home > results and commentary > Barack Obama vs. John McCain (3nd debate)

Word Analysis of 2008 U.S. Presidential Debates

Barack Obama vs. John McCain (3nd debate)

15 October 2008



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 1. Number of all words and unique words used by each speaker.
speaker word count
Barack Obama
7,259 1,375
52.7% 17.0%
60261233
John McCain
6,523 1,295
47.3% 17.7%
53681155
all
13,782 2,003
100.0% 13.4%
119301852
Table 1 Analysis

Obama continues to deliver consistently more words than McCain. Although in this debate some 300 words fewer were spoken by Obama than in the first debate, Obama said +11.3% more words than McCain. Obama' unique vocabulary size remained at 1,375, only one word less than in the first debate.

McCain's vocabulary size in this debate was only 1,295, a change of -6.2% from the first debate. Note that although fewer words were said, Obama delivered just as many unique words in this debate as the first one, suggesting that McCain's drop was not necessarily due less allotted time. Table 1 Legend

a c
b d
3010
a :: total number of words
b :: proportion of words in the debate
c :: unique words in (a)
d :: (c) relative to (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 are frequently-used bridging words (e.g. pronouns and conjunctions) and do not carry inherent meaning. The fraction of words that are stop words is one measure of the complexity of speech.

Table 2. Expanded analysis of total, stop and non-stop word count.
speaker word category
all stop non-stop
Barack Obama
7,259 1,375
52.7% 18.9%
58841375
3,972 142
54.7% 3.6%
3830142
3,287 1,233
45.3% 37.5%
20541233
John McCain
6,523 1,295
47.3% 19.9%
52281295
3,536 140
54.2% 4.0%
3396140
2,987 1,155
45.8% 38.7%
18321155
all
13,782 2,003
100.0% 14.5%
117792003
7,508 151
54.5% 2.0%
7357151
6,274 1,852
45.5% 29.5%
44221852
Table 2 Analysis

Non-stop word fraction in this debate was slightly lower than in the first debate, by about 2% for both candidates. 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 analysis uses debate content that has been filtered for stop words.

Word frequency

The word frequency table summarizes the frequency with which words were used. Specifically, 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 3. Average, 50%, and 90% weighted cumulative word frequencies (content filtered for stop words).
speaker word frequency
Barack Obama
2.67 4.00 28.00
2.6664.00028.000
John McCain
2.59 4.00 22.00
2.5864.00022.000
all
3.39 7.00 45.00
3.3887.00045.000
Table 3 Analysis

Average frequency remains very similar for both candidates, here at 2.67 for Obama and 2.591 for Mccain, compared to 2.63 and 2.51 during the first debate. 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. Number of words in a sentence, as measured by average number of words, 50% and 90% weighted cumulative values for three word groups (all words, stop words and non-stop words).
speaker sentence size (by word type)
all stop non-stop
Barack Obama
16.8 26.0 50.0
16.803
26.000
50.000
9.6 13.0 30.0
9.617
13.000
30.000
7.8 12.0 26.0
7.771
12.000
26.000
John McCain
13.1 18.0 46.0
13.098
18.000
46.000
7.6 10.0 26.0
7.588
10.000
26.000
6.2 8.0 22.0
6.159
8.000
22.000
all
14.8 21.0 47.0
14.819
21.000
47.000
8.5 12.0 28.0
8.542
12.000
28.000
6.9 10.0 24.0
6.910
10.000
24.000
Table 4 Analysis

Sentences of both candidates were shorter, by about 0.6 words for Obama and 2.8 for McCain. Once stop words were removed, the non-stop length sentence length for Obama was the same as the first debate, but nearly a whole word shorter for Mccain (6.2 vs 7.1). Here McCain was obviously either being cut short, simplifying his delivery or flustered.

Table 4 Legend
a b c
15
30
75
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. Count of words (total and unique) categorized by part of speech (POS).
parts of speech
n+v+adj+adv nouns (n) verbs (v) adjectives (adj) adverbs (adv)
Barack Obama
3,160 1,199
100.0% 37.9%
97263249435327921513976
1,604 632
50.8% 39.4%
972632
847 353
26.8% 41.7%
494353
494 215
15.6% 43.5%
279215
215 76
6.8% 35.3%
13976
John McCain
2,876 1,121
100.0% 39.0%
9586534273142041809644
1,611 653
56.0% 40.5%
958653
741 314
25.8% 42.4%
427314
384 180
13.4% 46.9%
204180
140 44
4.9% 31.4%
9644
all
6,036 1,807
100.0% 29.9%
2224991105053856831026095
3,215 991
53.3% 30.8%
2224991
1,588 538
26.3% 33.9%
1050538
878 310
14.5% 35.3%
568310
355 95
5.9% 26.8%
26095
Table 5 Analysis

There is no significant change for part of speech components from the first debate. Obama dropped noun use by just 2%, while McCain added 2% to his nouns. All other part of speech differences were smaller than a percent.

Unique part of speech component was quite different for verbs. Obama's unique fraction for verbs was 46%, up from 41.7% during the first debate. McCain on the other hand has 42.4% of his verbs unique, compared to 45.5% for the first debate. That's a significant difference and suggests more partial and less complex sentences. Table 5 Legend

a c
b d
1535
a :: total number of words for a given POS (all, noun, verb, adjective, adverb)
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. Frequency of words by part of speech (POS).
part of speech frequency
n+v+adj+adv nouns (n) verbs (v) adjectives (adj) adverbs (adv)
Barack Obama
2.64 4.0 28
2.6364.00028.000
2.54 4.0 16
2.5384.00016.000
2.26 3.0 29
2.2643.00029.000
2.30 3.0 13
2.2983.00013.000
2.83 4.0 32
2.8294.00032.000
John McCain
2.57 4.0 23
2.5664.00023.000
2.47 4.0 16
2.4674.00016.000
2.19 3.0 16
2.1943.00016.000
2.13 3.0 8
2.1333.0008.000
3.18 5.0 22
3.1825.00022.000
all
3.34 7.0 45
3.3407.00045.000
3.24 7.0 32
3.2447.00032.000
2.75 5.0 46
2.7545.00046.000
2.83 5.0 19
2.8325.00019.000
3.74 7.0 54
3.7377.00054.000
Table 5 Analysis

Part of speech frequency increased for both candidates. Certainly McCain' frequencies were quite a bit higher across the board from the first debate (nouns +1.2%, verbs +6.3%, adverbs +24.7%, except for adjectives which reduced in frequency by -4.1%. Obama, on the other hand, had a more modest increase (nouns -0.8%, verbs +7.6%, adjectives +3.6% and adverbs -3.1%.

We're seeing a greater increase in frequency for McCain. This, coupled with significantly fewer unique words delivered suggests a poor for this debate performance. 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 attempt to capture the contextual use of parts of speech within a sentence and extract concepts from the text. Specifically, unique pairs of words indicate complexity and inter-relatedness between concepts in a sentence.

Table 6a (Barack Obama). Word pairs (total and unique) categorized by part of speech (POS) for Barack Obama.
parts of speech pairings — Barack Obama
noun verb adjective adverb
noun
4,699 3,798
23.6% 80.8%
9013798
verb
4,706 3,897
23.6% 82.8%
8093897
1,017 831
5.1% 81.7%
186831
adjective
3,165 2,603
15.9% 82.2%
5622603
1,428 1,207
7.2% 84.5%
2211207
446 375
2.2% 84.1%
71375
adverb
1,080 944
5.4% 87.4%
136944
627 520
3.2% 82.9%
107520
358 308
1.8% 86.0%
50308
90 69
0.5% 76.7%
2169
Table 6b (John McCain). Word pairs (total and unique) categorized by part of speech (POS) for John McCain.
parts of speech pairings — John McCain
noun verb adjective adverb
noun
4,108 3,294
29.1% 80.2%
8143294
verb
3,482 2,942
24.6% 84.5%
5402942
616 538
4.4% 87.3%
78538
adjective
2,033 1,683
14.4% 82.8%
3501683
732 655
5.2% 89.5%
77655
216 191
1.5% 88.4%
25191
adverb
677 562
4.8% 83.0%
115562
294 256
2.1% 87.1%
38256
177 152
1.3% 85.9%
25152
27 20
0.2% 74.1%
720
Table 6c (Barack Obama vs John McCain). Word Pairs (total and unique) categorized by part of speech (POS) for both candidates.
parts of speech pairings
noun (n) verb (v) adjective (adj) adverb (adv)
noun
4,699 4,108
  87.4%
80.8% 80.2%
4699.000
3798
4108.000
3294
verb
4,706 3,482
  74.0%
82.8% 84.5%
4706.000
3897
3482.000
2942
1,017 616
  60.6%
81.7% 87.3%
1017.000
831
616.000
538
adjective
3,165 2,033
  64.2%
82.2% 82.8%
3165.000
2603
2033.000
1683
1,428 732
  51.3%
84.5% 89.5%
1428.000
1207
732.000
655
446 216
  48.4%
84.1% 88.4%
446.000
375
216.000
191
adverb
1,080 677
  62.7%
87.4% 83.0%
1080.000
944
677.000
562
627 294
  46.9%
82.9% 87.1%
627.000
520
294.000
256
358 177
  49.4%
86.0% 85.9%
358.000
308
177.000
152
90 27
  30.0%
76.7% 74.1%
90.000
69
27.000
20
Table 6 Analysis

McCain's word pairings were substantially lower than Obama's. He delivered only about half of the adjective/verb, adjective/adjective, adverb/verb, adverb/adjective pairs. His adverb/adverb pairings were only 30% that of Obama. To some degree this is expected because McCain consistently delivers shorter sentences and fewer words. However, during this debate the pairing difference is substantially greater between the candidates thatn during the first debate.

The only paring which remained relatively the same was the noun/noun pairing. All others dropped by about 10% (and many by significantly more, like adverb/adverb from 58.3% of Obama in the first debate to 30.0%).

McCain's speech in this debate is clearly lacking variety and complexity. Table 6a,b Legend

a c
b d
3010
a :: total number of pairs, for a given category (e.g. verb/noun)
b :: (a) relative to all pairs
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
b e
50
45
35
30
a :: total number of pairs for Barack Obama
b :: relative unique pairs for Barack Obama
c :: total pairs for John McCain
d :: (c) relative to (a) (i.e. John McCain relative to Barack Obama)
e :: relative unique pairs for John McCain
bars :: values of (a), (b), (c) and (e)

Word usage

This section enumerates words that were unique to a canddiate (e.g. used by one candidate but not the other). 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 all words (union).

Table 7. Total and unique words used exclusively by a candidate or by both candidates.
parts of speech
n+v+adj+adv nouns (n) verbs (v) adjectives (adj) adverbs (adv)
Barack Obama
993 686
100.0% 69.1%
16.5% 38.0%
307686
14233874224821302151
480 338
48.3% 70.4%
14.9% 34.1%
142338
142338
298 224
30.0% 75.2%
18.8% 41.6%
74224
74224
212 130
21.3% 61.3%
24.1% 41.9%
82130
82130
72 51
7.3% 70.8%
20.3% 53.7%
2151
2151
John McCain
904 608
100.0% 67.3%
15.0% 33.6%
296608
175359571855395819
534 359
59.1% 67.2%
16.6% 36.2%
175359
175359
242 185
26.8% 76.4%
15.2% 34.4%
57185
57185
148 95
16.4% 64.2%
16.9% 30.6%
5395
5395
27 19
3.0% 70.4%
7.6% 20.0%
819
819
both
4,139 513
100.0% 12.4%
68.6% 28.4%
3626513
19072949191294338523125
2,201 294
53.2% 13.4%
68.5% 29.7%
1907294
1907294
1,048 129
25.3% 12.3%
66.0% 24.0%
919129
919129
518 85
12.5% 16.4%
59.0% 27.4%
43385
43385
256 25
6.2% 9.8%
72.1% 26.3%
23125
23125
all
6,036 1,807
100.0% 29.9%
100.0% 100.0%
42291807
2224991105053856831026095
3,215 991
53.3% 30.8%
100.0% 100.0%
2224991
2224991
1,588 538
26.3% 33.9%
100.0% 100.0%
1050538
1050538
878 310
14.5% 35.3%
100.0% 100.0%
568310
568310
355 95
5.9% 26.8%
100.0% 100.0%
26095
26095
Table 7 Analysis

Obama shatters McCain in the number of unique exclusive verbs, adjectives and adverbs. Given that we have been seeing very small differences up to now, these differences are huge. Obama delivered 224 exclusive verbs (i.e. only spoken by him), compared to McCain at 185. In the first debate he edged McCain with 127 more unique exclusive adjectives compared to 106, but in this debate the gap widens with 130 vs 95. For adverbs, McCain is a disaster this time around with only 19 unique exclusive adverbs compared to 35 in the first debate.

What is greatly telling are the contributions of unique parts of speech by each candidate to the overall debate. In the first debate, the values were relatively close for nouns and verbs, with Obama contributing to 6% more adjectives and adverbs than McCain. In this debate, Obama's contribution for verbs, adjectives and adverbs is about 7%, 11% and 24%, respectively! That last number is spectacular — in this debate Obama individually contributed to over half of the adverbs spoken in the debate. Table 7c Legend

a d
b e
c f
4030
40302015105
a :: total number of words unique to a candidate, for a given POS group
b :: (a) relative to all unique words to the candidate
c :: (a) relative to all words
d :: unique words in (a)
e :: (d) relative to (a)
f :: (d) relative to all unique words
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.

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

This table reports the absolute number of noun phrases, which is related to the number of total words (specifically, nouns) delivered. The next table presents the number of phrases relative to the number of nouns.

Table 8. Number of noun phrases.
speaker noun phrase
all top-level derived
Barack Obama
870 730
100.0% 83.9%
140730
404 384
46.4% 95.0%
20384
466 346
53.6% 74.2%
120346
John McCain
826 686
100.0% 83.1%
140686
358 347
43.3% 96.9%
11347
468 339
56.7% 72.4%
129339
Table 8 Analysis

The gap between Obama and McCain for unique top-level noun phrases nearly doubled in this debate. The derived noun phrase use was similar. McCain was clearly not in his best form. Table 8c 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

Noun Phrase Richness

The previous table presented the total number of noun phrases, which can be equated to individual concepts. In this table, this value is shown relative to the number of nouns used. The interpretation of this ratio is that of richness. In other words, how many noun phrases were constructed, per noun.

Table 9. Number of noun phrases relative to the number of nouns.
speaker noun phrase
all top-level derived
Barack Obama
0.54 1.16
0.5423940149625941.15506329113924
0.25 0.61
0.2518703241895260.607594936708861
0.29 0.55
0.2905236907730670.54746835443038
John McCain
0.51 1.05
0.5127250155183121.05053598774885
0.22 0.53
0.2222222222222220.531393568147014
0.29 0.52
0.2905027932960890.519142419601838
Table 9 Analysis

Number of noun phrases relative to the number of nouns remains relatively constant.

Table 9c Legend
a b
25
a :: ratio of the number of noun phrases to number of nouns
b :: ratio of the number of unique noun phrases to number of unique nouns
bar :: ratio of a:b

Noun Phrase Frequency and Size

Table 10. Noun phrase frequency, word count and unique word count.
speaker noun phrase
avg frequency word count unique word count
Barack Obama
1.19 1.00 4.00
1.1921.0004.000
2.78 3.00 7.00
2.7793.0007.000
2.73 3.00 7.00
2.7323.0007.000
John McCain
1.20 1.00 4.00
1.2041.0004.000
2.84 3.00 7.00
2.8433.0007.000
2.78 3.00 7.00
2.7833.0007.000
Table 10 Analysis

Noun phrase frequency and size remains relatively constant.

Table 10c Legend
a b c
51020
a :: average
b :: 50% weighted cumulative value
c :: 90% weighted cumulative value
bar1 :: normalized ratio 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 11. Windbag Index for each speaker. The higher the value, the greater the degree of repetition in the speech.
speaker Windbag Index
index value index terms
Barack Obama
457
-9.6%
457.093781995837
0.453 0.375 0.394 0.417 0.435 0.353 0.839 0.526 1.155
-1.1% -3.0% -2.8% -1.6% -7.2% +12.5% +1.0% +4.0% +9.9%
0.4528171924507510.3751140857925160.3940149625935160.4167650531286890.4352226720647770.3534883720930230.8390804597701150.5260273972602741.15506329113924
John McCain
505
+10.6%
505.71988429032
0.458 0.387 0.405 0.424 0.469 0.314 0.831 0.506 1.051
+1.1% +3.1% +2.9% +1.7% +7.7% -11.1% -1.0% -3.8% -9.0%
0.4579181358270730.3866755942417140.4053382991930480.4237516869095820.468750.3142857142857140.8305084745762710.5058309037900871.05053598774885
Table 11 Analysis

McCain's performance in the third debate was much worse than the first two debates. His WI this time around was 505, which should be compared to values of 368 and 352 for his other debates. Obama's index was higher in this debate as well, but not significantly.

Like before, McCain has better uniqueness statistics for word usage, but does much worse for adverbs and unique noun phrases. In particular, t9 for McCain is 9% lower than Obama (in the first debate it was 7.5% lower). Table 11c Legend

The Windbag Index is 1/(t1*t2*...*t9) where t1,t2,...,t9 are the individual terms. These terms 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 have no parent
t9 :: ratio of unique noun phrases to unique nouns

Note that 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' corresponding term (i.e. 100*(x-x0)/x0 where x is the value for the present speaker and x0 for the other speaker).

Tag Clouds

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

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

Debate Tag Clouds for Each Candidate — All Words

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 words in these tag clouds include words unique to one candidate as well as words used by both candidates. For other tag clouds below, only words unique to a candidate are used.

Keep in mind that the word sizes between tag clouds cannot be directly compared, since the minimum and maximum size of the words in each tag cloud is the same. However, the distribution of sizes within a tag cloud reflects the frequency distribution of words (tag cloud details).

Debate Tag Cloud for Barack Obama — all words

Debate tag cloud for Barack Obama

Debate Tag Cloud for John McCain — all words

Debate tag cloud for John McCain
Debate Tag Cloud Analysis

Obama continues to focus on "important" and uses "now" a great deal. "Nuclear" is no longer on the menu, and is replaced by "people", and "health". Obama's cloud has a significant noun component.

McCain has a lot fewer nouns than Obama in the center of his cloud. He still doesn't say "Barack", but says "tough", "difficult" and continues on "nuclear". It is interesting to see the large fraction of adjectives in McCain's tag cloud (i.e. frequently used). Although adjectives appear prominently in McCain cloud, he actually contributed fewer unique adjectives to the debate.

Debate Tag Clouds for Each Candidate — Unique Words

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

Debate Tag Cloud for Barack Obama — words unique to Barack Obama

Debate tag cloud for Barack Obama

Debate Tag Cloud for John McCain — words unique to John McCain

Debate tag cloud for John McCain
Unique Word Tag Cloud Analysis

Unique words to Obama in this debate suggest he continues to approach subjects with greater respect for complexity and inter-relationships. He uses "probably", for example, which McCain does not say. Words like "apparently", "priorities", "additional", "terms", "recently" all suggest that Obama is more comfortable with nuance and multivariate topics.

McCain' unique tag cloud actually nearly fits into the image! As mentioned above, McCain did not contribute as many unique words to this debate as past debates. The words he used were "nuclear" (which Obama did not use, perhaps with the feeling that people have had enough fearmongering and wish to hear explanations of domestic policy plans), "extreme", "unprecedented", "terribly" and "unilaterally". These are unwavering superlatives.

It is clear from these two tag clouds that Obama's delivery in this debate was richer and that he overwhelmed McCain' contribute with a greater range of topics.

Part of Speech Tag Clouds

In these tag clouds, words by both candidates were categorized on the basis of exclusivity to a candidate. Words unique to each candidate are drawn with a different color. Words used by both candidates are shown in grey.

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.

Words were further cateogorized by part of speech (noun, verb, adjective, adverb) and individual tag clouds were prepared for each category.

The last tag cloud in this section, which uses all (noun + verb + adjective + adverb) parts of speech.

Tag Cloud of noun words, by speaker

Noun Tag Cloud Analysis

Do you see many blue words? Those are nouns exclusive to McCain and there is is hardly a blue word in sight. It is shocking how overwhelming Obama's delivery drowns out McCain's contribution in the realm of nouns.

Tag Cloud of verb words, by speaker

Verb Tag Cloud Analysis

For verbs, McCain's contribution also lagged behind Obama's, whose use of "agree" and "disagree" suggest a conciliatory and balanced stance.

Tag Cloud of adjective words, by speaker

Adjective Tag Cloud Analysis

McCain's top contributions, other than the regular "Obama", were "nuclear" and "angry". To the end, "nuclear" continues to be a favourite of McCain, and entirely dropped in this debate by Obama, who, on the other hand, stands out with "economic" (I cannot believe McCain did not use this word), "additional", and "financial".

Tag Cloud of adverb words, by speaker

Adverb Tag Cloud Analysis

McCain completely loses the fight for adverbs and his unique contributions only pepper a sea of words used exclusively by Obama.

Tag Cloud of all words, by speaker

All Tag Cloud Analysis

When all parts of speech are compared, the verbal victor of the night is easy to call. Obama spoke with more extensive use of a greater number of concepts, drowning out McCain nearly entirely. You can see, for example, that although McCain uses "nuclear" exclusively, and this is one of his favourite words, when relative frequency is compared to words spoken by Obama (i.e. relative to frequencies by the same speaker), "nuclear" is drowned out by Obama's terms. This means that as much as McCain repeated "nuclear", Obama in his delivery drove a much larger number of points across.

Word Pair Vignette Tag Clouds for Each Candidate

Tag Cloud of word pairs by 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 Pair Tag Cloud Analysis for Barack Obama.

Obama is driving his points harder than in the first debate. The word pair tag clouds are less populated and filled with larger words, suggesting more pairs with higher relative frequency. For example adjective/adjective pair tag cloud has only 8 pairs, compared to over 20 in the first debate.

Tag Cloud of word pairs by John McCain

adjective/adjective by John McCain
adjective/adverb by John McCain
adjective/noun by John McCain
adjective/verb by John McCain
adverb/adverb by John McCain
adverb/noun by John McCain
adverb/verb by John McCain
noun/noun by John McCain
noun/verb by John McCain
verb/verb by John McCain
Word Pair Tag Cloud Analysis for John McCain.

McCain's noun/verb pairings suggests an attack stance with "obama wants", "anything say", "anything saying". In fact, by having "obama" as a word in his primary noun/verb pairings, McCain is seen to be talking more about what his opponent is doing than what he would himself do.

Contrast this to Obama, who does not have "McCain" or "John" in his top noun/verb pairs, chosing instead to talk about "people think" and "tax give" and "energy make".

Downloads

debate transcript (courtesy of CNN).

parsed word lists (analyzed transcript, including words by speaker, by POS, and all POS pairings).

tag cloud images

data structure

Please see the methods section for details about these files.