Análisis Interactivo del Rendimiento de Videos en TikTok

Análisis Interactivo del Rendimiento de Videos en TikTok

Desarrollo de un dashboard para evaluar métricas de rendimiento de contenidos en TikTok, transformación de datos, genera 4 visualizaciones interactivas (Plotly/ggplot) con interpretaciones detalladas.

library(shiny)

## Warning: package 'shiny' was built under R version 4.4.3

library(tidyverse)

## Warning: package 'tidyverse' was built under R version 4.4.3

## Warning: package 'ggplot2' was built under R version 4.4.3

## Warning: package 'tidyr' was built under R version 4.4.3

## Warning: package 'purrr' was built under R version 4.4.3

## Warning: package 'dplyr' was built under R version 4.4.3

## Warning: package 'stringr' was built under R version 4.4.3

## Warning: package 'forcats' was built under R version 4.4.3

## Warning: package 'lubridate' was built under R version 4.4.3

## ── Attaching core tidyverse packages ──────────────────────── tidyverse 2.0.0 ──
## ✔ dplyr     1.1.4     ✔ readr     2.1.5
## ✔ forcats   1.0.0     ✔ stringr   1.5.1
## ✔ ggplot2   3.5.2     ✔ tibble    3.2.1
## ✔ lubridate 1.9.4     ✔ tidyr     1.3.1
## ✔ purrr     1.0.4     
## ── Conflicts ────────────────────────────────────────── tidyverse_conflicts() ──
## ✖ dplyr::filter() masks stats::filter()
## ✖ dplyr::lag()    masks stats::lag()
## ℹ Use the conflicted package (<http://conflicted.r-lib.org/>) to force all conflicts to become errors

library(plotly)

## Warning: package 'plotly' was built under R version 4.4.3

## 
## Adjuntando el paquete: 'plotly'
## 
## The following object is masked from 'package:ggplot2':
## 
##     last_plot
## 
## The following object is masked from 'package:stats':
## 
##     filter
## 
## The following object is masked from 'package:graphics':
## 
##     layout

library(DT)

## Warning: package 'DT' was built under R version 4.4.3

## 
## Adjuntando el paquete: 'DT'
## 
## The following objects are masked from 'package:shiny':
## 
##     dataTableOutput, renderDataTable

tiktok <- read.csv("tiktok_dataset.csv", stringsAsFactors = FALSE)
names(tiktok)

##  [1] "X."                       "claim_status"            
##  [3] "video_id"                 "video_duration_sec"      
##  [5] "video_transcription_text" "verified_status"         
##  [7] "author_ban_status"        "video_view_count"        
##  [9] "video_like_count"         "video_share_count"       
## [11] "video_download_count"     "video_comment_count"

Limpieza y Transformación de Datos

# Renombrar columnas para consistencia
colnames(tiktok) <- tolower(colnames(tiktok))

# Limpieza de caracteres no numéricos (como comas)
tiktok <- tiktok %>%
  mutate(
    video_view_count = as.numeric(gsub(",", "", video_view_count)),
    video_like_count = as.numeric(gsub(",", "", video_like_count)),
    video_comment_count = as.numeric(gsub(",", "", video_comment_count)),
    video_share_count = as.numeric(gsub(",", "", video_share_count))
  )

## Warning: There were 4 warnings in `mutate()`.
## The first warning was:
## ℹ In argument: `video_view_count = as.numeric(gsub(",", "",
##   video_view_count))`.
## Caused by warning:
## ! NAs introducidos por coerción
## ℹ Run `dplyr::last_dplyr_warnings()` to see the 3 remaining warnings.

# Eliminar filas incompletas
cat("Filas antes de na.omit:", nrow(tiktok), "\n")

## Filas antes de na.omit: 19382

tiktok <- na.omit(tiktok)
cat("Filas después de na.omit:", nrow(tiktok), "\n")

## Filas después de na.omit: 19084

# Crear variable engagement_rate
tiktok <- tiktok %>%
  mutate(engagement_rate = (video_like_count + video_comment_count + video_share_count) / video_view_count)

Visualizaciones Interactivas

1.- Distribución de vistas de los videos:

plot_ly(tiktok, x = ~video_view_count, type = "histogram", nbinsx = 30) %>%
  layout(title = "Distribución de Vistas",
         xaxis = list(title = "Vistas"),
         yaxis = list(title = "Cantidad de Videos"))

2.- Relación vistas vs likes:

plot_ly(tiktok, x = ~video_view_count, y = ~video_like_count, type = 'scatter', mode = 'markers') %>%
  layout(title = "Relación entre Vistas y Likes",
         xaxis = list(title = "Vistas"),
         yaxis = list(title = "Likes"))

3.- Comparacion entre los Top 20 Videos mas vistos:

top_videos <- tiktok %>%
  arrange(desc(video_view_count)) %>%
  slice_head(n = 20) %>%
  mutate(video_id = factor(video_id, levels = video_id[order(video_view_count)]))

ggplotly(
  ggplot(top_videos, aes(x = video_id, y = engagement_rate)) +
    geom_bar(stat = "identity", fill = "gold") +
    labs(title = "Los 20 Videos más Vistos", x = "Video ID", y = "Engagement Rate") +
    theme(axis.text.x = element_text(angle = 90, vjust = 0.5, hjust=1))
)

4.- Correlacion multiple:

plot_ly(tiktok, x = ~video_like_count, y = ~video_comment_count, z = ~video_share_count,
        type = "scatter3d", mode = "markers",
        marker = list(size = 3, color = ~video_view_count, colorscale = 'Viridis')) %>%
  layout(title = "Relación entre Likes, Comentarios y Shares")

Conclusion:

El análisis desarrolla un dashboard que evalua el rendimiento de videos en TikTok, integrando limpieza de datos (normalización, tratamiento de limpieza de datos) y creación de métricas como el engagement rate. Las visualizaciones revelan:

1.- Distribución de vistas concentrada en valores moderados,

2.- Relación positiva entre vistas y likes,

3.- Alta variabilidad en engagement en los top 20 videos. Herramientas como Plotly y ggplot permiten explorar dinámicamente los datos, facilitando la identificación de patrones clave para optimizar estrategias de contenido.

4.- Correlacion multiple que se muestra una relación tridimensional entre engagement (likes, comentarios, shares), con vistas como color para profundidad.