Word Analysis of 2016 U.S. Presidential Debates

Hillary Clinton vs Donald Trump (2nd debate)

19 October 2016

Word Statistics

Debate Word Count

Summary Word Count

The summary word count reports the total number of words and the number of unique, non-stop words used by each candidate. Word number is expressed as both absolute and relative values.

Table 1a

all words

Number of all words and unique words used by each speaker.

set

word count

Hillary Clinton

6,637 download text •	1,350
50.8%	20.3%

Donald Trump

6,436 download text •	1,008
49.2%	15.7%

total

13,073	1,815
100.0%	13.9%

Fields with • (e.g. 155•) link to data files. Hover over the field to show these links.

Table 1b

exclusive and shared words

Words exclusive to speaker (e.g. speaker A but not speaker B) and shared by speakers (speaker A and B).

set

word count

Hillary Clinton

1,309 download text •	807
19.7%	61.7%

Donald Trump

880 download text •	465
13.7%	52.8%

both candidates

10,884 download text •	543
83.3%	5.0%

Fields with • (e.g. 155•) link to data files. Hover over the field to show these links.

Table 1

legend

a	c
b	d

a :: word count

b :: word count, as fraction in total in debate

c :: unique words in (a)

d :: unique words in (a), as fraction in (a) bar :: proportion of (a-c):c

Table 1

commentary

Stop Word Contribution

In the table below, the candidates' delivery is partitioned into stop and non-stop words. Stop words (full list) are frequently-used bridging words (e.g. pronouns and conjunctions) whose meaning depends entirely on context. The fraction of words that are stop words is one measure of the complexity of speech.

Table 2a

non-stop words

Counts of stop and non-stop words.

speaker

all

stop

non-stop

Hillary Clinton

6,637 download text •	1,350
100.0%	20.3%

3,744 download text •	141
56.4%	3.8%

2,893 download text •	1,209
43.6%	41.8%

Donald Trump

6,436 download text •	1,008
100.0%	15.7%

3,776 download text •	140
58.7%	3.7%

2,660 download text •	868
41.3%	32.6%

total

13,073 download text •	1,815
100.0%	13.9%

7,520 download text •	152
57.5%	2.0%

5,553 download text •	1,663
42.5%	29.9%

Fields with • (e.g. 155•) link to data files. Hover over the field to show these links.

Table 2b

exclusive and shared non-stop words

Non-stop words exclusive to speaker (e.g. speaker A but not speaker B) and shared by speakers (speaker A and B).

set

word count

Hillary Clinton

1,272 download text •	795
44.0%	62.5%

Donald Trump

859 download text •	454
32.3%	52.9%

both candidates

3,422 download text •	414
61.6%	12.1%

Fields with • (e.g. 155•) link to data files. Hover over the field to show these links.

Table 2

legend

a	c
b	d

a :: total number of words, for a given category (all, stop, non-stop)

b :: (a) relative to words in the debate if category=all, otherwise relative to words by the candidate

c :: number of unique words with set (a)

d :: (c) relative to (a)

bar :: proportion of (a-c):c

Table 2

commentary

Word frequency

The word frequency table summarizes the frequency with which words were used. I show the average word frequency and the weighted cumulative frequencies at 50 and 90 percentile. The average word frequency indicates how many times, on average, a word is used. For a given fraction of the entire delivery, the weighted cumulative frequency indicates the largest word frequency within this fraction (details about weighted cumulative distribution).

Table 3a

word use frequency

Average and 50%/90% percentile word frequencies.

speaker

word frequency

all

stop

non-stop

Hillary Clinton

4.9 download text •	21	210

26.6 download text •	89	247

2.4 download text •	4	22

Donald Trump

6.4 download text •	25	193

27.0 download text •	83	203

3.1 download text •	5	25

total

7.2	41	413

49.5	125	440

3.3	6	35

Fields with • (e.g. 155•) link to data files. Hover over the field to show these links.

Table 3b

exclusive and shared non-stop word use frequency

Average and 50%/90% cumulative percentile word frequencies. Non-stop words exclusive to speaker (e.g. speaker A but not speaker B) and shared by speakers (speaker A and B).

set

word frequency

Hillary Clinton

1.60 download text •	2	5

Donald Trump

1.89 download text •	2	8

total

3.34 download text •	6	35

Fields with • (e.g. 155•) link to data files. Hover over the field to show these links.

Table 3

legend

a	b	c

a :: average word frequency

b :: largest word frequency in 50% of content

c :: largest word frequency in 90% of content

bar :: proportion of a:b:c

Table 3

commentary

Sentence Size

Table 4

sentence size

Number of sentences spoken by each speaker and sentence word count statistics. Number of words in a sentence is shown by average and 50%/90% cumulative values for all, stop and non-stop words.

speaker

number of sentences

sentence size

all

stop

non-stop

Hillary Clinton

427

15.6 download text •	21	45

8.9 download text •	12	28

6.9 download text •	9	20

Donald Trump

613

10.5 download text •	14	32

6.3 download text •	8	20

4.4 download text •	6	14

total

1,040

14.6	18	38

9.4	11	23

7.4	9	18

Fields with • (e.g. 155•) link to data files. Hover over the field to show these links.

Table 4

legend

a	b	c

a :: average sentence size

b :: largest sentence size for 50% of content

c :: largest sentence size for 90% of content

bar :: proportion of a:b:c

Table 4

commentary

All further word use statistics represent content that has been filtered for stop words, unless explicitly indicated.

Part of Speech Analysis

In this section, word frequency is broken down by their part of speech (POS). The four POS groups examined are nouns, verbs, adjectives and adverbs. Conjunctions and prepositions are not considered. The first category (n+v+adj+adv) is composed of all four POS groups.

Part of Speech Count

Table 5

part of speech count

Count of words categorized by part of speech (POS).

part of speech

n+v+adj+adv

nouns (n)

verbs (v)

adjectives (adj)

adverbs (adv)

Hillary Clinton

2,713 download text •	1,161
40.9%	42.8%

1,280 download text •	580
47.2%	45.3%

839 download text •	409
30.9%	48.7%

463 download text •	267
17.1%	57.7%

131 download text •	58
4.8%	44.3%

Donald Trump

2,441 download text •	822
37.9%	33.7%

1,028 download text •	400
42.1%	38.9%

775 download text •	278
31.7%	35.9%

494 download text •	240
20.2%	48.6%

144 download text •	38
5.9%	26.4%

total

5,154 download text •	1,601
39.4%	31.1%

2,308 download text •	810
44.8%	35.1%

1,614 download text •	568
31.3%	35.2%

957 download text •	434
18.6%	45.4%

275 download text •	74
5.3%	26.9%

Fields with • (e.g. 155•) link to data files. Hover over the field to show these links.

Table 5

legend

a	c
b	d

a :: total number of words for a given POS (all, noun, verb, adjective, adverb, pronoun)

b :: (a) relative to all words by candidate

c :: unique words in (a)

d :: (c) relative to (a)

bar :: proportion of (a-c):c

Table 5

commentary

Part of Speech Frequency

Table 5

part of speech frequency

Frequency of words categorized by part of speech (POS).

part of speech frequency

n+v+adj+adv

nouns (n)

verbs (v)

adjectives (adj)

adverbs (adv)

Hillary Clinton

2.34	3	22

2.21	3	16

2.05	3	27

1.73	2	7

2.26	4	19

Donald Trump

2.97	5	23

2.57	4	13

2.79	5	23

2.06	3	16

3.79	8	27

total

3.22	6	34

2.85	5	26

2.84	5	45

2.21	3	13

3.72	12	46

Fields with • (e.g. 155•) link to data files. Hover over the field to show these links.

Table 5

legend

a	b	c

a :: average word frequency

b :: largest word frequency in 50% of content

c :: largest word frequency in 90% of content

bar :: proportion of a:b:c

Table 5

commentary

Part of Speech Pairing

Through word pairing, I extract concepts from the text. The number of unique word pairs is a function of sentence length and is one of the measures of complexity.

Table 6a

part of speech pairing — Hillary Clinton

Word pairs (total and unique) categorized by part of speech (POS)

part of speech pairings - Hillary Clinton

noun

verb

adjective

adverb

noun

3,148 download text •	2,803
	89.0%

verb

4,049 download text •	3,624
	89.5%

1,081 download text •	957
	88.5%

adjective

1,891 download text •	1,756
	92.9%

1,169 download text •	1,102
	94.3%

317 download text •	291
	91.8%

adverb

543 download text •	513
	94.5%

377 download text •	348
	92.3%

172 download text •	168
	97.7%

30 download text •	30
	100.0%

Fields with • (e.g. 155•) link to data files. Hover over the field to show these links.

Table 6b

part of speech pairing — Donald Trump

Word pairs (total and unique) categorized by part of speech (POS)

part of speech pairings - Donald Trump

noun

verb

adjective

adverb

noun

1,469 download text •	1,196
	81.4%

verb

2,172 download text •	1,791
	82.5%

690 download text •	559
	81.0%

adjective

1,098 download text •	957
	87.2%

789 download text •	687
	87.1%

226 download text •	198
	87.6%

adverb

419 download text •	352
	84.0%

308 download text •	264
	85.7%

165 download text •	143
	86.7%

34 download text •	27
	79.4%

Fields with • (e.g. 155•) link to data files. Hover over the field to show these links.

Table 6c

unique part of speech pairing — candidate comparison

Unique word pairs categorized by part of speech (POS)

unique part of speech pairings

noun (n)

verb (v)

adjective (adj)

adverb (adv)

noun

2,803 download text •	1,196 download text •
	42.7%

verb

3,624 download text •	1,791 download text •
	49.4%

957 download text •	559 download text •
	58.4%

adjective

1,756 download text •	957 download text •
	54.5%

1,102 download text •	687 download text •
	62.3%

291 download text •	198 download text •
	68.0%

adverb

513 download text •	352 download text •
	68.6%

348 download text •	264 download text •
	75.9%

168 download text •	143 download text •
	85.1%

30 download text •	27 download text •
	90.0%

Fields with • (e.g. 155•) link to data files. Hover over the field to show these links.

Table 6 a,b

legend

a	c
	d

a :: total number of pairs, for a given category (e.g. verb/noun)

c :: number of unique pairs within set (a)

d :: (c) relative to (a)

bar :: proportion of (a-c):c

Table 6c

legend

a	c
	d

a :: unique pairs for Hillary Clinton

c :: unique pairs for Donald Trump

d :: (c) relative to (a) (i.e. Donald Trump relative to Hillary Clinton)

bars :: (a) and (c)

Table 6

commentary

Exclusive and Shared Usage

This section enumerates words that were exclusive to a candidate (e.g. used by one candidate but not the other). This content provides insight into what the candidates' priorities are and reveals differences in perspective on similar topics.

For a given part of speech, the table breaks down the number of words that were spoken by only one of the candidates or both candidates (intersection). The last row includes words spoken by either candidate (union).

Table 7

exclusive word usage

Total and unique words used exclusively by a candidate, or by both.

part of speech

n+v+adj+adv

nouns (n)

verbs (v)

adjectives (adj)

adverbs (adv)

Hillary Clinton

1,235 download text •	779
100.0%	63.1%
24.0%	48.7%

606 download text •	378
49.1%	62.4%
26.3%	46.7%

354 download text •	273
28.7%	77.1%
21.9%	48.1%

241 download text •	174
19.5%	72.2%
25.2%	40.1%

34 download text •	28
2.8%	82.4%
12.4%	37.8%

Donald Trump

823 download text •	440
100.0%	53.5%
16.0%	27.5%

372 download text •	213
45.2%	57.3%
16.1%	26.3%

222 download text •	138
27.0%	62.2%
13.8%	24.3%

202 download text •	126
24.5%	62.4%
21.1%	29.0%

27 download text •	15
3.3%	55.6%
9.8%	20.3%

both candidates

3,096 download text •	382
100.0%	12.3%
60.1%	23.9%

1,243 download text •	170
40.1%	13.7%
53.9%	21.0%

989 download text •	119
31.9%	12.0%
61.3%	21.0%

405 download text •	73
13.1%	18.0%
42.3%	16.8%

200 download text •	22
6.5%	11.0%
72.7%	29.7%

total

5,154 download text •	1,601
100.0%	31.1%
100.0%	100.0%

2,308 download text •	810
44.8%	35.1%
100.0%	100.0%

1,614 download text •	568
31.3%	35.2%
100.0%	100.0%

957 download text •	434
18.6%	45.4%
100.0%	100.0%

275 download text •	74
5.3%	26.9%
100.0%	100.0%

Fields with • (e.g. 155•) link to data files. Hover over the field to show these links.

Table 7c

legend

a	d
b	e
c	f

a :: total number of words in set (e.g. obama \ romney, obama ∩ romney, obama ∪ romney , for a given part of speech

b :: (a) relative to all exclusive words in n+v+adj+adv

c :: (a) relative to all words in n+v+adj+adv

d :: unique words in (a)

e :: (d) relative to (a)

f :: (d) relative to all unique words in n+v+adj+adv

bar1 :: normalized ratio of (a-d):d

bar2 :: absolute ratio of (a-d):d for all POS groups (first column) or POS group (other columns)

Table 7

commentary

Noun Phrase Usage

Noun phrases were extracted from the text and analyzed for frequency, word count, unique word count and richness. Single-word phrases were not counted.

Top-level noun phrases are those without a parent noun phrase (a parent phrase is one that a similar, longer phrase). Derived noun phrases are those with a parent (more details about noun phrase analysis).

The top-level noun phrases can be interpreted as independent concepts. Derived noun phrases can be interpreted as variants on concepts embodied by the top-level phrases.

Noun Phrase Count and length

This table reports the absolute number of noun phrases, which is related to the number of nouns, and their length.

Table 8a

noun phrase count

Counts of noun phrases in words and per noun.

speaker

noun phrase count

all

top-level

Hillary Clinton

425 download text •	238
100.0%	56.0%
0.33	0.41

384 download text •	235
90.4%	61.2%
0.30	0.41

Donald Trump

374 download text •	193
100.0%	51.6%
0.36	0.48

307 download text •	186
82.1%	60.6%
0.30	0.47

Fields with • (e.g. 155•) link to data files. Hover over the field to show these links.

Table 8b

noun phrase length

Average and 50%/90% cumulative length of noun phrases, in words.

speaker

noun phrase length

all

top-level

Hillary Clinton

2.30	2	4

2.32	2	4

Donald Trump

2.21	2	3

2.25	2	3

Fields with • (e.g. 155•) link to data files. Hover over the field to show these links.

Table 8a

legend

a	d
b	e
c	f

a :: number of noun phrases

b :: (a) relative to number of all noun phrases

c :: number of noun phrases per noun

d :: number of unique phrases

e :: (c) relative to (a)

f :: number of unique noun phrases per unique noun

bar :: normalized ratio of (a-c):c

Table 8b

legend

a	b	c

a :: average noun phrase size, in words

b :: largest noun phrase size in 50% of content

c :: largest noun phrase size in 90% of content

bar :: proportion of a:b:c

Table 8

commentary

Exclusive and Shared Noun Phrase Count and length

Table 9a

exclusive and shared noun phrase count

Counts of exclusive and shared noun phrases in words and per noun.

speaker

noun phrase count

all

top-level

Hillary Clinton

383 download text •	232
47.9%	60.6%

369 download text •	230
96.3%	62.3%

Donald Trump

332 download text •	185
41.6%	55.7%

289 download text •	181
87.0%	62.6%

both candidates

84 download text •	18
10.5%	21.4%

33 download text •	10
39.3%	30.3%

Fields with • (e.g. 155•) link to data files. Hover over the field to show these links.

Table 9b

exclusive and shared noun phrase length

Average and 50%/90% cumulative length of noun phrases, in words.

speaker

noun phrase length

all

top-level

Hillary Clinton

2.33	2	4

2.33	2	4

Donald Trump

2.23	2	3

2.26	2	3

both candidates

2.05	2	2

2.12	2	3

Fields with • (e.g. 155•) link to data files. Hover over the field to show these links.

Table 9a

legend

a	c
b	d

a :: number of noun phrases

b :: (a) relative to number of all noun phrases

c :: number of unique phrases

d :: (c) relative to (a)

bar :: normalized ratio of (a-c):c

Table 9b

legend

a	b	c

a :: average noun phrase size, in words

b :: largest noun phrase size in 50% of content

c :: largest noun phrase size in 90% of content

bar :: proportion of a:b:c

Table 9

commentary

Windbag Index

The Windbag Index is a compound measure that characterizes the complexity of speech. A low index is indicative of succinct speech with low degree of repetition and large number of independent concepts.

Table 10

windbag index

Windbag Index for each speaker. The higher the value, the more repetitive the speech.

speaker

Windbag Index

index value

index terms

Hillary Clinton

176
-78.9%

0.436	0.418	0.453	0.487	0.577	0.443	0.560	0.987
+5.5%	+28.1%	+16.5%	+35.9%	+18.7%	+67.8%	+8.5%	+2.5%

Donald Trump

833
+373.3%

0.413	0.326	0.389	0.359	0.486	0.264	0.516	0.964
-5.2%	-21.9%	-14.1%	-26.4%	-15.8%	-40.4%	-7.8%	-2.4%

Table 10

legend

The Windbag Index is 1/(t1*t2*...*t9) where t1,t2,...,t8 are

t1 :: fraction of words that are non-stop

t2 :: fraction of non-stop words that are unique

t3 :: fraction of nouns that are unique

t4 :: fraction of verbs that are unique

t5 :: fraction of adjectives that are unique

t6 :: fraction of adverbs that are unique

t7 :: fraction of noun phrases that are unique

t8 :: fraction of noun phrases that are top-level

Large individual terms t1...t9 contribute to a smaller index.

The percentage values below the index and each term are relative differences to the other speaker's corresponding term (i.e. 100*(a-b)/b where a is the value for one speaker and b for the other).

Table 10

commentary

Word Clouds

In the word clouds below, the size of the word is proportional to the number of times it was used by a candidate (method details).

Not all words from a group used to draw the cloud fit in the image — less frequently used words for large word groups may fall outside the image.

All Words for Each Candidate

Each candidate's debate portion was extracted and frequencies were compiled for each part of speech (noun, verb, adjective, adverb), with words colored by their part of speech category.

The distribution of sizes within a tag cloud follows the frequency distribution of words. However, word size cannot be compared between clouds, since the minimum and maximum size of the words is fixed.

Debate Word Cloud for Hillary Clinton - all words

Debate Word Cloud for Donald Trump - all words

commentary

Exclusive Words for Each Candidate

The clouds below show words used exlusively by a candidate. For example, if candidate A used the word "invest" (any number of times), but candidate B did not, then the word will appear in the exclusive word tag cloud for candidate A.

Words exclusive to Hillary Clinton

Words exclusive to Donald Trump

commentary

Part of Speech Word Clouds

In these clouds, words from each major part of speech were colored based on whether they were exclusive to a candidate or shared by the candidates.

The size of the word is relative to the frequency for the candidate — word sizes between candidates should not be used to indicate difference in absolute frequency.