05-sentiment-analysis.Rmd

---
title: "Sentiment analysis: Appendix"
author: "Francisco Rowe ([`@fcorowe`](http://twitter.com/fcorowe))"
date: "`r Sys.Date()`"
output: tint::tintHtml
bibliography: skeleton.bib
link-citations: yes
---

```{r setup, include=FALSE}
library(tint)
# handle spatial data
library(sf)
library(spdep)
# manipulate data
library(tidyverse)
# sentiment analysis
library(vader)
# create maps
library(tmap)
# nice colour schemes
library(viridis) 
library(viridisLite)
# invalidate cache when the package version changes
knitr::opts_chunk$set(tidy = FALSE, cache.extra = packageVersion('tint'), class.source = "col-source")
options(htmltools.dir.version = FALSE)
```


```{css, echo=FALSE}
.col-source {
  background-color: #E5E7E9;
  border: 3px #000000;
}
```

```{marginfigure}
[**Back**](04-spatial-econometrics.html) \
```

This notebook contains the code to obtain sentiment analysis scores for a sample of tweets relating to public opinion on migration originated from the United Kingdom during January 1st to December 31st 2019.
 
# Data
```{r}
df <- read_csv("./data/uk_geo_tweets_01012019_31012019.csv")
head(df)
```

# Compute sentiment scores

```{r, warning=FALSE}
vader_sentiment <- vader_df(df$text)
```
# Output

```{r}
final_df <- cbind(df$tweet_id, df$created_at, df$place_name, df$full_place_name, df$lat, df$long, df$exact_coords, df$place_type, df$country_code, df$username, vader_sentiment) %>% 
  rename( 
    tweet_id = "df$tweet_id",
    created_at = "df$created_at", 
    place_name = "df$place_name", 
    full_place_name = "df$full_place_name", 
    lat = "df$long",
    long = "df$lat",
    exact_coords = "df$exact_coords",
    place_type = "df$place_type", 
    country_code = "df$country_code", 
    username = "df$username"
  )

```


# Save
```{r}
write_csv(final_df, "./data/uk-sentiment-data.csv")
```