home > results and commentary > Obama vs Romney (1st debate)

Word Analysis of 2012 U.S. Presidential Debates

Barack Obama vs Mitt Romney (1st debate)

3 October 2012



Introduction

This debate has been generally seen as a victory for Romney, who eclipsed Obama's with his energy and charisma. The analysis here does not attempt to capture the tone and energy level of the speaker — to do so in an automated way would be extraordinarily difficult from the transcript alone.

The analysis describes in detail the structure of each candidate's speech, words and phrases that they used (exclusively or shared), and the degree to which they repeated themselves.

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
7,280 1,255
48.3% 17.2%
60251255
Mitt Romney
7,791 1,214
51.7% 15.6%
65771214
total
15,071 1,825
100.0% 12.1%
132461825

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
934 611
12.8% 65.4%
323611
Mitt Romney
932 570
12.0% 61.2%
362570
both candidates
13,205 644
87.6% 4.9%
12561644

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

Table 1
commentary
Obama' delivery slower, but has more unique and exclusive words. Democrats more articulate than in 2008, Republicans less.

Obama spoke for longer (42:50 min = 2,570 seconds) than Romney (38:32 min = 2,312 seconds) (debate timing by CNN). Romney used +7.0% (7,791 vs 7,280) more words than Obama — he spoke faster with a rate of 3.37 words/second, +19.1% (3.37 vs 2.83) faster than Obama's 2.83 words/second. Despite the fact that Obama delivered -6.6% (7,280 vs 7,791) fewer words, he used +3.4% (1,255 vs 1,214) more unique words. Romney either comes across as rushed, repetitive and aggressive or Obama as slow, strained and laborious.

In the first debate of 2008, Obama delivered +6.9% (7,529 vs 7,043) more words than McCain. This year, we find Obama speaking -3.4% (7,270 vs 7,529) fewer words than in 2008, while the Republican candidate speaking +10.6% (7,791 vs 7,043) more. In the 2008 debate, the number of unique words was nearly identical for both candidates (1,376 for Obama and 1,380 for McCain). This time we see Obama use +3.4% (1,255 vs 1,214) more unique words than Romney. Obama appears more articulate and measured, having more unique words and slower speech.

Obama's unique word fraction increased from 2008, from 16.5% to 17.2%. The Republican candidate's fraction dropped, from McCain's 17.6% to Romney's 15.6%. The Democrats have become more articulate, the Republicans less.

Of all the words used in the debate, 13,205 were spoken by both candidates. Of Obama's 7,280 words, 934 (12.8%) were exclusive to him (i.e. spoken by Obama, but not Romney), higher than Romney's 12.0%. Within these exlusive words, Obama had a higher fraction of unique ones (65.4% vs 61.2%). Obama tended to repeat exclusive words less than Romney.

Table 1
legend
a c
b d
3010

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
7,280 1,255
100.0% 17.2%
60251255
4,095 147
56.2% 3.6%
3948147
3,185 1,108
43.8% 34.8%
20771108
Mitt Romney
7,791 1,214
100.0% 15.6%
65771214
4,328 144
55.6% 3.3%
4184144
3,463 1,070
44.4% 30.9%
23931070
total
15,071 1,825
100.0% 12.1%
132461825
8,423 158
55.9% 1.9%
8265158
6,648 1,667
44.1% 25.1%
49811667

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
910 597
28.6% 65.6%
313597
Mitt Romney
905 559
26.1% 61.8%
346559
both candidates
4,833 511
72.7% 10.6%
4322511

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

Table 2
commentary
Obama's speech more varied. Less than half of a candidate's unique words are spoken by the other.

Obama's relative stop word count is slightly higher than Romney's. 56.2% of Obama's words are stop, compared to 55.6% of Romney's. When we look at unique non-stop words, Obama's fraction is significantly higher, 34.8% vs 30.9%, indicating that his speech is more varied.

When exclusive non-stop words are examined, we see there were more unique words that were exclusive than shared. Obama had +6.8% (597 vs 559) more unique exclusive words. The two candidates shared 511 unique words.

Stop word frequency counts do not reveal significant difference between the two candidates, although much can be gleaned from which stop words were actually used. For example, pronoun profiles speak volumes.

Table 2
legend
a c
b d
3010

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
5.8 23 260
5.80123.000260.000
27.9 80 267
27.85780.000267.000
2.9 5 23
2.8755.00023.000
Mitt Romney
6.4 26 243
6.41826.000243.000
30.1 94 308
30.05694.000308.000
3.2 6 31
3.2366.00031.000
total
8.3 45 483
8.25845.000483.000
53.3 172 568
53.310172.000568.000
4.0 9 47
3.9889.00047.000

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
1.52 2 5
1.5242.0005.000
Mitt Romney
1.62 2 5
1.6192.0005.000
total
3.99 9 47
3.9889.00047.000

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

Table 3
commentary
Obama's repeats words less and suggests we can "now" "make" things with what we "know". Romney acts as saviour with "one" and "plan" for the "people".

We've already seen that Obama delivered proportionately more unique words (17.2%) than Romney (15.6%). This is reflected in his -9.4% (5.8 vs 6.4) (all words) and -9.4% (2.9 vs 3.2) (non-stop words) lower average word frequency. Obama also repeated stop words less often, -7.3% (27.9 vs 30.1). Finally, if we look at exclusive words, these are repeated -6.2% (1.52 vs 1.62) less by Obama as well.

The top 5 non-stop words (and frequencies) spoken by Obama were know (28), now (37), make (44), romney (44) and governor (48). Romney used plan (35), one (37), tax (39), president (41) and people (73).

Looking only at exclusive words, the top 5 non-stop words for Obama were investments (7), difference (8), loopholes (9), folks (11) and opportunity (11) and for Romney, retirees (6), current (7), half (7), mr (7) and middle-income (8).

For those words used by both candidates, the top 5 were plan (54), now (56), tax (60), make (63) and people (100). Three of these appear in Romney's top 5 list (plan, tax and people) but only one in Obama's (now).

Table 3
legend
a b c
51025

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
391
391
18.6 26 50
18.61926.00050.000
10.6 15 29
10.63615.00029.000
8.4 12 23
8.36012.00023.000
Mitt Romney
579
579
13.5 18 37
13.45618.00037.000
7.8 10 22
7.77010.00022.000
6.0 8 18
6.0448.00018.000
total
970
970
17.5 23 46
17.53723.00046.000
10.9 13 28
10.94213.00028.000
9.0 11 22
8.96911.00022.000

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

Table 4
commentary
Obama's delivery more complex, oratorial.

The number and size of sentences suggests that Obama's delivery is gramatically more complex than Romney. Obama delivered -32.5% (391 vs 579) fewer sentences than Romney but only -6.6% (7,280 vs 7,791) fewer words. He packed more into his sentences.

Obama's sentences were +37.8% (18.6 vs 13.5) longer when all words are considered and +40.0% (8.4 vs 6) longer when only non-stop words are counted. This is quite a large difference, especially given that Obama spoke for longer and his unique word usage is higher than Romney.

Both candidates delivered some whopping sentences. Obama's largest sentence is quite oratorial, with 112 words (536 characters).

Obama, 112 words — And everything that I've tried to do and everything that I'm now proposing for the next four years in terms of improving our education system, or developing American energy, or making sure that we're closing loopholes for companies that are shipping jobs overseas and focusing on small businesses and companies that are creating jobs here in the United States, or - or closing our deficit in a responsible, balanced way that allows us to invest in our future - all those things are designed to make sure that the American people, their genius, their grit, their determination is - is channeled, and - and - and they have an opportunity to succeed.

Romney's longest sentence is stammering gibberish of 71 words and 318 characters.

Romney, 71 words — Look, the right course for - for America's government - we were talking about the role of government - is not to become the economic player picking winners and losers, telling people what kind of health treatment they can receive, taking over the health care system that - that has existed in this country for - for a long, long time and has produced the best health records in the world.

Table 4
legend
a b c
51025

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
2,949 1,061
40.5% 36.0%
9045434813562592529262
1,447 543
49.1% 37.5%
904543
837 356
28.4% 42.5%
481356
511 252
17.3% 49.3%
259252
154 62
5.2% 40.3%
9262
Mitt Romney
3,112 1,025
39.9% 32.9%
10305504833302992739255
1,580 550
50.8% 34.8%
1030550
813 330
26.1% 40.6%
483330
572 273
18.4% 47.7%
299273
147 55
4.7% 37.4%
9255
total
6,061 1,600
40.2% 26.4%
2182845109555567141221586
3,027 845
49.9% 27.9%
2182845
1,650 555
27.2% 33.6%
1095555
1,083 412
17.9% 38.0%
671412
301 86
5.0% 28.6%
21586

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

Table 5
commentary
Obama's use of verbs and adverbs higher. Romney prefers nouns and adjectives.

The relative total of nouns, verbs, adjectives and adverbs in Obama's and Romney's delivery was roughly the same, with Obama using slightly more Δrel=+1.5% (Δabs=+0.6%, 40.5% vs 39.9%). Within this set of words, Obama had a +3.5% (1,061 vs 1,025) more unique words.

Romney used Δrel=+3.5% (Δabs=+1.7%, 50.8% vs 49.1%) more nouns and Δrel=+6.4% (Δabs=+1.1%, 18.4% vs 17.3%) more adjectives, but Obama used Δrel=+8.8% (Δabs=+2.3%, 28.4% vs 26.1%) more verbs and Δrel=+10.6% (Δabs=+0.5%, 5.2% vs 4.7%) more adverbs.

Across all parts of speech, Obama's use of unique words is 3-8% richer than Romney's. Relative to Romney, Obama's use of unique nouns, verbs, adjectives and adverbs was Δrel=+7.8% (Δabs=+2.7%, 37.5% vs 34.8%), Δrel=+4.7% (Δabs=+1.9%, 42.5% vs 40.6%), Δrel=+3.4% (Δabs=+1.6%, 49.3% vs 47.7%), and Δrel=+7.8% (Δabs=+2.9%, 40.3% vs 37.4%).

Table 5
legend
a c
b d
1535

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
2.78 5 21
2.7795.00021.000
2.67 5 21
2.6655.00021.000
2.35 3 24
2.3513.00024.000
2.03 3 11
2.0283.00011.000
2.48 4 25
2.4844.00025.000
Mitt Romney
3.04 6 26
3.0366.00026.000
2.87 5 31
2.8735.00031.000
2.46 4 17
2.4644.00017.000
2.10 3 11
2.0953.00011.000
2.67 3 26
2.6733.00026.000
total
3.79 8 43
3.7888.00043.000
3.58 9 42
3.5829.00042.000
2.97 5 37
2.9735.00037.000
2.63 4 19
2.6294.00019.000
3.50 6 51
3.5006.00051.000

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

Table 5
commentary
Obama repeats his top verbs more than Romney: know, think and make.

Obama is consistently less repetitive with his words than Romney. For nouns, verbs, adjectives and adverbs his average word frequency is -7.0% (2.67 vs 2.87), -4.5% (2.35 vs 2.46), -3.3% (2.03 vs 2.1), and -7.1% (2.48 vs 2.67), less, respectively. He particularly repeats nouns and adverbs less than Romney.

For verbs the 90% cumulative distribution value is higher than Obama, indicating that his frequency distribution is skewed and that his most repeated verbs were repeated more often. Obama's top 3 verbs were know (24), think (26) and make (39). Romney's were make (18), want (26) and will (31).

Romney hammers away at his nouns. His top 4 by frequency were medicare (31), tax (37), president (39) and people (64). Obama's were people (21), tax (21), romney (44) and governor (48). It is interesting to see that Romney refers to people 64 times but to Obama 39 times. Obama mentions people 21 times, prefering the use of folks, which he mentions 10 times.

Table 5
legend
a b c
51025

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
Word pairs (total and unique) categorized by part of speech (POS)
part of speech pairings - Barack Obama
noun verb adjective adverb
noun
4,105 3,451
  84.1%
6543451
verb
5,187 4,596
  88.6%
5914596
1,423 1,318
  92.6%
1051318
adjective
2,740 2,413
  88.1%
3272413
1,639 1,475
  90.0%
1641475
423 381
  90.1%
42381
adverb
853 788
  92.4%
65788
512 479
  93.6%
33479
290 266
  91.7%
24266
44 42
  95.5%
242

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

Table 6b
part of speech pairing — Mitt Romney
Word pairs (total and unique) categorized by part of speech (POS)
part of speech pairings - Mitt Romney
noun verb adjective adverb
noun
3,600 2,862
  79.5%
7382862
verb
3,601 3,109
  86.3%
4923109
792 723
  91.3%
69723
adjective
2,155 1,820
  84.5%
3351820
1,016 944
  92.9%
72944
355 319
  89.9%
36319
adverb
600 536
  89.3%
64536
317 299
  94.3%
18299
178 170
  95.5%
8170
30 27
  90.0%
327

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
3,451 2,862
  82.9%
3451
2862
verb
4,596 3,109
  67.6%
4596
3109
1,318 723
  54.9%
1318
723
adjective
2,413 1,820
  75.4%
2413
1820
1,475 944
  64.0%
1475
944
381 319
  83.7%
381
319
adverb
788 536
  68.0%
788
536
479 299
  62.4%
479
299
266 170
  63.9%
266
170
42 27
  64.3%
42
27

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

Table 6
commentary
Obama repeats his top verbs more than Romney: know, think and make.

Because Obama's sentences were +40.0% (8.4 vs 6) longer than Romney's, he had consistenly more total and unique pairings.

Obama had nearly twice as many, +82.3% (1,318 vs 723), unique verb-verb pairings as Romney. Where the candidates were most similar was in the number of unique noun-noun and adjective-adjective pairings. It is interesting to see the contrast between noun-noun and verb-verb statistics — Obama's sentences had relatively more verbs in them, suggesting that he spoke in terms of compound actions.

Table 6 a,b
legend
a c
  d
3010

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
50
45

a :: unique pairs for Barack Obama

c :: unique pairs for Mitt Romney

d :: (c) relative to (a) (i.e. Mitt Romney relative to Barack Obama)

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
875 575
100.0% 65.7%
14.4% 35.9%
300575
1242669920335113728
390 266
44.6% 68.2%
12.9% 31.5%
124266
124266
302 203
34.5% 67.2%
18.3% 36.6%
99203
99203
148 113
16.9% 76.4%
13.7% 27.4%
35113
35113
35 28
4.0% 80.0%
11.6% 32.6%
728
728
Mitt Romney
859 539
100.0% 62.7%
14.2% 33.7%
320539
12627686168441231422
402 276
46.8% 68.7%
13.3% 32.7%
126276
126276
254 168
29.6% 66.1%
15.4% 30.3%
86168
86168
167 123
19.4% 73.7%
15.4% 29.9%
44123
44123
36 22
4.2% 61.1%
12.0% 25.6%
1422
1422
both candidates
4,327 486
100.0% 11.2%
71.4% 30.4%
3841486
190924889113155711318831
2,157 248
49.8% 11.5%
71.3% 29.3%
1909248
1909248
1,022 131
23.6% 12.8%
61.9% 23.6%
891131
891131
670 113
15.5% 16.9%
61.9% 27.4%
557113
557113
219 31
5.1% 14.2%
72.8% 36.0%
18831
18831
total
6,061 1,600
100.0% 26.4%
100.0% 100.0%
44611600
2182845109555567141221586
3,027 845
49.9% 27.9%
100.0% 100.0%
2182845
2182845
1,650 555
27.2% 33.6%
100.0% 100.0%
1095555
1095555
1,083 412
17.9% 38.0%
100.0% 100.0%
671412
671412
301 86
5.0% 28.6%
100.0% 100.0%
21586
21586

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

Table 7
commentary
Candidates use many exclusive words, share fewer.

This table shows the number of words that were spoken exclusively by either candidate, and those that were shared. In total, 1,600 unique nouns, verbs, adjectives and adverbs were used between the two candidates. The shared fraction (486, 30.4%) was smallest, with Obama having the larger number of exclusive words (575, 35.9%) than Romney (539, 33.7%).

Of all unique nouns (845), Obama and Romney had more exclusive to them (266, 31.5%) and (276, 32.7) than they shared (248, 29.3%). Within this set of nouns, Romney had a slightly richer set with 276 unique nouns, compared to Obama's 266.

An even greater difference is found in the set of unique verbs (555), of which only 131 (23.6%) were shared. The largest fraction was used exclusively by Obama (203, 36.6%) with 168 (30.3%) by Romney. Obama's high fraction of exclusive verbs suggests his emphasis on various forms of action.

Like for nouns, Romney had the largest fraction of adjectives (29.9%).

Adverbs were the only part of speech that were more extensively shared (31, 36.0%), indicating a lower variety in this part of speech within the debate. Obama had a greater exlusive fraction (32.6%) than Romney (25.6%).

Table 7c
legend
a d
b e
c f
4030
40302015105

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
529 240
100.0% 45.4%
0.37 0.44
289240
433 234
81.9% 54.0%
0.30 0.43
199234
Mitt Romney
549 241
100.0% 43.9%
0.35 0.44
308241
439 231
80.0% 52.6%
0.28 0.42
208231

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
2.31 2 3
2.3122.0003.000
2.36 2 4
2.3602.0004.000
Mitt Romney
2.29 2 3
2.2952.0003.000
2.35 2 4
2.3462.0004.000

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

Table 8
commentary
Candidates deliver similar number of concepts.

Obama has -3.6% (529 vs 549) fewer noun phrases than Romney. But, given that he delivered fewer words and a higher fraction of unique words, it is not surprising that he had a higher fraction of unique phrases by Δrel=+4.6% (Δabs=+2.0%, 45.4% vs 43.39%).

Obama was less repetitive, which can be seen in the number of phrases per noun. He delivered +5.7% (0.37 vs 0.35) more noun phrases per noun than Romney.

Obama's phrases were only slightly longer by +0.9% (2.31 vs 2.29), for all phrases, and by +0.4% (2.36 vs 2.35), for top-level phrases.

Table 8a
legend
a d
b e
c f
1070

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
102080

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
448 225
41.6% 50.2%
223225
399 226
89.1% 56.6%
173226
Mitt Romney
458 231
42.5% 50.4%
227231
399 224
87.1% 56.1%
175224
both candidates
172 31
16.0% 18.0%
14131
74 18
43.0% 24.3%
5618

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
2.35 2 4
2.3552.0004.000
2.38 2 4
2.3762.0004.000
Mitt Romney
2.34 2 4
2.3382.0004.000
2.36 2 4
2.3632.0004.000
both candidates
2.08 2 3
2.0762.0003.000
2.18 2 3
2.1762.0003.000

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

Table 9
commentary
Relatively few phrases are spoken by both speakers.

The majority of phrases are not shared by the speakers. Only 16.0% of all phrases are shared, with Obama and Romney delivering roughly the same number of exclusive phrases (448 vs 458). The number of total and unique top-level phrases is almost identical for the two speakers.

Exclusive phrases tended to be longer for the candidates (2.34, 2.35) than shared (2.08).

Table 9a
legend
a c
b d
1070

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
102080

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
468
-31.7%
468.732412593364
0.438 0.348 0.375 0.425 0.493 0.403 0.454 0.975
-1.6% +12.6% +7.8% +4.8% +3.3% +7.6% +3.4% +1.7%
0.43750.3478806907378340.3752591568762960.4253285543608120.4931506849315070.4025974025974030.4536862003780720.975
Mitt Romney
685
+46.3%
685.849492170176
0.444 0.309 0.348 0.406 0.477 0.374 0.439 0.959
+1.6% -11.2% -7.2% -4.6% -3.2% -7.1% -3.2% -1.7%
0.4444872288538060.3089806526133410.3481012658227850.405904059040590.4772727272727270.3741496598639460.4389799635701280.95850622406639
Table 10
commentary
Obama thoroughly less repetitive than Romney — by almost 50%

Obama had -31.7% lower Windbag Index. This is a reflection of the fact that his speech is less repetitive across 7 of the 8 metrics. The only factor that was lower for Obama was the fraction of words that were non-stop (0.438 vs 0.444).

Note that the 2012 Windbag Index cannot be compared directly to the 2008 version because of different methodology in computing noun phrases.

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 - all words

Debate tag cloud for Barack Obama

Debate Word Cloud for Mitt Romney - all words

Debate tag cloud for Mitt Romney
commentary

Romney's cloud appears more bloated that Obama's. This is due to his higher repetition — recall that Romney had a non-stop average word frequency +10.3% (3.2 vs 2.9) higher than Obama.

Romney's most commonly used verb was "want", suggesting a sense of desire and entitlement on the part of his constituents and "will", suggesting that he'll give it to them. From his top words you can construct the sentence "people just want lower tax".

Obama mentioned Romney quite a bit (Romney did not return the favour) and had a predilection for "make", "think", "know", as well as "want".

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

Debate tag cloud for Barack Obama

Words exclusive to Mitt Romney

Debate tag cloud for Mitt Romney
commentary

Romney engages in some fearmongering, with words like "lose", "kill", "debt" and "always". Remember, these are words unique to Romney, not used by Obama. Obama's major exclusive words were "difference", "folks", "opportunity" and "loopholes".

Notice Romney's approach to describing the middle-class — he uses "middle-income", whereas Obama uses "average" and "folks".

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.

Cloud of noun words, by speaker

commentary

Obama's contribution of "folks" and "opportunity" dominates here. This means that within the set of words unique to Obama, he repeated them more than the corresponding top-use words of Romney, which were "half" (refering to the deficit) and "retirees".

The rest of the cloud, however, is filled more with Romney's words than Obamas, suggesting repetition now on Romney's part. Romney is paranoid about "food", "stamps" and "debt", which are all words unmentioned by Obama.

Some interesting nouns for Obama are "choices", "math", "law", and "war". Romney has "principle", "Spain", "China", "burden" and "mortgage".

Cloud of verb words, by speaker

commentary

The top verbs unique to Romney were "lose" and "hurt", followed by words like "concerned", "taxed" and "kill". For Obama, the top unique verb was the general "went", and also "buy", "created" and "called".

If the verbs are an indication of action planned for and supported by the candidates, then Romney is someone who wishes to "stop" and "simplify" and worries about being "kill"(ed) and "crushed". Obama is ever more hopeful and positive with "initiate", "invest", "created", and "reflect".

Cloud of adjective words, by speaker

commentary

Obama and Romney reserve unique adjectives to refer to the middle class. Romney uses their income, "middle-income", whereas Obama uses the more neutral "average". Romney did not use "fair", mentioned by Obama 4 times.

Obama contributes more large words to this cloud, indicating greater relative repetition in adjectives exclusive to him.

Cloud of adverb words, by speaker

commentary

Adverbs yield the smallest word cloud because they are the least frequent of the four parts of speech I examined. Obama seems to want to energize the audience with "aggressively", "vitally" and "essentially". Romney is categorical with "always" and "rather". These words suggest that Romney is guided by immutable rules that apply "always" and "correctly" (to him, also "obviously").

Note Romney's use of technical words like "mathematically", against Obama's "structurally", and "extraordinarily". I'd vote for Obama merely for his exclusive use of "ironically".

Cloud of all words, by speaker

commentary

When all parts of speech are combined into cloud, Romney's unique words swamp out those of Obama, suggesting that Romney repeated terms exclusive to him more frequently.

Obama wants to remind "folks" of "opportunity", sticking to his message of hope. Romney, on the other hand, is reminding the audience that he hasn't forgotten the "middle-income" segment.

Word Pair Clouds for Each Candidate

word pairs for Barack Obama

adjective/adjective by Barack Obama
adjective/adverb by Barack Obama
adjective/noun by Barack Obama
adjective/verb by Barack Obama
adverb/adverb by Barack Obama
adverb/noun by Barack Obama
adverb/verb by Barack Obama
noun/noun by Barack Obama
noun/verb by Barack Obama
verb/verb by Barack Obama

word pairs for Mitt Romney

adjective/adjective by Mitt Romney
adjective/adverb by Mitt Romney
adjective/noun by Mitt Romney
adjective/verb by Mitt Romney
adverb/adverb by Mitt Romney
adverb/noun by Mitt Romney
adverb/verb by Mitt Romney
noun/noun by Mitt Romney
noun/verb by Mitt Romney
verb/verb by Mitt Romney
commentary

The major contributors to Obama's word pair tag clouds are "right now", "small businesses", "middle-class families", and "well think". Romney knows what is "always best" and focuses on "efficient private" and "free ever", with heavy reference to finances.

Obama's noun/noun combination tag is uniform in size, suggesting that he did not put undue emphasis on any one specific concept. He mentions "health care", "tax cuts", and "health insurance". Romney has some very large word in the noun/noun cloud, indicating heavy repetition of "health care" and "income tax".

Downloads

Debate transcript

Parsed word lists (word lists, part of speech lists, noun phrases, sentences)

Word clouds

Raw data structure

Please see the methods section for details about these files.