Research Tools
Discourse Analysis
Semantic discourse categories assigned by Claude Haiku — 14 DH-informed categories classifying how commenters frame their arguments.
Comments Labeled
44,412
of 487,977 total
Coverage
9.1%
of eligible comments
Categories Active
14
of 14 discourse types
Avg Confidence
0.807
classifier confidence
Model
Claude Haiku
multi-label classification
Search & Filter
Meta-Commentary
3,846 comments
Thanks to the parties
Thanks to the parties
Vague reference to political parties appears to be commentary on video content or broader discourse rather than substantive argument.
Meta-Commentary
0.70
ahrick08
Sep 21, 2025
12:55 ❤ 14:50 ❤ Hindu Sikh
12:55 ❤ 14:50 ❤ Hindu Sikh
Comment references timestamps and religious identities visible in the video, indicating engagement with video content rather than substantive discourse about immigration.
Meta-Commentary
0.70
Nue195
Sep 23, 2025
I heard enough 😂
I heard enough 😂
Brief dismissive reaction to the video content itself, expressing disengagement through humor.
alexisvillaroman
Sep 29, 2025
Not "THEY" More like HE.,\nPlease.,
Not "THEY" More like HE.,\nPlease.,
Commenter appears to correct grammar or pronoun usage in the video or previous comments.
Meta-Commentary
0.70
@wiseforce7045
Mar 4, 2025
Michelle for prime minster .!! She is the best.
Michelle for prime minster .!! She is the best.
Brief statement of support for a specific person mentioned in the video, likely a public figure or politician.
Meta-Commentary
0.70
JaneDoe-k3r
Oct 3, 2025
blame sidhu moose whala
blame sidhu moose whala
Brief reference to a specific person (likely mentioned in video) without substantive argument; appears to be a tangential comment about the video content.
Meta-Commentary
0.70
gregcooks9
Oct 5, 2025
City with 0 vibe.
City with 0 vibe.
Brief comment about the video's subject matter or location rather than substantive immigration discourse.
Meta-Commentary
0.70
stefandee1970
Oct 16, 2025
No . Not true .
No . Not true .
Vague disagreement without substantive content; appears to be a reaction to the video or previous comments rather than substantive discourse.
Meta-Commentary
0.70
luketracey3269
Oct 20, 2025
The node guys in the back are very agreeable ?
The node guys in the back are very agreeable ?
Comments on the appearance and demeanor of people visible in the video background.
Meta-Commentary
0.68
@ionescudragos2123
Mar 4, 2025
trump said , trudeau got to go
trump said , trudeau got to go
Brief reference to Trump's statement about Trudeau, functioning as commentary on political discourse rather than substantive argument.
Meta-Commentary
0.68
@kenpitak8479
Mar 4, 2025
More lying from cnn! drop the russian BS
More lying from cnn! drop the russian BS
Dismisses the news source (CNN) and its coverage as dishonest, critiquing media rather than substantive policy.
@flyingwyoming5184
Mar 4, 2025
If Carney doesn't suffer fools lightly - how does Annandasangaree still have a job?
If Carney doesn't suffer fools lightly - how does Annandasangaree still have a job?
Questions the competence of a specific government official, using a rhetorical jab rather than substantive policy analysis.
jimg.4913
Feb 26, 2026
Everyone in the comments loves this man - yet his country don't like him... just saying
Everyone in the comments loves this man - yet his country don't like him... just saying
Observes a disconnect between YouTube comment support and domestic popularity, commenting on the video's reception and broader perception.
@petertheobald9624
Mar 4, 2025
Why is anyone surprised?
Why is anyone surprised?
Rhetorical question about the video's content or the broader situation, inviting engagement with the discussion itself.
Meta-Commentary
0.68
@MerrielBloomfield
Mar 4, 2025
Love how those chicken wingers came all the way from the United States to race bait in Canada. Of course when u can't cover real issues like AIPAC in ur country u must stir the …
Love how those chicken wingers came all the way from the United States to race bait in Canada. Of course when u can't cover real issues like AIPAC in ur country u must stir the pot elsewhere
Criticizes the video/creator for alleged race-baiting and avoiding real issues, with unsubstantiated claims about motives.
WhoUnalivedRogerRabbit
Sep 19, 2025
seeing this after the New Zealand protest is perfect timing
seeing this after the New Zealand protest is perfect timing
References external event (New Zealand protest) and comments on the video's timing relevance.
Meta-Commentary
0.68
liz____518
Jan 27, 2026
Make that make sense he says. No senses here
Make that make sense he says. No senses here
Brief dismissive comment about the video's logic or a speaker's statement, critiquing coherence.
Meta-Commentary
0.65
@MrsDeCastilloTube
Mar 4, 2025
And that's how it's done!
And that's how it's done!
Brief affirmation of the video content itself without substantive engagement with immigration policy.
Meta-Commentary
0.65
@cd7206
Mar 4, 2025
Trump seemes to be a russian assed, \n\nCNN analyst: 18 reasons why Trump may be a Russian asset\n\nUS author explains Donald Trump’s Russia, KGB connections
Trump seemes to be a russian assed, \n\nCNN analyst: 18 reasons why Trump may be a Russian asset\n\nUS author explains Donald Trump’s Russia, KGB connections
References media coverage and news analysis rather than engaging with the video's immigration topic directly.
Meta-Commentary
0.65
@koosherbrink2820
Mar 4, 2025
no sparkle socks you did only had to do 2 things\nwe see the world news we can read
no sparkle socks you did only had to do 2 things\nwe see the world news we can read
Dismissive comment about the speaker ('sparkle socks') and the video's relevance, with sarcastic tone about global awareness.
@smileographer
Mar 4, 2025
Compare Videos
Select 2–4 videos to compare their discourse profiles side by side (% of labeled comments).
Discourse Taxonomy
Category Distribution
Primary discourse type assigned to each comment
Classifier Confidence
Distribution of confidence scores across all labeled comments
Discourse Over Time
Top 6 discourse types by month — how framing evolves over time
Category Co-occurrence
Which discourse types most frequently appear together on the same comment
Top Channels by Discourse Type
Identity Assertion
CNN
2,313
Tyler Oliveira
1,991
RocaNews
467
JamCan
274
Yoke Immigration Canada
89
Solidarity
CNN
4,297
Tyler Oliveira
400
RocaNews
75
JamCan
36
CTV Your Morning
32
Policy Critique
CNN
3,445
Tyler Oliveira
551
Toronto Sun
340
CTV News
268
RocaNews
235
Humor / Satire
CNN
2,078
Tyler Oliveira
1,667
RocaNews
241
Global News
89
CTV News
68
Fear / Threat
Tyler Oliveira
1,549
CNN
1,332
RocaNews
321
JamCan
204
Toronto Sun
118
Meta-Commentary
Tyler Oliveira
1,702
CNN
1,478
RocaNews
168
CTV News
81
JamCan
77
Unverified Claim
CNN
1,480
Tyler Oliveira
820
RocaNews
203
Yoke Immigration Canada
203
JamCan
152
Moral Argument
CNN
1,733
Tyler Oliveira
704
RocaNews
205
JamCan
73
CTV Your Morning
23
Classified by Claude Haiku (Anthropic)
|
14-category DH taxonomy
|
Search
|
Discourse Quality (Perspective API)