Analisis Sentimen di R

Gambaran Umum Analisis Sentimen

library(tidytext)

# Available sentiment lexicons
# AFINN: -5 to +5 numeric score
# Bing:  binary positive/negative
# NRC:   emotion categories (joy, fear, anger, ...)

# Preview AFINN
afinn_sample <- get_sentiments('afinn')
cat('AFINN rows:', nrow(afinn_sample), '\n')
cat('Score range:', range(afinn_sample$value), '\n')
print(head(afinn_sample, 5))

get_sentiments('afinn')

library(tidytext)
library(dplyr)

afinn <- get_sentiments('afinn')

# Most positive and most negative words
cat('Most positive words:\n')
print(afinn |> slice_max(value, n = 5))

cat('\nMost negative words:\n')
print(afinn |> slice_min(value, n = 5))

# Score distribution
cat('\nScore distribution:\n')
print(table(afinn$value))

get_sentiments('bing')

library(tidytext)
library(dplyr)

bing <- get_sentiments('bing')

cat('Bing lexicon size:', nrow(bing), '\n')
cat('Positive words:', sum(bing$sentiment == 'positive'), '\n')
cat('Negative words:', sum(bing$sentiment == 'negative'), '\n')

# Sample positive and negative words
cat('\nSample positive:', head(bing$word[bing$sentiment == 'positive'], 8), '\n')
cat('Sample negative:', head(bing$word[bing$sentiment == 'negative'], 8), '\n')

inner_join: Menilai Kata

library(tidytext)
library(dplyr)

reviews <- tibble::tibble(
  review_id = 1:3,
  text = c(
    'The product is excellent and outstanding quality',
    'Terrible experience, broken and disappointing',
    'Good value but slow delivery, acceptable overall'
  )
)

scored <- reviews |>
  unnest_tokens(word, text) |>
  inner_join(get_sentiments('afinn'), by = 'word')

cat('Scored words:\n')
print(scored[, c('review_id', 'word', 'value')])

Sentimen Bersih per Dokumen

library(tidytext)
library(dplyr)

reviews <- tibble::tibble(
  review_id = 1:5,
  text = c(
    'excellent outstanding perfect love best amazing',
    'terrible broken horrible awful waste money',
    'good acceptable okay decent average',
    'brilliant fantastic outstanding love recommend',
    'poor bad disappointing slow useless'
  )
)

net_sentiment <- reviews |>
  unnest_tokens(word, text) |>
  inner_join(get_sentiments('afinn'), by = 'word') |>
  group_by(review_id) |>
  summarise(
    sentiment  = sum(value),
    word_count = n()
  ) |>
  mutate(polarity = ifelse(sentiment > 0, 'positive', 'negative'))

print(net_sentiment)

Sentimen Bing: Jumlah Positif vs Negatif

library(tidytext)
library(dplyr)

corpus <- tibble::tibble(
  chapter = 1:4,
  text = c(
    'the hero was brave courageous strong and victorious in battle',
    'disaster struck terrible losses failure defeat mourning grief',
    'love joy happiness beautiful peaceful wonderful morning',
    'evil darkness corrupt wicked terrible pain suffering fear'
  )
)

bing_sentiment <- corpus |>
  unnest_tokens(word, text) |>
  inner_join(get_sentiments('bing'), by = 'word') |>
  count(chapter, sentiment) |>
  tidyr::pivot_wider(names_from = sentiment, values_from = n, values_fill = 0) |>
  mutate(net = positive - negative)

print(bing_sentiment)

Sentimen berdasarkan Bab atau Bagian

library(tidytext)
library(dplyr)
library(ggplot2)

# Simulate a 10-chapter story arc
set.seed(42)
chapters <- tibble::tibble(
  chapter = 1:10,
  text    = c(
    'peaceful beautiful joy love happy wonderful',
    'good friends happy carefree enjoyable fun',
    'worried anxious trouble fear uncertain dark',
    'danger terrible threat awful pain suffering',
    'fear horror disaster terrible devastation loss',
    'fight battle struggle hard difficult challenge',
    'hope courage determination brave strong resist',
    'triumph victory success celebrate joy love',
    'relief peace gratitude wonderful blessed happy',
    'love joy peace beautiful grateful wonderful'
  )
)

arc <- chapters |>
  unnest_tokens(word, text) |>
  inner_join(get_sentiments('afinn'), by = 'word') |>
  group_by(chapter) |>
  summarise(net_sentiment = sum(value))

ggplot(arc, aes(chapter, net_sentiment)) +
  geom_line(color = 'steelblue', linewidth = 1.2) +
  geom_hline(yintercept = 0, linetype = 'dashed') +
  labs(x = 'Chapter', y = 'Net Sentiment', title = 'Story Sentiment Arc') +
  theme_minimal()

Leksikon NRC: Kategori Emosi

library(tidytext)
library(dplyr)

nrc <- get_sentiments('nrc')
cat('NRC size:', nrow(nrc), '\n')
cat('Emotions:', paste(unique(nrc$sentiment), collapse = ', '), '\n')

# Words associated with 'joy'
joy_words <- nrc |> filter(sentiment == 'joy')
cat('\nJoy words:', nrow(joy_words), '\n')
cat('Sample:', head(joy_words$word, 10), '\n')

# Count words per emotion
nrc |>
  count(sentiment, sort = TRUE) |>
  print()

Menerapkan NRC pada Korpus

library(tidytext)
library(dplyr)

docs <- tibble::tibble(
  doc_id = c(1, 1, 2, 2, 3, 3),
  text   = c(
    'wonderful joyful happy love peace',
    'excited surprise anticipation trust',
    'fear anger terrible hate disgust',
    'dark horrible awful suffering pain',
    'curious wonder discovery learning',
    'hope trust anticipation future growth'
  )
)

nrc_scores <- docs |>
  unnest_tokens(word, text) |>
  inner_join(get_sentiments('nrc'), by = 'word') |>
  filter(!sentiment %in% c('positive', 'negative')) |>  # keep only emotions
  count(doc_id, sentiment, sort = TRUE)

cat('Emotion counts per document:\n')
print(nrc_scores)

Konsep Awan Kata

library(tidytext)
library(dplyr)

# Prepare word frequencies coloured by Bing sentiment
corpus_text <- tibble::tibble(
  text = c(
    'excellent performance amazing results love beautiful',
    'terrible failure poor broken horrible waste',
    'brilliant outstanding success happy wonderful joy',
    'awful disappointing bad slow useless frustrating'
  )
)

word_freq <- corpus_text |>
  unnest_tokens(word, text) |>
  count(word, sort = TRUE) |>
  left_join(get_sentiments('bing'), by = 'word') |>
  mutate(
    sentiment = replace(sentiment, is.na(sentiment), 'neutral'),
    colour    = case_when(
      sentiment == 'positive' ~ '#2196F3',
      sentiment == 'negative' ~ '#F44336',
      TRUE                    ~ '#9E9E9E'
    )
  )

print(word_freq)
# In practice: wordcloud2(word_freq[, c('word','n')], color = word_freq$colour)

Keterbatasan Sentimen Berbasis Leksikon

library(tidytext)
library(dplyr)

# Negation problem
neg_examples <- tibble::tibble(
  text = c(
    'not good at all',   # negative, but 'good' scores +3
    'not bad',           # positive, but 'bad' scores -3
    'sick beats bro'     # slang positive, 'sick' is negative in AFINN
  )
)

scored <- neg_examples |>
  unnest_tokens(word, text) |>
  inner_join(get_sentiments('afinn'), by = 'word')

cat('Lexicon scores (naive - ignores negation):\n')
print(scored[, c('word', 'value')])
cat('\nNote: "not" is a stop word - the negation is lost!\n')

Pemeriksaan Singkat

Ringkasan: Analisis Sentimen

library(tidytext)
library(dplyr)

tibble::tibble(text = 'excellent amazing love joy beautiful happy') |>
  unnest_tokens(word, text) |>
  inner_join(get_sentiments('afinn'), by = 'word') |>
  summarise(net_sentiment = sum(value)) |>
  print()