Conferencia 24-04-2025

# Instalar si no están presentes
if (!require("tidyverse")) install.packages("tidyverse")

## Loading required package: tidyverse

## -- Attaching packages --------------------------------------- tidyverse 1.3.1 --

## v ggplot2 3.4.4     v purrr   1.0.1
## v tibble  3.2.1     v dplyr   1.1.3
## v tidyr   1.3.0     v stringr 1.5.0
## v readr   2.1.4     v forcats 0.5.1

## Warning: package 'tibble' was built under R version 4.1.3

## Warning: package 'tidyr' was built under R version 4.1.3

## Warning: package 'readr' was built under R version 4.1.3

## Warning: package 'purrr' was built under R version 4.1.3

## Warning: package 'stringr' was built under R version 4.1.3

## -- Conflicts ------------------------------------------ tidyverse_conflicts() --
## x dplyr::filter() masks stats::filter()
## x dplyr::lag()    masks stats::lag()

if (!require("tidytext")) install.packages("tidytext")

## Loading required package: tidytext

## Warning: package 'tidytext' was built under R version 4.1.3

if (!require("wordcloud")) install.packages("wordcloud")

## Loading required package: wordcloud

## Warning: package 'wordcloud' was built under R version 4.1.3

## Loading required package: RColorBrewer

## Warning: package 'RColorBrewer' was built under R version 4.1.3

if (!require("tm")) install.packages("tm")

## Loading required package: tm

## Warning: package 'tm' was built under R version 4.1.3

## Loading required package: NLP

## 
## Attaching package: 'NLP'

## The following object is masked from 'package:ggplot2':
## 
##     annotate

if (!require("textdata")) install.packages("textdata")

## Loading required package: textdata

## Warning: package 'textdata' was built under R version 4.1.3

if (!require("readr")) install.packages("readr")

# Cargar librerías
library(tidyverse)
library(tidytext)
library(wordcloud)
library(tm)
library(textdata)
library(readr)

Carga del Dataset

El dataset se encuentra en:https://drive.google.com/file/d/1PJcyHdI1eUmINPmJtHngxvTncJ9Qmmxb/view?usp=sharing

comentarios <- read_csv("../datasets/comentarios_sentimiento.csv")

## Rows: 150 Columns: 3
## -- Column specification --------------------------------------------------------
## Delimiter: ","
## chr (2): comentario, sentimiento
## dbl (1): id
## 
## i Use `spec()` to retrieve the full column specification for this data.
## i Specify the column types or set `show_col_types = FALSE` to quiet this message.

head(comentarios)

## # A tibble: 6 x 3
##      id comentario                        sentimiento
##   <dbl> <chr>                             <chr>      
## 1     1 Estuvo bien, nada especial.       Neutro     
## 2     2 El servicio fue aceptable.        Neutro     
## 3     3 Estuvo bien, nada especial.       Neutro     
## 4     4 Muy decepcionado con el servicio. Negativo   
## 5     5 Nunca volveré a comprar esto.     Negativo   
## 6     6 Estuvo bien, nada especial.       Neutro

Limpieza de Datos

Convertir a minúsculas

Eliminar puntuación, números y stopwords

Tokenizar las palabras

library(dplyr)
library(tidytext)
library(stringr)

# Convertir a minúsculas y quitar NA
comentarios <- comentarios %>%
  filter(!is.na(comentario)) %>%
  mutate(comentario = tolower(comentario))

# Tokenizar palabras
comentarios_tokens <- comentarios %>%
  unnest_tokens(palabra, comentario)

# Remover palabras vacías (stopwords) y números
data("stop_words")
comentarios_limpios <- comentarios_tokens %>%
  anti_join(stop_words, by = c("palabra" = "word")) %>%
  filter(!str_detect(palabra, "^[0-9]+$"))

Palabras más frecuentes por sentimiento

frecuencias <- comentarios_limpios %>%
  count(sentimiento, palabra, sort = TRUE)

frecuencias %>%
  group_by(sentimiento) %>%
  top_n(10, n) %>%
  ggplot(aes(x = reorder(palabra, n), y = n, fill = sentimiento)) +
  geom_col(show.legend = FALSE) +
  coord_flip() +
  facet_wrap(~ sentimiento, scales = "free") +
  labs(title = "Palabras más frecuentes por sentimiento",
       x = "Palabra", y = "Frecuencia")