Whole Class Feedback Script Example I - Academic Listening
Chris Elvin
6/13/2021
Load Libraries
library(tidyverse)## ── Attaching packages ─────────────────────────────────────── tidyverse 1.3.1 ──## ✓ ggplot2 3.3.3 ✓ purrr 0.3.4
## ✓ tibble 3.1.1 ✓ dplyr 1.0.6
## ✓ tidyr 1.1.3 ✓ stringr 1.4.0
## ✓ readr 1.4.0 ✓ forcats 0.5.1## ── Conflicts ────────────────────────────────────────── tidyverse_conflicts() ──
## x dplyr::filter() masks stats::filter()
## x dplyr::lag() masks stats::lag()library(readtext)
library(quanteda)## Package version: 3.0.0
## Unicode version: 10.0
## ICU version: 61.1## Parallel computing: 4 of 4 threads used.## See https://quanteda.io for tutorials and examples.library(quanteda.textstats)Build a corpus.
x <- list.files(pattern = "docx") %>%
readtext(ignore_missing_files = T) %>%
texts %>% corpus()Extract summaries.
summary_start <- str_locate(x, "Summary")[,2]
summary_end <- str_locate(x, "Opinion")[,1]
summary <- str_sub(x, summary_start + 1, summary_end - 1) %>% str_squishExtract opinions.
opinion_start <- str_locate(x, "Opinion")[,2]
opinion_end <- str_locate(x, "What")[,1]
opinion <- str_sub(x, opinion_start +1, opinion_end - 4) %>% str_squishCommon Words for Students’ Summaries
summary %>% tokens(remove_punct=T,
remove_symbols = T,
remove_numbers = T) %>% dfm %>%
dfm_remove(stopwords("en")) %>%
textstat_frequency() %>%
summarise(word = feature, frequency) %>%
filter(frequency>5) %>%
arrange(-frequency, word) word frequency
1 skin 94
2 color 81
3 people 44
4 humanae 27
5 discrimination 23
6 many 22
7 world 22
8 project 18
9 colors 14
10 also 12
11 black 12
12 first 12
13 impression 12
14 speaker 12
15 still 11
16 family 10
17 however 10
18 photographer 10
19 started 10
20 white 10
21 angelica 9
22 different 9
23 work 9
24 called 8
25 important 8
26 race 8
27 various 8
28 abolished 7
29 can 7
30 lot 7
31 pictures 7
32 public 7
33 human 6
34 meanings 6
35 places 6
36 tones 6
37 took 6
38 use 6
39 used 6
40 years 6Rare Words for Students’ Summaries
summary %>% tokens(remove_punct=T,
remove_symbols = T,
remove_numbers = T) %>% dfm %>%
dfm_remove(stopwords("en")) %>%
textstat_frequency() %>%
filter(frequency==1) %>%
summarize(word = feature) %>%
arrange(word) word
1 academia
2 act
3 actions
4 added
5 addition
6 adds
7 advantage
8 affairs
9 affect
10 affected
11 ages
12 allow
13 allowed
14 allows
15 although
16 always
17 ambassador
18 angela's
19 angelica's
20 appeared
21 applying
22 argue
23 aruond
24 automatically
25 babysitter
26 backgrounds
27 bad
28 barrier
29 beauty
30 became
31 beings
32 beliefs
33 belong
34 big
35 blacks
36 brazil
37 brazilian
38 brown
39 call
40 capture
41 casts
42 caused
43 chance
44 change
45 changed
46 children
47 cities
48 classification
49 classify
50 colour
51 communication
52 communities
53 community
54 completely
55 complicated
56 computer
57 confident
58 conflict
59 conflicts
60 consciousness
61 continues
62 convey
63 copies
64 corner
65 corresponding
66 country
67 cousin
68 cover
69 covered
70 creative
71 dark
72 darker
73 day
74 describes
75 determine
76 disabilities
77 disapprear
78 discimination
79 discover
80 discremination
81 distinction
82 distinctions
83 drawing
84 due
85 elevator
86 eliminated
87 eliminating
88 encouraged
89 eradicate
90 especially
91 establishing
92 etc
93 every
94 everybody
95 everyone's
96 evolves
97 example
98 exhibition
99 exhibitions
100 exist
101 expanded
102 experiencing
103 experiments
104 explanations
105 express
106 expressed
107 expressiveness
108 extend
109 families
110 fear
111 fears
112 field
113 filmed
114 finally
115 finding
116 finds
117 fitting
118 focusing
119 foreigh
120 found
121 furthermore
122 gathered
123 gave
124 gives
125 globe
126 got
127 gradually
128 great
129 groups
130 growed
131 grown
132 hand
133 hard
134 heading
135 help
136 helping
137 highlight
138 history
139 hoped
140 horrible
141 humanage
142 humanse
143 illustrators
144 impact
145 impressions
146 incident
147 including
148 individual
149 individual's
150 inferiority
151 inquired
152 insists
153 interested
154 interesting
155 internet
156 introduced
157 judge
158 judged
159 judging
160 kid
161 kinds
162 king
163 king's
164 label
165 large
166 later
167 latest
168 launched
169 lesson
170 life
171 live
172 living
173 loneliness
174 looking
175 lovely
176 lower
177 makes
178 making
179 manage
180 marriage
181 married
182 masses
183 material
184 matter
185 means
186 meant
187 media
188 members
189 mentioned
190 mirrored
191 mistake
192 mistaked
193 misunderstood
194 mixed
195 mold
196 movement
197 must
198 natural
199 near
200 needs
201 neglecting
202 never
203 nevertheless
204 new
205 nose
206 notice
207 number
208 ongoing
209 origin
210 outside
211 painted
212 painting
213 palette
214 pantone
215 pastes
216 pattern
217 person's
218 persuades
219 photograph
220 photographs
221 photography
222 physical
223 poor
224 posted
225 present
226 proud
227 provides
228 published
229 pursuing
230 pursuit
231 pursuited
232 questions
233 racism
234 raised
235 reason
236 received
237 recognized
238 recognizes
239 reconsider
240 regarded
241 regardless
242 religion
243 remove
244 removing
245 researchers
246 respects
247 rich
248 roads
249 science
250 seek
251 self-portraits
252 separate
253 servant
254 shadow
255 show
256 showed
257 shown
258 shows
259 simple
260 simply
261 slavely
262 social
263 solve
264 someone
265 somewhere
266 soon
267 sort
268 space
269 spaces
270 spaniard
271 speaker's
272 stare
273 start
274 stereotype
275 stereotypes
276 stereotypical
277 stopped
278 street
279 strive
280 strong
281 struggled
282 suffer
283 suffered
284 suffering
285 surrounded
286 switzerland
287 take
288 taken
289 takes
290 talk
291 teaches
292 thank-you
293 thanks
294 though
295 times
296 together
297 told
298 town
299 treatment
300 truest
301 trying
302 turn
303 uncomfortable
304 unfair
305 unreasonably
306 untrue
307 upper
308 value
309 varieties
310 visited
311 wanted
312 waste
313 whore
314 without
315 working
316 youngLong Collocations of Students’ Summaries
summary %>% textstat_collocations(size=5) %>%
arrange(-count) %>%
summarise(collocation, count) collocation count
1 how we see each other 3
2 for the colored people has 2
3 has a lot of meanings 2
4 bias for the colored people 2
5 many black discrimination systems have 2
6 there are many cases where 2
7 the colored people has continued 2
8 the bias for the colored 2
9 she started a project called 2
10 but the world was different 2
11 black discrimination systems have abolished 2
12 because of their skin color 2
13 because of her skin color 2
14 speaker grew up in a 2
15 so she didn't care about 2
16 does not go away naturally 2
17 discrimination does not go away 2
18 the color of the skin 2
19 was exhibited in many places 2
20 shared all over the world 2
21 the speaker grew up in 2Short Collocations of Students’ Summaries
summary %>% textstat_collocations(size=3) %>%
arrange(-count) %>%
summarise(collocation, count) collocation count
1 as a photographer 8
2 it is a 8
3 in the world 8
4 the color of 7
5 the first impression 7
6 a lot of 6
7 started a project 5
8 skin color is 5
9 their skin color 5
10 in a family 4
11 up in a 4
12 color of skin 4
13 of her skin 4
14 all over the 4
15 her skin color 4
16 a project called 4
17 she started a 4
18 the skin color 4
19 over the world 4
20 see each other 4
21 but also in 3
22 there are many 3
23 she was a 3
24 because of her 3
25 color of the 3
26 we still need 3
27 skin color has 3
28 to eliminate discrimination 3
29 people who have 3
30 it has been 3
31 different skin tones 3
32 still need to 3
33 we see each 3
34 she didn't care 3
35 of skin color 3
36 in many places 3
37 lot of meanings 3
38 discrimination does not 3
39 skin color and 3
40 the speaker grew 3
41 original skin color 3
42 around the world 3
43 how we see 3
44 speaker grew up 3
45 own skin color 3
46 the people in 2
47 discrimination in the 2
48 and so on 2
49 has also been 2
50 a work that 2
51 world was different 2
52 she decided to 2
53 we have to 2
54 the colored people 2
55 a family with 2
56 to find their 2
57 many black discrimination 2
58 not only the 2
59 color is not 2
60 color of human 2
61 people has continued 2
62 and it was 2
63 because of their 2
64 because she has 2
65 she began to 2
66 the bias for 2
67 colored people has 2
68 for the colored 2
69 bias for the 2
70 of the skin 2
71 and it is 2
72 skin and hair 2
73 a skin color 2
74 there is a 2
75 she started the 2
76 skin color in 2
77 also used in 2
78 of human skin 2
79 the race problem 2
80 that she was 2
81 skin color because 2
82 discrimination based on 2
83 discrimination systems have 2
84 she took the 2
85 the world was 2
86 are not only 2
87 have to keep 2
88 categorized as white 2
89 believes that you 2
90 is a work 2
91 has passed since 2
92 systems have abolished 2
93 started the project 2
94 years has passed 2
95 a variety of 2
96 in public places 2
97 was exhibited in 2
98 are many cases 2
99 3,000 people in 2
100 their own skin 2
101 many cases where 2
102 has a lot 2
103 these works were 2
104 but the world 2
105 determines the first 2
106 fit into any 2
107 black discrimination systems 2
108 she noticed that 2
109 she realized that 2
110 she grew up 2
111 so she didn't 2
112 as teaching materials 2
113 not go away 2
114 own unique color 2
115 use these pictures 2
116 exhibited in many 2
117 a maid or 2
118 skin color still 2
119 skin color affects 2
120 to rethink how 2
121 taking pictures of 2
122 people who don't 2
123 more than 3,000 2
124 first impression and 2
125 seem to be 2
126 in 13 countries 2
127 than 3,000 people 2
128 of their skin 2
129 color of her 2
130 needed to eliminate 2
131 find their own 2
132 does not go 2
133 go away naturally 2
134 since martin luther 2
135 when she was 2
136 is a photographer 2
137 didn't care about 2
138 by skin color 2
139 people's skin color 2
140 shared all over 2
141 grew up in 2
142 128 years ago 2
143 rethink how we 2
144 it is not 2Common Words Among Students’ Opinions
summary %>% tokens(remove_punct=T,
remove_symbols = T,
remove_numbers = T) %>% dfm %>%
dfm_remove(stopwords("en")) %>%
textstat_frequency() %>%
summarise(word = feature, frequency) %>%
filter(frequency>6) %>%
arrange(-frequency, word) word frequency
1 skin 94
2 color 81
3 people 44
4 humanae 27
5 discrimination 23
6 many 22
7 world 22
8 project 18
9 colors 14
10 also 12
11 black 12
12 first 12
13 impression 12
14 speaker 12
15 still 11
16 family 10
17 however 10
18 photographer 10
19 started 10
20 white 10
21 angelica 9
22 different 9
23 work 9
24 called 8
25 important 8
26 race 8
27 various 8
28 abolished 7
29 can 7
30 lot 7
31 pictures 7
32 public 7Rare Words Among Students’ Opinions
summary %>% tokens(remove_punct=T,
remove_symbols = T,
remove_numbers = T) %>% dfm %>%
dfm_remove(stopwords("en")) %>%
textstat_frequency() %>%
filter(frequency==1) %>%
summarise(word = feature) %>%
arrange(word) word
1 academia
2 act
3 actions
4 added
5 addition
6 adds
7 advantage
8 affairs
9 affect
10 affected
11 ages
12 allow
13 allowed
14 allows
15 although
16 always
17 ambassador
18 angela's
19 angelica's
20 appeared
21 applying
22 argue
23 aruond
24 automatically
25 babysitter
26 backgrounds
27 bad
28 barrier
29 beauty
30 became
31 beings
32 beliefs
33 belong
34 big
35 blacks
36 brazil
37 brazilian
38 brown
39 call
40 capture
41 casts
42 caused
43 chance
44 change
45 changed
46 children
47 cities
48 classification
49 classify
50 colour
51 communication
52 communities
53 community
54 completely
55 complicated
56 computer
57 confident
58 conflict
59 conflicts
60 consciousness
61 continues
62 convey
63 copies
64 corner
65 corresponding
66 country
67 cousin
68 cover
69 covered
70 creative
71 dark
72 darker
73 day
74 describes
75 determine
76 disabilities
77 disapprear
78 discimination
79 discover
80 discremination
81 distinction
82 distinctions
83 drawing
84 due
85 elevator
86 eliminated
87 eliminating
88 encouraged
89 eradicate
90 especially
91 establishing
92 etc
93 every
94 everybody
95 everyone's
96 evolves
97 example
98 exhibition
99 exhibitions
100 exist
101 expanded
102 experiencing
103 experiments
104 explanations
105 express
106 expressed
107 expressiveness
108 extend
109 families
110 fear
111 fears
112 field
113 filmed
114 finally
115 finding
116 finds
117 fitting
118 focusing
119 foreigh
120 found
121 furthermore
122 gathered
123 gave
124 gives
125 globe
126 got
127 gradually
128 great
129 groups
130 growed
131 grown
132 hand
133 hard
134 heading
135 help
136 helping
137 highlight
138 history
139 hoped
140 horrible
141 humanage
142 humanse
143 illustrators
144 impact
145 impressions
146 incident
147 including
148 individual
149 individual's
150 inferiority
151 inquired
152 insists
153 interested
154 interesting
155 internet
156 introduced
157 judge
158 judged
159 judging
160 kid
161 kinds
162 king
163 king's
164 label
165 large
166 later
167 latest
168 launched
169 lesson
170 life
171 live
172 living
173 loneliness
174 looking
175 lovely
176 lower
177 makes
178 making
179 manage
180 marriage
181 married
182 masses
183 material
184 matter
185 means
186 meant
187 media
188 members
189 mentioned
190 mirrored
191 mistake
192 mistaked
193 misunderstood
194 mixed
195 mold
196 movement
197 must
198 natural
199 near
200 needs
201 neglecting
202 never
203 nevertheless
204 new
205 nose
206 notice
207 number
208 ongoing
209 origin
210 outside
211 painted
212 painting
213 palette
214 pantone
215 pastes
216 pattern
217 person's
218 persuades
219 photograph
220 photographs
221 photography
222 physical
223 poor
224 posted
225 present
226 proud
227 provides
228 published
229 pursuing
230 pursuit
231 pursuited
232 questions
233 racism
234 raised
235 reason
236 received
237 recognized
238 recognizes
239 reconsider
240 regarded
241 regardless
242 religion
243 remove
244 removing
245 researchers
246 respects
247 rich
248 roads
249 science
250 seek
251 self-portraits
252 separate
253 servant
254 shadow
255 show
256 showed
257 shown
258 shows
259 simple
260 simply
261 slavely
262 social
263 solve
264 someone
265 somewhere
266 soon
267 sort
268 space
269 spaces
270 spaniard
271 speaker's
272 stare
273 start
274 stereotype
275 stereotypes
276 stereotypical
277 stopped
278 street
279 strive
280 strong
281 struggled
282 suffer
283 suffered
284 suffering
285 surrounded
286 switzerland
287 take
288 taken
289 takes
290 talk
291 teaches
292 thank-you
293 thanks
294 though
295 times
296 together
297 told
298 town
299 treatment
300 truest
301 trying
302 turn
303 uncomfortable
304 unfair
305 unreasonably
306 untrue
307 upper
308 value
309 varieties
310 visited
311 wanted
312 waste
313 whore
314 without
315 working
316 youngLong Collocations of Students’ Opinions
opinion %>% textstat_collocations(size=4) %>%
arrange(-count) %>%
summarise(collocation, count) collocation count
1 skin color is not 3
2 difference in skin color 2
3 i think it's important 2
4 their own unique color 2
5 think it's important to 2
6 my skin color was 2
7 skin is better than 2
8 i think it is 2
9 we don't have to 2
10 we need to change 2
11 have different skin colors 2
12 also have different skin 2
13 i think we should 2Short Collocations of Students’ Opinions
opinion %>% textstat_collocations(size=2) %>%
arrange(-count) %>%
summarise(collocation, count) collocation count
1 skin color 36
2 i think 21
3 it is 13
4 is not 10
5 think that 10
6 the same 10
7 my skin 8
8 to be 7
9 skin colors 7
10 in the 7
11 of the 7
12 when i 6
13 we have 6
14 the world 6
15 there are 5
16 many people 5
17 think we 5
18 there is 5
19 different skin 5
20 our skin 5
21 i thought 5
22 color of 5
23 i was 5
24 the color 5
25 their own 4
26 same race 4
27 such as 4
28 this project 4
29 we should 4
30 difference in 4
31 own unique 4
32 important to 4
33 we are 4
34 white skin 4
35 dark skin 4
36 i feel 4
37 we need 4
38 this is 4
39 need to 4
40 have to 4
41 i am 4
42 of skin 4
43 skin is 4
44 is the 4
45 as white 3
46 if we 3
47 people who 3
48 japanese people 3
49 so i 3
50 in japan 3
51 his subtitle 3
52 black people 3
53 have different 3
54 but we 3
55 that there 3
56 physical characteristics 3
57 but i 3
58 to live 3
59 unique color 3
60 was a 3
61 subtitle was 3
62 people are 3
63 i had 3
64 kind of 3
65 color and 3
66 that we 3
67 skin tones 3
68 people think 3
69 i agree 3
70 and i 3
71 not to 3
72 is a 3
73 color is 3
74 to think 3
75 in skin 3
76 to the 3
77 the skin 3
78 who has 2
79 better than 2
80 each other 2
81 each person's 2
82 for each 2
83 about our 2
84 agree with 2
85 various colors 2
86 made by 2
87 racial discrimination 2
88 social media 2
89 including me 2
90 can not 2
91 they are 2
92 was very 2
93 rather than 2
94 are all 2
95 last year 2
96 had a 2
97 by race 2
98 it's important 2
99 very impressed 2
100 some people 2
101 also have 2
102 don't have 2
103 have various 2
104 so we 2
105 we can 2
106 we don't 2
107 should not 2
108 and some 2
109 don't think 2
110 there was 2
111 race and 2
112 feel that 2
113 us that 2
114 a black 2
115 said to 2
116 people with 2
117 everyone is 2
118 is no 2
119 is better 2
120 is said 2
121 to change 2
122 to make 2
123 to show 2
124 have never 2
125 a different 2
126 a long 2
127 people tend 2
128 meet people 2
129 color makes 2
130 in order 2
131 is also 2
132 think it's 2
133 that white 2
134 colors to 2
135 believe that 2
136 that social 2
137 it was 2
138 is important 2
139 is very 2
140 the idea 2
141 i used 2
142 the person 2
143 and yellow 2
144 think it 2
145 that our 2
146 own skin 2
147 various skin 2
148 of different 2
149 order to 2
150 tend to 2
151 want to 2
152 color as 2
153 hair color 2
154 i don't 2
155 of race 2
156 think this 2
157 about skin 2
158 color was 2
159 the difference 2
160 race is 2
161 the case 2
162 the distinction 2
163 the first 2
164 the paints 2
165 i realize 2
166 have a 2
167 black skin 2
168 same skin 2
169 people have 2
170 is different 2
171 for the 2
172 by skin 2
173 the discrimination 2
174 the yellow 2
175 people of 2
176 we think 2
177 that people 2
178 as the 2
179 have the 2
180 not the 2
181 i have 2
182 is that 2
183 that is 2What are the merits and demerits of asking questions about race?
start <- str_locate(x, "questions")[,2]
merits <- str_sub(x, start + 2,) %>% str_squish %>% as.factor()
merits [1] <NA>
[2]
[3] I think the advantage is knowing how many people are prejudiced about race, and the disadvantage is that this question may remind you of the notion of judging people by skin color or nationality.
[4] I think merit is a strong statement of one's identity. Demerits are causing suffering to people with complex backgrounds. It is a deep sorrow for those who are lost as to what race they are.
[5] It can tell people where they belong but it can also be distinguished people.
[6] I think that no one deny there is discrimination under consciousness even a child. Everyone can visualize discimination in daily life under consciousness by taking statistics. This is the advantage whereas the disadvantage is that it is rude to ask such questions. Race is one of identity; it is private. I think that asking someone I first met about identity is rude.
[7] Merit is we can see the approximate rate of three skin color categories but now, I think it is not a suitable question because every person has their own unique skin color.
[8] The advantage is that you can respect people's culture. The disadvantage is that it emphasizes the differences between people.
[9] The merit is to know that there are people with diverse cultural backgrounds. The demerit is that people with complex cultural backgrounds are difficult to explain.
[10] about the color of skin. So, she started the project “Humanea” taking advantage of photography. She took a variety of people and expressed their color of skin using a computer. She showed how different colors exist and the diversity of people by this work. Humanea affected society and individuals Because this work was exhibited in many places. Furthermore, Humanea was used as teaching materials at the schools. Angelica hoped discrimination will disapprear aruond the world. Opinion Before I watched this video, I thought my skin color was yellow. Because I am Asian. Asian people were called yellow or yellow monkeys a long time ago. However, I rethought it. I thought judging the color of my skin from these stereotypes is discremination by myself. I used an App and searched for my skin color. Then, there were many names of colors. In addition, the color names concluded with yellow were few. I knew my skin color for the first time. We should understand the colors of skin are different from each other. If we are categorized as the same race, the color of skin is different. Thus, the idea of race is so unclear. We have not to judge people from it. What is your skin color? (use a color name app to find out) Middle Yellow Red What is the skin color of a famous person you admire? (find a photo of her and use a color name app to find out) Born Questions about race are often included in research questionnaires, especially in multicultural societies. What do you think are the merits and demerits of asking such questions? Merits are that we can have fellow feelings with people of the same races and the identity will be strong as particular race. Demerits are that we are categorized. In addition, there are many people who have many roots. They may wonder which race I am.
[11] Marits: The research can be a good chance to let everyone know about unreasonable discrimination. Demerits: At the time of using the phrase “race”, it means that the research categorizes our own. It is capable of creating irresponsible sympathy.
[12] ] In my opinion, the merit is finding your roots by using their skin color. However, I think that you need to ask about the skin color to understand the other person’s roots. There is another way to know. The demerit is making discrimination and hurting some people. Some People are proud of their skin’s colors but some people are not because of their background.
[13] Merits: We can notice distintion between races. Demerits: It connects stereotypes of race.
[14] > Questions about race are sometimes convenient because race can classify many survey subjects, such as when conducting many surveys and examining differences in trends between individuals. If we classify the complicated world by race, we can get a feeling that we can grasp the reality more easily. However, even within a group classified into the same race, each individual has different values and personalities. I think if we classify the questions by race, we will not be able to reflect the true reality.
[15] The merits is it helps solve the race problems to analyze shch questionnaires. The demerits is that such questionnaires sometimes contain discriminative words and may hurt minorities.
[16] The merit is we can find the position or community where we are. The disadvantage is it may divide people by skin color.
[17] The merit is that society can deal with several kinds of race by the result but the demerit is that the questionnaire may causes discrimination.
[18]
[19] I think the merit is that I can deepen understanding of others by knowing various values and backgrounds, and the demerite is that I may hurt or burden the person by stepping into the identity of the other person.
[20] Merit: We can think about social issues based on differences of race. Demerit: It may cause racism.
[21] The merit is that we may be able to solve it by thinking seriously about racial problems. The demerit is that it can be offensive when talking about racial issues. Notes Slavely was stopped before 128 years, but skin colors decide our first impression. Her family members have various skin tones. She wondered why there is only a unique flesh color. Her skin color and hair can not belong to some places. She got used to it, but she was conflicted in her heart. She started a project called “Humanae.” This project pursues the original skin color. Her work was displayed in various places. Humanae is useful to discover our unique color.
[22] I think marite is a possibility to correct differences, demerit is a possibility to grow up the distinction.
[23] The advantage is that you can understand that there are various cultures and values, and the disadvantage is that you may have a stereotype for that person.
[24] I think the merit is that we can get data for each race, and the disadvantage is that it may hurt people who have a complex about that race.
22 Levels: ...Density Plot for Summaries
df <- data.frame(summary)
df$words <- ntoken(summary)
df$types <- ntype(summary)
df %>% ggplot(aes(x=words)) +
geom_density() +
labs(y = "") +
theme(axis.text.y = element_blank(),
axis.ticks.y = element_blank())
Density Plot for Opinions
df <- data.frame(opinion)
df$words <- ntoken(opinion)
df$types <- ntype(opinion)
df %>% ggplot(aes(x=words)) +
geom_density() +
labs(y = "") +
theme(axis.text.y = element_blank(),
axis.ticks.y = element_blank())
Dass, A. (2016, February). The beauty of human skin in every color [Video file]. TED2016. Retrieved from https://www.ted.com/talks/angelica_dass_the_beauty_of_human_skin_in_every_color