link) & is.na(MD.nolink) & is.na(NoDr.link)~NoDr.nolink - pre.Tweet.2 ,
is.na(Dr.nolink) & is.na(MD.link) & is.na(MD.nolink) & is.na(NoDr.link) & is.na(NoDr.nolink)~Dr.link - pre.Tweet.2,
is.na(Dr.link) & is.na(Dr.nolink) & is.na(MD.nolink) & is.na(NoDr.link) & is.na(NoDr.nolink)~MD.link - pre.Tweet.2,
is.na(Dr.link) & is.na(Dr.nolink) & is.na(MD.link) & is.na(MD.nolink) & is.na(NoDr.nolink)~NoDr.link - pre.Tweet.2))
#not all difference are positive
plot(newdata_sub2$noabsDifference)
summary(newdata_sub2$noabsDifference)
sd(newdata_sub2$noabsDifference)
#explore the data where is negative change
negative_change2 <- subset(newdata_sub2, noabsDifference < 0)
#plot the difference2
Difference2 <- newdata_sub2 %>%
group_by(noabsDifference) %>%
summarise(counts = n())
ggplot(Difference2, aes(x = factor(noabsDifference), y = counts)) +
geom_bar(stat = "identity", fill="#6666CC", width=0.3) +
geom_text(aes(label = counts), vjust = -0.3) + theme_minimal() +
theme(axis.line = element_line(),
panel.grid.major = element_blank(),
panel.grid.minor = element_blank(),
panel.border = element_blank(),
panel.background = element_blank()) +
labs(title="Statement 2 Difference Counts Plot",
x ="Difference of Credibility Change Level", y = "Count of Participants")+
theme(plot.title = element_text(hjust = 0.5))
newdata_link <- newdata_sub2[,c("ID","LinkLabel", "TitleLabel","Difference")]
#link t test
link.t <- t.test(Difference ~ LinkLabel, data = newdata_link)
link.t
barplot(table(newdata_link$LinkLabel, newdata_link$Difference),
beside = T,
legend.text = T,
#ylab = "Difference",
main = "Plot of link and difference", col=c("#bdb2ff","#ffc6ff"))
```
# H6
```{r}
#Assign Lables for Hypothesis 6
newdata_sub3 <- newdata[,c("ID","Pre.Tweet.3", "Irrelevant.profile", "relevant.profile", "Twitter.usage", "Twitter.Frequence", "Education.Level", "Age", "Gender")]
#Assign link Label
newdata_sub3 <- mutate(newdata_sub3,
bioLabel = case_when(
is.na(Irrelevant.profile) ~ 'relevant',
is.na(relevant.profile) ~'irrelevant'))
#Calculate Difference
newdata_sub3 <- mutate(newdata_sub3,
Difference = case_when(
is.na(Irrelevant.profile) ~ abs(Pre.Tweet.3 - relevant.profile),
is.na(relevant.profile)~ abs(Pre.Tweet.3 - Irrelevant.profile) ))
newdata_sub3 <- mutate(newdata_sub3,
noabsDifference = case_when(
is.na(Irrelevant.profile) ~ relevant.profile - Pre.Tweet.3 ,
is.na(relevant.profile)~ Irrelevant.profile - Pre.Tweet.3 ))
#not all difference are positive
plot(newdata_sub3$noabsDifference)
#explore the data where is negative change
negative_change3 <- subset(newdata_sub3, noabsDifference < 0)
summary(newdata_sub3$noabsDifference)
sd(newdata_sub3$noabsDifference)
#plot the difference3
Difference3 <- newdata_sub3 %>%
group_by(noabsDifference) %>%
summarise(counts = n())
ggplot(Difference3, aes(x = factor(noabsDifference), y = counts)) +
geom_bar(stat = "identity", fill="#CCCFF0", width=0.3) +
geom_text(aes(label = counts), vjust = -0.3) + theme_minimal() +
theme(axis.line = element_line(),
panel.grid.major = element_blank(),
panel.grid.minor = element_blank(),
panel.border = element_blank(),
panel.background = element_blank()) +
labs(title="Statement 3 Difference Counts Plot",
x ="Difference of Credibility Change Level", y = "Count of participants")+
theme(plot.title = element_text(hjust = 0.5))
newdata_bio <- newdata_sub3[,c("ID","bioLabel","Difference")]
#bio t test
bio.t <- t.test(Difference ~ bioLabel, data = newdata_bio)
bio.t
barplot(table(newdata_bio$bioLabel, newdata_bio$Difference),
beside = T,
legend.text = T,
#ylab = "Difference",
main = "Plot of bio level and difference", col=c("#9bf6ff","#fdffb6"))
```
# Further exploration on negative impacted users and their type.
```{r}
#Investigate more into negative changes
negative1 <- negative_change[ , c("ID", "Twitter.Frequence", "Twitter.usage", "Education.Level", "Age","Gender", "noabsDifference")]
negative2 <- negative_change2[ , c("ID", "Twitter.Frequence", "Twitter.usage", "Education.Level", "Age","Gender", "noabsDifference")]
negative3 <- negative_change3[ , c("ID", "Twitter.Frequence", "Twitter.usage", "Education.Level", "Age","Gender", "noabsDifference")]
negative <- rbind(negative1, negative2,negative3 )
#Twitter usage negative plot
negative_Twitter_usage <- negative %>%
group_by(Twitter.usage) %>%
summarise(counts = n())
ggplot(negative_Twitter_usage, aes(x = fct_rev(fct_reorder(Twitter.usage,
counts)), y = counts)) +
geom_bar(stat = "identity", fill="#FFFFCC", width=0.3) +
geom_text(aes(label = counts), vjust = -0.3) + theme_minimal() +
theme(axis.line = element_line(),
panel.grid.major = element_blank(),
panel.grid.minor = element_blank(),
panel.border = element_blank(),
panel.background = element_blank()) +
labs(title="Twitter Usage Counts for negative users Plot",
x ="Twitter Usage", y = "Count")+
theme(plot.title = element_text(hjust = 0.5))
#negative Twitter frequency negative plot
negative_Twitter_usage <- negative %>%
group_by(Twitter.Frequence) %>%
summarise(counts = n())
ggplot(negative_Twitter_usage, aes(x = fct_rev(fct_reorder(Twitter.Frequence,
counts)), y = counts)) +
geom_bar(stat = "identity", fill="#009900", width=0.3) +
geom_text(aes(label = counts), vjust = -0.3) + theme_minimal() +
theme(axis.line = element_line(),
panel.grid.major = element_blank(),
panel.grid.minor = element_blank(),
panel.border = element_blank(),
panel.background = element_blank()) +
labs(title="Twitter Frequence Counts for negative users Plot",
x ="TwitterFrequence", y = "Count")+
theme(plot.title = element_text(hjust = 0.5))
#negative user education plot
negative_Twitter_usage <- negative %>%
group_by(Education.Level) %>%
summarise(counts = n())
ggplot(negative_Twitter_usage, aes(x = fct_rev(fct_reorder(Education.Level,
counts)), y = counts)) +
geom_bar(stat = "identity", fill="#00cc99", width=0.3) +
geom_text(aes(label = counts), vjust = -0.3) + theme_minimal() +
theme(axis.line = element_line(),
panel.grid.major = element_blank(),
panel.grid.minor = element_blank(),
panel.border = element_blank(),
panel.background = element_blank()) +
labs(title="Education Level for negative users Plot",
x ="Education Level", y = "Count")+
theme(plot.title = element_text(hjust = 0.5))
#negative user gender plot
negative_Twitter_usage <- negative %>%
group_by(Gender) %>%
summarise(counts = n())
ggplot(negative_Twitter_usage, aes(x = fct_rev(fct_reorder(Gender,
counts)), y = counts)) +
geom_bar(stat = "identity", fill="#99FF00", width=0.3) +
geom_text(aes(label = counts), vjust = -0.3) + theme_minimal() +
theme(axis.line = element_line(),
panel.grid.major = element_blank(),
panel.grid.minor = element_blank(),
panel.border = element_blank(),
panel.background = element_blank()) +
labs(title="Gender negative users Plot",
x ="Gender", y = "Count")+
theme(plot.title = element_text(hjust = 0.5))
#negative user Age plot
negative_Twitter_usage <- negative %>%
group_by(Age) %>%
summarise(counts = n())
ggplot(negative_Twitter_usage, aes(x = fct_rev(fct_reorder(Age,
counts)), y = counts)) +
geom_bar(stat = "identity", fill="#00FFFF", width=0.3) +
geom_text(aes(label = counts), vjust = -0.3) + theme_minimal() +
theme(axis.line = element_line(),
panel.grid.major = element_blank(),
panel.grid.minor = element_blank(),
panel.border = element_blank(),
panel.background = element_blank()) +
labs(title="Age negative users Plot",
x ="Age", y = "Count")+
theme(plot.title = element_text(hjust = 0.5))
```