data clean

libraries

library(tidyverse)

## ── Attaching packages ───────────────────────────────────────────────────────────────────────── tidyverse 1.2.1 ──

## ✔ ggplot2 3.1.0       ✔ purrr   0.2.5  
## ✔ tibble  2.1.1       ✔ dplyr   0.8.0.1
## ✔ tidyr   0.8.2       ✔ stringr 1.3.1  
## ✔ readr   1.1.1       ✔ forcats 0.3.0

## ── Conflicts ──────────────────────────────────────────────────────────────────────────── tidyverse_conflicts() ──
## ✖ dplyr::filter() masks stats::filter()
## ✖ dplyr::lag()    masks stats::lag()

Trust

Trust news in social media most of the time

Scale:

• Strongly disagree

• Disagree

• Tend to disagree

• Neither agree nor disagree

• Tend to agree

• Agree

• Strongly agree

social_trust <- read_csv("data/trust/social-news-trust.csv")

## Parsed with column specification:
## cols(
##   .default = col_integer(),
##   question = col_character(),
##   question_choice = col_character()
## )

## See spec(...) for full column specifications.

# stack gender
social_trust_gender <- social_trust %>% select(question,question_choice, male, female) %>% gather(gender, count, male, female)

# stack age
social_trust_age <- social_trust %>% select(question, question_choice, `18-24`:`65+`) %>% gather(age, count, `18-24`:`65+`)

#write_csv(social_trust_age, "data/trust/age-socialtrust-split.csv")

Trust news in search engines most of the time

Scale:

• Strongly disagree

• Disagree

• Tend to disagree

• Neither agree nor disagree

• Tend to agree

• Agree

• Strongly agree

search_trust <- read_csv("data/trust/search-news-trust.csv")

## Parsed with column specification:
## cols(
##   .default = col_integer(),
##   question = col_character(),
##   question_choice = col_character()
## )

## See spec(...) for full column specifications.

# stack gender
search_trust_gender <- search_trust %>% select(question, question_choice, male, female) %>% gather(gender, count, male, female)

# stack age
search_trust_age <- search_trust %>% select(question, question_choice, `18-24`:`65+`) %>% gather(age, count, `18-24`:`65+`)

#write_csv(search_trust_age, "data/trust/age-searchtrust-split.csv")

Trust(6-10) vs. Distrust(0-4) in brands

Scale: 1-10

Options:

• Fox News

• CNN

• NBC/MSNBC News

• ABC News

• CBS News

• Yahoo! News

• Local television news

• New York Times

• Washington Post

• HuffPost (Huffington Post)

• Buzzfeed News

• NPR News

• Breitbart

• Wall Street Journal

• Vice News

brand_trust <- read_csv("data/trust/brand-trust-distrust.csv")

## Parsed with column specification:
## cols(
##   .default = col_integer(),
##   trust_level = col_character(),
##   brand = col_character()
## )

## See spec(...) for full column specifications.

# stack gender
brand_trust_gender <- brand_trust %>% select(trust_level, brand, male, female) %>% gather(gender, count, male, female)

# stack age
brand_trust_age <- brand_trust %>% select(trust_level, brand, `18-24`:`65+`) %>% gather(age, count, `18-24`:`65+`)

---

Misinformation

Agree with statements:

• Technology companies (e.g. Facebook and Google) should do more to make it easier to separate what is real and what is fake on the internet

• Media companies and journalists should do more to make it easier to separate what is real and what is fake on the internet

• The Government should do more to make it easier to separate what is real and fake on the internet

Scale:

• Strongly disagree

• Disagree

• Tend to disagree

• Neither agree nor disagree

• Tend to agree

• Agree

• Strongly agree

misinfo_trio <- read_csv("data/misinfo/tech-media-gov.csv")

## Parsed with column specification:
## cols(
##   .default = col_integer(),
##   entity = col_character(),
##   question_choice = col_character()
## )

## See spec(...) for full column specifications.

# stack gender
misinfo_gender <- misinfo_trio %>% select(entity, question_choice, Male, Female) %>% gather(gender, count, Male, Female)

# stack age
misinfo_age <- misinfo_trio %>% select(entity, question_choice, `18-24`:`65+`) %>% gather(age, count, `18-24`:`65+`)

# separate by age groups

misinfo_age_tech <- misinfo_age %>% filter(entity == "Technology companies")
#write_csv(misinfo_age_tech, "data/misinfo/trio-tech.csv")

misinfo_age_media <- misinfo_age %>% filter(entity == "Media companies and journalists")
#write_csv(misinfo_age_media, "data/misinfo/trio-media.csv")

misinfo_age_gov <- misinfo_age %>% filter(entity == "Government")
#write_csv(misinfo_age_gov, "data/misinfo/trio-gov.csv")