15-sentiment
Load the Data
Random (?) sample of 26,882 reviews of coursera courses (Source: Kaggle)
en_coursera_reviews <- read_csv("https://stat220-f26.github.io/data/en_coursera_sample.csv")
en_coursera_reviews# A tibble: 26,882 × 5
CourseId Review Label cld2 review_id
<chr> <chr> <dbl> <chr> <dbl>
1 nurture-market-strategies It would be better if the … 1 en 1
2 nand2tetris2 Superb course. Great prese… 5 en 2
3 schedule-projects Excellent course! 5 en 3
4 teaching-english-capstone-2 I'd recommend this course … 5 en 4
5 machine-learning This course was so effecti… 5 en 5
6 python-network-data Words cannot describe how … 5 en 6
7 clinical-trials Great course! 5 en 7
8 python-genomics I didn't know anything abo… 3 en 8
9 strategic-management Loved everything about thi… 5 en 9
10 script-writing No significant instruction… 1 en 10
# ℹ 26,872 more rowsLoad Sentiment data
“bing”
bing_sentiments = get_sentiments("bing") %>%
slice_sample(n = 20)“afinn”
library(textdata)
get_sentiments("afinn") %>%
slice_sample(n = 20)# A tibble: 20 × 2
word value
<chr> <dbl>
1 weary -2
2 comforting 2
3 novel 2
4 substantially 1
5 costly -2
6 appreciated 2
7 piteous -2
8 excite 3
9 revered 2
10 flu -2
11 cancelling -1
12 benefits 2
13 beautify 3
14 unconcerned -2
15 fortunate 2
16 vulnerability -2
17 goddamn -3
18 restore 1
19 menace -2
20 enlightens 2Sentiment of each review
bing_review_scores <- en_coursera_reviews %>%
unnest_tokens(word, Review) %>%
inner_join(bing_sentiments, by = "word") %>%
group_by(review_id) %>%
summarize(
sum = (sum(sentiment == "positive") - sum(sentiment == "negative"))
)
bing_review_scores# A tibble: 6 × 2
review_id sum
<dbl> <int>
1 766 -1
2 3768 1
3 13782 -1
4 15401 -1
5 15988 -1
6 23226 -1