Word Analysis of 2012 U.S. Presidential Debates

Barack Obama (2008 vs 2012)

Introduction

In this analysis the content of Obama's 2008 first debate (vs McCain) is compared to that of the 2012 first debate (vs Romney). The purpose of this comparison is to highlight the debate dynamics of Obama's as the first-time candidate and as the encumbent.

The method of analysis is the same as for other debates, except in this case the transcript is constructed by treating Obama in 2008 as one speaker and Obama in 2012 as the another.

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

Barack Obama (2008)

7,517 download text •	1,370
50.8%	18.2%

Barack Obama (2012)

7,280 download text •	1,255
49.2%	17.2%

total

14,797	2,010
100.0%	13.6%

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

Barack Obama (2008)

1,284 download text •	755
17.1%	58.8%

Barack Obama (2012)

1,173 download text •	640
16.1%	54.6%

both candidates

12,340 download text •	615
83.4%	5.0%

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

Table 1

commentary

Obama fit +3.3% (7,517 vs 7,280) more words back in 2008 than in 2012. He was less repetitive in 2008, delivering Δ_rel=+5.8% (Δ_abs=+1.0%, 18.2% vs 17.2%) more unique words.

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

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

Barack Obama (2008)

7,517 download text •	1,370
100.0%	18.2%

4,282 download text •	135
57.0%	3.2%

3,235 download text •	1,235
43.0%	38.2%

Barack Obama (2012)

7,280 download text •	1,255
100.0%	17.2%

4,095 download text •	147
56.2%	3.6%

3,185 download text •	1,108
43.8%	34.8%

total

14,797 download text •	2,010
100.0%	13.6%

8,377 download text •	155
56.6%	1.9%

6,420 download text •	1,855
43.4%	28.9%

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

Barack Obama (2008)

1,257 download text •	747
38.9%	59.4%

Barack Obama (2012)

1,118 download text •	620
35.1%	55.5%

both candidates

4,045 download text •	488
63.0%	12.1%

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

Table 2

commentary

Stop word content was very similar in 2008 and 2012. The most popular non-stop word used exclusively in 2008 were "troops", "nulcear", "iran", and "al Qaeda", whereas in 2012 it was "insurance", "small", "deficit", "opportunity" and "middle-class" (not counting references to Obama's opponents, e.g. "John", "McCain", "governor" and "Romney").

There were quite a bit more words unique, +20.5% (747 vs 620), to the 2008 debate than 2012.

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

All further word use statistics represent content that has been filtered for stop words.

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

Barack Obama (2008)

5.5 download text •	25	256

31.7 download text •	96	309

2.6 download text •	4	24

Barack Obama (2012)

5.8 download text •	23	260

27.9 download text •	80	267

2.9 download text •	5	23

total

7.4	44	523

54.0	166	569

3.5	8	37

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

Barack Obama (2008)

1.68 download text •	2	17

Barack Obama (2012)

1.80 download text •	2	25

total

3.46 download text •	8	37

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

Table 3

commentary

Word frequency profile indicates Obama increased repetition in 2012 by +11.5% (2.9 vs 2.6).

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

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

Barack Obama (2008)

431

17.5 download text •	24	61

10.0 download text •	15	34

7.6 download text •	11	26

Barack Obama (2012)

391

18.6 download text •	26	50

10.6 download text •	15	29

8.4 download text •	12	23

total

822

20.0	26	56

12.3	16	31

10.0	12	26

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

Table 4

commentary

Obama's sentences were +10.5% (8.4 vs 7.6) longer in 2012. Given that repetition was also higher, the overall delivery was less dense.

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

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)

Barack Obama (2008)

2,990 download text •	1,177
39.8%	39.4%

1,500 download text •	607
50.2%	40.5%

806 download text •	374
27.0%	46.4%

518 download text •	293
17.3%	56.6%

166 download text •	59
5.6%	35.5%

Barack Obama (2012)

2,949 download text •	1,061
40.5%	36.0%

1,447 download text •	543
49.1%	37.5%

837 download text •	356
28.4%	42.5%

511 download text •	252
17.3%	49.3%

154 download text •	62
5.2%	40.3%

total

5,939 download text •	1,778
40.1%	29.9%

2,947 download text •	933
49.6%	31.7%

1,643 download text •	590
27.7%	35.9%

1,029 download text •	454
17.3%	44.1%

320 download text •	90
5.4%	28.1%

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

Table 5

commentary

Part of speech analysis shows little change from 2008 to 2012. The ratios of each of noun, verb, adjective and adverb is similar. Verb use is slightly up in 2012 by Δ_rel=+5.2% (Δ_abs=+1.4%, 28.4% vs 27%).

In 2012 Obama used a greater fraction of unique adverbs, Δ_rel=+13.5% (Δ_abs=+4.8%, 40.3% vs 35.5%). Unique fraction of all other parts of speech was lower in 2012.

In fact, adverbs were the only part of speech for which Obama's delivery was richer in 2012, by +5.1% (62 vs 59). In 2012 he delivered -10.5% (543 vs 607) fewer nouns, -4.8% (356 vs 374) fewer verbs and -14.0% (252 vs 293) fewer adjectives.

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

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)

Barack Obama (2008)

2.54	4	25

2.47	4	19

2.15	3	23

1.77	2	14

2.81	5	36

Barack Obama (2012)

2.78	5	21

2.67	5	21

2.35	3	24

2.03	3	11

2.48	4	25

total

3.34	7	36

3.16	7	30

2.79	6	47

2.27	3	18

3.56	8	61

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

Table 5

commentary

Repetition was higher in 2012 for all parts of speech, except adverbs: nouns by -100.0% (0 vs 47), verbs by +9.3% (2.35 vs 2.15), and adjectives by +14.7% (2.03 vs 1.77). Adverb repetition fell by -11.7% (2.48 vs 2.81),

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

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 — Barack Obama (2008)

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

part of speech pairings - Barack Obama (2008)

noun

verb

adjective

adverb

noun

4,673 download text •	3,993
	85.4%

verb

5,069 download text •	4,547
	89.7%

1,211 download text •	1,105
	91.2%

adjective

2,691 download text •	2,463
	91.5%

1,449 download text •	1,319
	91.0%

350 download text •	336
	96.0%

adverb

990 download text •	874
	88.3%

543 download text •	490
	90.2%

284 download text •	255
	89.8%

65 download text •	50
	76.9%

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

Table 6b

part of speech pairing — Barack Obama (2012)

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

part of speech pairings - Barack Obama (2012)

noun

verb

adjective

adverb

noun

4,105 download text •	3,451
	84.1%

verb

5,187 download text •	4,596
	88.6%

1,423 download text •	1,318
	92.6%

adjective

2,740 download text •	2,413
	88.1%

1,639 download text •	1,475
	90.0%

423 download text •	381
	90.1%

adverb

853 download text •	788
	92.4%

512 download text •	479
	93.6%

290 download text •	266
	91.7%

44 download text •	42
	95.5%

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

3,993 download text •	3,451 download text •
	86.4%

verb

4,547 download text •	4,596 download text •
	101.1%

1,105 download text •	1,318 download text •
	119.3%

adjective

2,463 download text •	2,413 download text •
	98.0%

1,319 download text •	1,475 download text •
	111.8%

336 download text •	381 download text •
	113.4%

adverb

874 download text •	788 download text •
	90.2%

490 download text •	479 download text •
	97.8%

255 download text •	266 download text •
	104.3%

50 download text •	42 download text •
	84.0%

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

Table 6

commentary

The 2012 debate saw longer sentences, but fewer unique words. Nevertheless, the number of noun/noun combinations in 2008 was higher by +15.7% (3,993 vs 3,451), indicating that the 2008 debate was richer in concepts.

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 Barack Obama (2008)

c :: unique pairs for Barack Obama (2012)

d :: (c) relative to (a) (i.e. Barack Obama (2012) relative to Barack Obama (2008))

bars :: (a) and (c)

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)

Barack Obama (2008)

1,195 download text •	717
100.0%	60.0%
20.1%	40.3%

680 download text •	368
56.9%	54.1%
23.1%	39.4%

260 download text •	209
21.8%	80.4%
15.8%	35.4%

228 download text •	168
19.1%	73.7%
22.2%	37.0%

27 download text •	22
2.3%	81.5%
8.4%	24.4%

Barack Obama (2012)

1,076 download text •	601
100.0%	55.9%
18.1%	33.8%

580 download text •	292
53.9%	50.3%
19.7%	31.3%

257 download text •	194
23.9%	75.5%
15.6%	32.9%

207 download text •	134
19.2%	64.7%
20.1%	29.5%

32 download text •	23
3.0%	71.9%
10.0%	25.6%

both candidates

3,668 download text •	460
100.0%	12.5%
61.8%	25.9%

1,611 download text •	217
43.9%	13.5%
54.7%	23.3%

1,054 download text •	140
28.7%	13.3%
64.2%	23.7%

500 download text •	91
13.6%	18.2%
48.6%	20.0%

236 download text •	31
6.4%	13.1%
73.8%	34.4%

total

5,939 download text •	1,778
100.0%	29.9%
100.0%	100.0%

2,947 download text •	933
49.6%	31.7%
100.0%	100.0%

1,643 download text •	590
27.7%	35.9%
100.0%	100.0%

1,029 download text •	454
17.3%	44.1%
100.0%	100.0%

320 download text •	90
5.4%	28.1%
100.0%	100.0%

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

Table 7

commentary

The 2008 debate had +19.3% (717 vs 601) more exclusive words than 2012. The number of nouns and adjectives unique to the debate was +26.0% (368 vs 292) and +25.4% (168 vs 134) higher in 2008 than 2012, respectively. This is a good indication of just how much more vigorous and varied the 2008 debate was than 2012.

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)

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

Barack Obama (2008)

527 download text •	261
100.0%	49.5%
0.35	0.43

447 download text •	257
84.8%	57.5%
0.30	0.42

Barack Obama (2012)

529 download text •	240
100.0%	45.4%
0.37	0.44

433 download text •	234
81.9%	54.0%
0.30	0.43

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

Barack Obama (2008)

2.29	2	3

2.33	2	3

Barack Obama (2012)

2.31	2	3

2.36	2	4

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

Table 8

commentary

As hinted by the analysis above, the drop in the number of concepts is reflected in the reduced number of noun phrases. Although in 2012 noun phrases were slightly longer, +1.3% (2.36 vs 2.33) for top-level phrases, there were -8.9% (234 vs 257) fewer of them.

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

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

Barack Obama (2008)

472 download text •	256
43.8%	54.2%

411 download text •	253
87.1%	61.6%

Barack Obama (2012)

476 download text •	234
44.2%	49.2%

406 download text •	230
85.3%	56.7%

both candidates

172 download text •	31
16.0%	18.0%

74 download text •	18
43.0%	24.3%

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

Barack Obama (2008)

2.31	2	3

2.35	2	4

Barack Obama (2012)

2.34	2	3

2.38	2	4

both candidates

2.08	2	3

2.18	2	3

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

Table 9

commentary

The 2008 debate had a greater variety of exclusive noun phrases, by +9.6% (252 vs 230).

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

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

Barack Obama (2008)

330
-29.5%

0.430	0.382	0.405	0.464	0.566	0.355	0.495	0.985
-1.6%	+9.7%	+7.8%	+9.1%	+14.7%	-11.7%	+9.2%	+1.0%

Barack Obama (2012)

468
+41.8%

0.438	0.348	0.375	0.425	0.493	0.403	0.454	0.975
+1.7%	-8.9%	-7.3%	-8.3%	-12.8%	+13.3%	-8.4%	-1.0%

Table 10

commentary

The 2008 debate delivery was denser and more vigorous. Repetition plagued Obama in 2012, resulting in a +41.8% (468 vs 330) larger Windbag Index. The only terms in 2012 that contributed to a lower index were the fraction of non-stop words and the fraction of unique adverbs. All other quantities indicated greater repetition across all others parts of the delivery.

Table 10

legend

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

t1 :: fraction of words which are non-stop

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

t3 :: fraction of nouns which are unique

t4 :: fraction of verbs which are unique

t5 :: fraction of adjectives which are unique

t6 :: fraction of adverbs which are unique

t7 :: fraction of noun phrases which are unique

t8 :: fraction of noun phrases which 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).

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 Barack Obama (2008) - all words

Debate Word Cloud for Barack Obama (2012) - 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 Barack Obama (2008)

Words exclusive to Barack Obama (2012)

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.