NGSS stands for Next Generation Science Standards, which are long-standing standards-based educational reform efforts. We investigated the sentiments of multiple stakeholders towards them. To understand how the public feels about this reform, collect and extract opinion data from the Twitter API and use text mining and sentiment analysis techniques to evaluate the various sentiments in California. There are three major questions we want to investigate: 1. What is the public sentiment expressed toward the NGSS? 2. Compared with CCSS, what’s the difference between NGSS? 3. How does sentiment for the California public?
message=FALSE
library(dplyr)
## Warning: package 'dplyr' was built under R version 4.3.2
##
## Attaching package: 'dplyr'
## The following objects are masked from 'package:stats':
##
## filter, lag
## The following objects are masked from 'package:base':
##
## intersect, setdiff, setequal, union
library(readr)
## Warning: package 'readr' was built under R version 4.3.2
library(tidyr)
## Warning: package 'tidyr' was built under R version 4.3.2
library(rtweet)
## Warning: package 'rtweet' was built under R version 4.3.2
library(writexl)
## Warning: package 'writexl' was built under R version 4.3.2
library(readxl)
## Warning: package 'readxl' was built under R version 4.3.2
library(tidytext)
## Warning: package 'tidytext' was built under R version 4.3.2
library(textdata)
## Warning: package 'textdata' was built under R version 4.3.2
library(ggplot2)
## Warning: package 'ggplot2' was built under R version 4.3.2
library(textdata)
library(scales)
## Warning: package 'scales' was built under R version 4.3.2
##
## Attaching package: 'scales'
## The following object is masked from 'package:readr':
##
## col_factor
ngss_tweets <- read_xlsx("~/588/data/ngss_tweets.xlsx")
ccss_tweets <- read_xlsx("~/588/data/ccss_tweets.xlsx")
ngss_text <- filter(ngss_tweets, lang == "en")
ngss_text <- select(ngss_text,screen_name, created_at, text)
ngss_text <- mutate(ngss_text, standards = "ngss")
ngss_text <- relocate(ngss_text, standards)
ngss_text <- select(ngss_text, standards, screen_name, created_at, text)
ngss_text <-
ngss_tweets %>%
filter(lang == "en") %>%
select(screen_name, created_at, text,location) %>%
mutate(standards = "ngss") %>%
relocate(standards)
echo=FALSE
ccss_text <-
ccss_tweets %>%
filter(lang == "en") %>%
select(screen_name, created_at, text,location) %>%
mutate(standards = "ccss") %>%
relocate(standards)
tweets <- bind_rows(ngss_text, ccss_text)
print(tweets)
## # A tibble: 1,441 × 5
## standards screen_name created_at text location
## <chr> <chr> <dttm> <chr> <chr>
## 1 ngss loyr2662 2021-02-27 17:33:27 "Switching gears for a… Philade…
## 2 ngss loyr2662 2021-02-20 20:02:37 "Was just introduced t… Philade…
## 3 ngss Furlow_teach 2021-02-27 17:03:23 "@IBchemmilam @chemmas… Michigan
## 4 ngss Furlow_teach 2021-02-27 14:41:01 "@IBchemmilam @chemmas… Michigan
## 5 ngss TdiShelton 2021-02-27 14:17:34 "I am so honored and a… Kentuck…
## 6 ngss TdiShelton 2021-02-27 15:49:17 "Thank you @brian_woma… Kentuck…
## 7 ngss TdiShelton 2021-02-27 16:51:32 "Please share #NGSScha… Kentuck…
## 8 ngss TdiShelton 2021-02-22 01:57:58 "So excited about this… Kentuck…
## 9 ngss STEMTeachTools 2021-02-26 23:25:03 "The Educators Evaluat… <NA>
## 10 ngss STEMTeachTools 2021-02-23 23:35:05 "Foster existing teach… <NA>
## # ℹ 1,431 more rows
filtered_tweets<-tweets[grepl("CA|Carlifornia",tweets$location),]
#head(tweets)
#tail(tweets)
print(filtered_tweets)
## # A tibble: 46 × 5
## standards screen_name created_at text location
## <chr> <chr> <dttm> <chr> <chr>
## 1 ngss rjmama 2021-02-26 17:56:00 "@SRVUSD_NGSS @Melise… Ohlone …
## 2 ngss flabellinaJG 2021-02-24 19:53:07 "So proud of our @K12… Long Be…
## 3 ngss flabellinaJG 2021-02-26 03:50:06 "Congrats to this mig… Long Be…
## 4 ngss DrDSteele_PhD 2021-02-25 23:46:47 "I have 2 days (3 hrs… Los Ang…
## 5 ngss DrDSteele_PhD 2021-02-26 00:58:39 "@KRenaeP @dtcampbe @… Los Ang…
## 6 ngss KidsMakingSense 2021-02-25 21:00:00 "Our new #KidsMakingS… Petalum…
## 7 ngss RocketLitReads 2021-02-24 23:45:11 "It's share time! Wha… Los Ang…
## 8 ngss the_fish_nerd 2021-02-24 22:49:58 "We had \"art class\"… Winches…
## 9 ngss InnerOrbitedu 2021-02-24 20:02:04 "What IS Elephant Too… Los Ang…
## 10 ngss casciencecenter 2021-02-24 20:01:14 "\U0001f514 ATTN: Tea… Los Ang…
## # ℹ 36 more rows
tweet_tokens <-
tweets %>%
unnest_tokens(output = word,
input = text,)
tidy_tweets <-
tweet_tokens %>%
anti_join(stop_words, by = "word")
count(tidy_tweets, word, sort = T)
## # A tibble: 7,163 × 2
## word n
## <chr> <int>
## 1 common 1112
## 2 core 1109
## 3 https 623
## 4 t.co 623
## 5 math 450
## 6 ngss 224
## 7 students 141
## 8 science 140
## 9 school 128
## 10 amp 127
## # ℹ 7,153 more rows
filter(tweets, grepl('amp', text))
## # A tibble: 124 × 5
## standards screen_name created_at text location
## <chr> <chr> <dttm> <chr> <chr>
## 1 ngss TdiShelton 2021-02-27 14:17:34 "I am so honored and a… Kentuck…
## 2 ngss STEMTeachTools 2021-02-27 16:25:04 "Open, non-hierarchica… <NA>
## 3 ngss NGSSphenomena 2021-02-25 13:24:22 "Bacteria have music p… <NA>
## 4 ngss CTSKeeley 2021-02-21 21:50:04 "Today I was thinking … Maine a…
## 5 ngss richbacolor 2021-02-24 14:14:49 "Last chance to regist… Ann Arb…
## 6 ngss MrsEatonELL 2021-02-27 06:24:09 "Were we doing the han… <NA>
## 7 ngss STEMuClaytion 2021-02-24 14:56:19 "#WonderWednesday w/ q… Olean, …
## 8 ngss LearningUNDFTD 2021-02-24 18:13:01 "Are candies like M&am… Gaither…
## 9 ngss abeslo 2021-02-26 18:54:31 "#M'Kenna, whose story… Philade…
## 10 ngss E3Chemistry 2021-02-25 14:15:20 "Molarity & Parts … excite …
## # ℹ 114 more rows
tidy_tweets <-
tweet_tokens %>%
anti_join(stop_words, by = "word") %>%
filter(!word == "amp") %>%
filter(!word == "t3ic") %>%
filter(!word == "https")
afinn <- get_sentiments("afinn")
bing <- get_sentiments("bing")
nrc <- get_sentiments("nrc")
loughran <- get_sentiments("loughran")
sentiment_afinn <- inner_join(tidy_tweets, afinn, by = "word")
sentiment_bing <- inner_join(tidy_tweets, bing, by = "word")
#`echo=F, results=F`
sentiment_nrc <- inner_join(tidy_tweets, nrc, by = "word")
## Warning in inner_join(tidy_tweets, nrc, by = "word"): Detected an unexpected many-to-many relationship between `x` and `y`.
## ℹ Row 24 of `x` matches multiple rows in `y`.
## ℹ Row 7509 of `y` matches multiple rows in `x`.
## ℹ If a many-to-many relationship is expected, set `relationship =
## "many-to-many"` to silence this warning.
sentiment_loughran <- inner_join(tidy_tweets, loughran, by = "word")
## Warning in inner_join(tidy_tweets, loughran, by = "word"): Detected an unexpected many-to-many relationship between `x` and `y`.
## ℹ Row 2297 of `x` matches multiple rows in `y`.
## ℹ Row 2302 of `y` matches multiple rows in `x`.
## ℹ If a many-to-many relationship is expected, set `relationship =
## "many-to-many"` to silence this warning.
ts_plot(tweets, by = "days")
echo=F
tweets %>%
group_by(standards) %>%
ts_plot(by = "days")
summary_bing <- count(sentiment_bing, sentiment, sort = TRUE)
summary_bing
## # A tibble: 2 × 2
## sentiment n
## <chr> <int>
## 1 negative 992
## 2 positive 676
summary_bing <- sentiment_bing %>%
group_by(standards) %>%
count(sentiment)
summary_bing <- sentiment_bing %>%
group_by(standards) %>%
count(sentiment, sort = TRUE) %>%
spread(sentiment, n)
summary_bing <- sentiment_bing %>%
group_by(standards) %>%
count(sentiment, sort = TRUE) %>%
spread(sentiment, n) %>%
mutate(sentiment = positive - negative) %>%
mutate(lexicon = "bing") %>%
relocate(lexicon)
head(sentiment_afinn)
## # A tibble: 6 × 6
## standards screen_name created_at location word value
## <chr> <chr> <dttm> <chr> <chr> <dbl>
## 1 ngss loyr2662 2021-02-27 17:33:27 Philadelphia, PA win 4
## 2 ngss Furlow_teach 2021-02-27 17:03:23 Michigan love 3
## 3 ngss Furlow_teach 2021-02-27 17:03:23 Michigan sweet 2
## 4 ngss Furlow_teach 2021-02-27 17:03:23 Michigan signific… 1
## 5 ngss TdiShelton 2021-02-27 14:17:34 Kentucky& Tennessee honored 2
## 6 ngss TdiShelton 2021-02-27 14:17:34 Kentucky& Tennessee opportun… 2
summary_afinn <- sentiment_afinn %>%
group_by(standards) %>%
summarise(sentiment = sum(value)) %>%
mutate(lexicon = "AFINN") %>%
relocate(lexicon)
nrc
## # A tibble: 13,872 × 2
## word sentiment
## <chr> <chr>
## 1 abacus trust
## 2 abandon fear
## 3 abandon negative
## 4 abandon sadness
## 5 abandoned anger
## 6 abandoned fear
## 7 abandoned negative
## 8 abandoned sadness
## 9 abandonment anger
## 10 abandonment fear
## # ℹ 13,862 more rows
#`echo=FALSE,message=FALSE`
summary_nrc <- sentiment_nrc %>%
filter(sentiment %in% c("positive", "negative")) %>%
group_by(standards) %>%
count(sentiment, sort = TRUE) %>%
mutate(method = "nrc") %>%
spread(sentiment, n) %>%
mutate(sentiment = positive/negative)
summary_afinn <- sentiment_afinn %>%
group_by(standards) %>%
summarise(sentiment = sum(value)) %>%
mutate(lexicon = "AFINN") %>%
relocate(lexicon)
ngss_text <-
ngss_tweets %>%
filter(lang == "en") %>%
select(status_id, text) %>%
mutate(standards = "ngss") %>%
relocate(standards)
ccss_text <-
ccss_tweets %>%
filter(lang == "en") %>%
select(status_id, text) %>%
mutate(standards = "ccss") %>%
relocate(standards)
tweets <- bind_rows(ngss_text, ccss_text)
tweets
## # A tibble: 1,441 × 3
## standards status_id text
## <chr> <chr> <chr>
## 1 ngss 1365716690336645124 "Switching gears for a bit for the \"Crosscutt…
## 2 ngss 1363217513761415171 "Was just introduced to the Engineering Habits…
## 3 ngss 1365709122763653133 "@IBchemmilam @chemmastercorey I’m familiar w/…
## 4 ngss 1365673294360420353 "@IBchemmilam @chemmastercorey How well does t…
## 5 ngss 1365667393188601857 "I am so honored and appreciative to have an o…
## 6 ngss 1365690477266284545 "Thank you @brian_womack I loved connecting wi…
## 7 ngss 1365706140496130050 "Please share #NGSSchat PLN! https://t.co/Qc2c…
## 8 ngss 1363669328147677189 "So excited about this weekend’s learning... p…
## 9 ngss 1365442786544214019 "The Educators Evaluating the Quality of Instr…
## 10 ngss 1364358149164175362 "Foster existing teacher social networks that …
## # ℹ 1,431 more rows
message=FALSE
#sentiment_afinn <- tweets %>%
# unnest_tokens(output = word,
# input = text,
# token = "tweets") %>%
# anti_join(stop_words, by = "word") %>%
# filter(!word == "amp") %>%
# inner_join(afinn, by = "word")
sentiment_afinn <- tweets %>%
unnest_tokens(output = word, input = text) %>%
anti_join(stop_words, by = "word") %>%
filter(!word == "amp") %>%
inner_join(afinn, by = "word")
sentiment_afinn
## # A tibble: 1,540 × 4
## standards status_id word value
## <chr> <chr> <chr> <dbl>
## 1 ngss 1365716690336645124 win 4
## 2 ngss 1365709122763653133 love 3
## 3 ngss 1365709122763653133 sweet 2
## 4 ngss 1365709122763653133 significance 1
## 5 ngss 1365667393188601857 honored 2
## 6 ngss 1365667393188601857 opportunity 2
## 7 ngss 1365667393188601857 wonderful 4
## 8 ngss 1365667393188601857 powerful 2
## 9 ngss 1365690477266284545 loved 3
## 10 ngss 1365706140496130050 share 1
## # ℹ 1,530 more rows
message=FALSE
afinn_score <- sentiment_afinn %>%
group_by(standards, status_id) %>%
summarise(value = sum(value))
## `summarise()` has grouped output by 'standards'. You can override using the
## `.groups` argument.
afinn_score
## # A tibble: 857 × 3
## # Groups: standards [2]
## standards status_id value
## <chr> <chr> <dbl>
## 1 ccss 1362894990813188096 2
## 2 ccss 1362899370199445508 4
## 3 ccss 1362906588021989376 -2
## 4 ccss 1362910494487535618 -9
## 5 ccss 1362910913855160320 -1
## 6 ccss 1362928225379250179 2
## 7 ccss 1362933982074073090 -1
## 8 ccss 1362947497258151945 -3
## 9 ccss 1362949805694013446 3
## 10 ccss 1362970614282264583 3
## # ℹ 847 more rows
afinn_sentiment <- afinn_score %>%
filter(value != 0) %>%
mutate(sentiment = if_else(value < 0, "negative", "positive"))
afinn_sentiment
## # A tibble: 820 × 4
## # Groups: standards [2]
## standards status_id value sentiment
## <chr> <chr> <dbl> <chr>
## 1 ccss 1362894990813188096 2 positive
## 2 ccss 1362899370199445508 4 positive
## 3 ccss 1362906588021989376 -2 negative
## 4 ccss 1362910494487535618 -9 negative
## 5 ccss 1362910913855160320 -1 negative
## 6 ccss 1362928225379250179 2 positive
## 7 ccss 1362933982074073090 -1 negative
## 8 ccss 1362947497258151945 -3 negative
## 9 ccss 1362949805694013446 3 positive
## 10 ccss 1362970614282264583 3 positive
## # ℹ 810 more rows
afinn_ratio <- afinn_sentiment %>%
group_by(standards) %>%
count(sentiment) %>%
spread(sentiment, n) %>%
mutate(ratio = negative/positive)
afinn_ratio
## # A tibble: 2 × 4
## # Groups: standards [2]
## standards negative positive ratio
## <chr> <int> <int> <dbl>
## 1 ccss 421 211 2.00
## 2 ngss 21 167 0.126
afinn_counts <- afinn_sentiment %>%
group_by(standards) %>%
count(sentiment) %>%
filter(standards == "ngss")
afinn_counts %>%
ggplot(aes(x="", y=n, fill=sentiment)) +
geom_bar(width = .6, stat = "identity") +
labs(title = "Next Gen Science Standards",
subtitle = "Proportion of Positive & Negative Tweets") +
coord_polar(theta = "y") +
theme_void()
summary_afinn2 <- sentiment_afinn %>%
group_by(standards) %>%
filter(value != 0) %>%
mutate(sentiment = if_else(value < 0, "negative", "positive")) %>%
count(sentiment, sort = TRUE) %>%
mutate(method = "AFINN")
summary_bing2 <- sentiment_bing %>%
group_by(standards) %>%
count(sentiment, sort = TRUE) %>%
mutate(method = "bing")
summary_nrc2 <- sentiment_nrc %>%
filter(sentiment %in% c("positive", "negative")) %>%
group_by(standards) %>%
count(sentiment, sort = TRUE) %>%
mutate(method = "nrc")
summary_loughran2 <- sentiment_loughran %>%
filter(sentiment %in% c("positive", "negative")) %>%
group_by(standards) %>%
count(sentiment, sort = TRUE) %>%
mutate(method = "loughran")
summary_sentiment <- bind_rows(summary_afinn2,
summary_bing2,
summary_nrc2,
summary_loughran2) %>%
arrange(method, standards) %>%
relocate(method)
total_counts <- summary_sentiment %>%
group_by(method, standards) %>%
summarise(total = sum(n))
## `summarise()` has grouped output by 'method'. You can override using the
## `.groups` argument.
sentiment_counts <- left_join(summary_sentiment, total_counts)
## Joining with `by = join_by(method, standards)`
sentiment_percents <- sentiment_counts %>%
mutate(percent = n/total * 100)
sentiment_percents %>%
ggplot(aes(x = standards, y = percent, fill=sentiment)) +
geom_bar(width = .8, stat = "identity") +
facet_wrap(~method, ncol = 1) +
coord_flip() +
labs(title = "Public Sentiment on Twitter",
subtitle = "The Common Core & Next Gen Science Standards",
x = "State Standards",
y = "Percentage of Words")