Social-Media-Impact.qmd

---
title: "Social Media Impact on Education"
format: pdf
editor: visual
---

## Introduction
Social media's influence on education is a vital area of study, exploring its effects on student behavior and academic engagement.

```{r}
library(wesanderson)
library(ggplot2) 
library(dplyr)
library(ggalt)   
library(tidyverse)
library(mosaic)
library("ggpubr")
library(latticeExtra)
library(sysfonts)
library("showtext")
library(PairedData)
library(rstatix)
library(XML)
library(reshape2)
library(pyramid)
library(cowplot)
```

## Methods
We conducted an experimental survey via Qualtrics and mTurk, examining students' interaction with educational content.

```{r}
blue <- "#0171CE"
red <- "#DE4433"
font_add_google("Lato")
showtext_auto(enable = TRUE, record = TRUE)
```

```{r}
demo<-read.csv2(file="SocialMedia_Cleaned.csv", sep = ",")
prepost<-read.csv2(file="prepost.csv", sep = ",")
```
## Results
Analysis of 229 respondents revealed insights into age, gender, internet usage, and educational levels impacting social media engagement.

#-------------------Age & Gender-----------

```{r}
favstats(demo$AGE)

demo$AGE<-as.numeric(demo$AGE)

ggplot(demo, aes(x=factor(AGE)))+
  geom_bar(width=0.7, fill="steelblue")+
  theme_minimal()
```

```{r}
ggplot(demo, aes(x=as.factor(AGE), fill=as.factor(AGE) )) + 
  geom_bar(width=0.5, fill = "steelblue") +
  ggtitle("Participant Ages\nMean = 32.06; Standard Deviation = 8.12") +
  xlab("Ages") + ylab("Frequency")+
  scale_y_continuous(limits = c(0, 65), breaks = seq(0, 65, by = 2))

```

```{r}
demo %>% count(GENDER_1)

demo %>% group_by(GENDER_1) %>% count(AGE)
```

```{r}
# ag_2<-demo %>%
#   group_by(GENDER_1) %>% 
#   count(age_group)

demo["age_group"] = cut(demo$AGE, c(18, 20, 30, 40, 50, 60, 70, Inf), c("18-20", "21-30", "31-40", "41-50", "51-60", "61-70", "61-70"), include.lowest=TRUE)
ages <- c("18-20", "21-30", "31-40", "41-50", "51-60", "61-70")
males <- c(0,43,22,5,4,0)
females <- c(1,60,67,16,5,1)
data <- data.frame(males,females,ages)
pyramid(data)

age<-pyramids(Left=males, Llab="Males", Right=females, Rlab="Females", Center = ages,
         Laxis=c(0,10,20,30,40,50,60,70), main="Participants Age - Mean = 32.06; Standard Deviation = 8.12")

```

#-------------------Internet to study--------

```{r}


demo$IN_EDU<-as.factor(demo$IN_EDU)

edu<-demo %>%
  count(IN_EDU)

ggplot(edu, aes(x=IN_EDU, y=n)) +
     geom_bar(stat="identity", fill = "salmon4") +
     ggtitle("Respondents that use internet to study") +
     geom_text(aes(label=n, vjust=-1))+
    xlab("") + ylab("Count")+
    scale_y_continuous(limits = c(0, 230), breaks = seq(0, 230, by = 50))

```

#-------------------Income-----------

```{r}
demo$INCOME<-as.factor(demo$INCOME)
demo %>% count(INCOME)

demo$INCOME <- factor(demo$INCOME, levels=c("Less than $10,000", "$10,000 - $19,999", "$20,000 - $29,999", "$30,000 - $39,999", "$40,000 - $49,999", "$50,000 - $59,999", "$60,000 - $69,999", "$70,000 - $79,999", "$80,000 - $89,999", "$90,000 - $99,999", "$100,000 - $149,999"))

ggplot(demo, aes(x=INCOME, fill=INCOME)) + 
  geom_bar(width=0.5, fill = "chartreuse4") +
  #ggtitle("Annual Income ($)") +
  xlab("Annual Income ($)") + ylab("Count")+ geom_text(stat='count', aes(label=after_stat(count)), vjust=-1)+
  scale_y_continuous(limits = c(0, 60), breaks = seq(0, 60, by = 15))+
  theme(axis.text.x = element_text(angle = 90, vjust = 0.5, hjust=1))+
  scale_x_discrete(limits = c("Less than $10,000", "$10,000 - $19,999", "$20,000 - $29,999", "$30,000 - $39,999", "$40,000 - $49,999", "$50,000 - $59,999", "$60,000 - $69,999", "$70,000 - $79,999", "$80,000 - $89,999", "$90,000 - $99,999", "$100,000 - $149,999"))

```

#-------------------Education-----------

```{r}
demo %>% count(EDU_1)

demo$EDU_1 <- factor(demo$EDU_1, levels=c("High School (Not Completed)", "High School", "Associate's Degree", "Some College coursework", "Bachelor's Degree", "Master's or PhD"))

ggplot(demo, aes(x=EDU_1, fill=EDU_1)) + 
  geom_bar(width=0.5, fill = "darkslategray4") +
  #ggtitle("Annual Income ($)") +
  xlab("Education Levels") + ylab("Count")+ geom_text(stat='count', aes(label=after_stat(count)), vjust=-1)+
  scale_y_continuous(limits = c(0, 150), breaks = seq(0, 150, by = 50))+
  theme(axis.text.x = element_text(angle = 90, vjust = 0.5, hjust=1))
```

#-------------------Living Environment-----------

```{r}
demo %>% count(LOC_1)

demo$LOC_1 <- factor(demo$LOC_1, levels=c("Urban", "Rural", "Other"))

ggplot(demo, aes(x=LOC_1, fill=LOC_1)) + 
  geom_bar(width=0.5, fill = "coral4") +
  #ggtitle("Annual Income ($)") +
  xlab("") + ylab("Count")+ geom_text(stat='count', aes(label=after_stat(count)), vjust=-1)+
  scale_y_continuous(limits = c(0, 150), breaks = seq(0, 150, by = 50))

```

#-------------------Hours spent on internet-----------

```{r}
favstats(demo$HOURS)

demo %>% count(HOURS)

demo$AGE<-as.numeric(demo$HOURS)

ggplot(demo, aes(x=factor(HOURS)))+
  geom_bar(width=0.7, fill="steelblue")+
  theme_minimal()
```

#-------------------PRE-POST-----------

```{r}

favstats(demo$PRE)
favstats(demo$POST)

#prepost$PID<-as.factor(prepost$PID)
prepost$GROUP<-as.factor(prepost$GROUP)
prepost$VALUE<-as.numeric(prepost$VALUE)
prepost$CONDITION<-as.factor(prepost$CONDITION)

```

```{r}
ggplot(prepost, aes(x=GROUPS, y=VALUE, fill=CONDITION)) + 
  geom_bar(position = "dodge", stat = "identity")+
  ylim(0,6)

ggplot(prepost, aes(x=reorder(GROUPS,desc(GROUPS)), y=VALUE, fill=reorder(CONDITION, desc(CONDITION)))) + 
  geom_boxplot()+
  geom_jitter(shape=16, position=position_jitter(0.2))+
  scale_fill_manual(values = wes_palette("Darjeeling2"))+
  xlab("Treatment Method")+
  ylab("Pre and Post Willingness to Engage scores")+
  guides(fill=guide_legend(title="Treatment Condition"))
  
```

```{r}
res_aov<-aov(VALUE ~ CONDITION+GROUPS, data = prepost)

summary(res_aov)
```

```{r}
ggplot(data = demo,
       aes(
         x = EDU_1,
         y = prop.table(stat(count)),
         fill = factor(IN_EDU), width = -6,
         label = scales::percent(prop.table(stat(count)))
       )) +
  geom_bar(position = position_dodge(), width = 0.4) + theme(axis.text = element_text(size = -0.30))+
  geom_text(
    stat = "count",
    position = position_dodge(.8),
    vjust = -1,
    size = 2.5
  ) + scale_y_continuous(labels = scales::percent) +
  theme(axis.text.x = element_text(angle = 90, vjust = 0.5, hjust = 1))+
  labs(title = "Education levels based on internet usage",
       x = "Level of Education",
       y = "Count") +
  theme_classic() +
  scale_fill_discrete(
    name = "Respondents that use internet to study",
    labels = c("No", "Yes")
  )
```

## Discussion
The study's findings emphasize the need for tailored educational strategies considering social media's ubiquitous presence in students' lives.

## Conclusion
This research provides valuable insights for educators and policymakers to leverage social media positively in education.

## Repository Name: Social-Media-Impact-on-Education-Research