Skip to content
Canadian Immigration Dashboard [ CID ]
Perspective API

Toxicity Scores & Embeddings

Search and explore comments with their Perspective API toxicity/prosocial scores alongside AI sentiment labels.

Communalytic | Toxicity & prosocial scores, embeddings, and clusters generated via Communalytic (Social Media Lab, Toronto Metropolitan University) using Google's Perspective API.
Toxicity Scored
55,769
9.3% of 596,542 total
Prosocial Scored
54,229
Embeddings
55,418
403 clusters
Avg Tox / Con
0.245 / 0.328

Summary Charts

click to expand

All 13 Dimensions

Score Distribution

Scored: 55,769
Unscored: 596,542 remaining
9.3% complete
{# Expects: explorer_rows, explorer_total, explorer_pages, current_page, page_range, filter_opts, f_q, f_polarity, f_tox_min, f_tox_max, f_sort, f_cluster, f_scope, explorer_reset_url #}

Comment Explorer

Browse comments with toxicity & constructive scores. Filter by keyword, polarity, toxicity range, or cluster.

Search & Filter

Search comment text, filter by category or toxicity level
Active: "Now do a "investigative journalism" …" 2 comments
Now do a "investigative journalism" on whyte invasi()n in Canada and where are the original Canadians .
Now do a "investigative journalism" on whyte invasi()n in Canada and where are the original Canadians .
Identity Attack0.3072352
Insult0.07745308
Profanity0.025497584
Threat0.008764107
Severe Toxicity0.007972717
Low Tox 0.26859093 Low Con 0.222 Call_To_Action
Jan 27, 2026 2 likes Inside Canada's Indian Invasion...
For someone who presents himself as a “journalist,” this is a deeply dishonest piece of work. The framing is not subtle: loaded titles, racial counting, selective locations, and deliberately uneven questioning all push the same …
For someone who presents himself as a “journalist,” this is a deeply dishonest piece of work. The framing is not subtle: loaded titles, racial counting, selective locations, and deliberately uneven questioning all push the same conclusion. Immigrants are interrogated about their presence and legality, while others are invited to pass judgment on them. When racial stereotypes are voiced, you don’t challenge them — you laugh. That’s not an accident, and it’s not neutral. You clearly understand that housing shortages, sanitation issues, and infrastructure strain are the result of policy failures and poor planning. Yet you repeatedly avoid those causes because blaming systems doesn’t generate clicks the way racial implication does. Reducing complex, structural problems to identity isn’t investigative — it’s lazy, cynical, and intellectually shallow. When a city worker gives a grounded response that doesn’t fit the narrative you’re pushing, it’s brushed aside. When visuals can be used to imply blame, they’re highlighted. That pattern makes the “just asking questions” defense ring hollow. This isn’t exposing truth — it’s manufacturing outrage and calling it journalism. With your reach, that’s not just irresponsible, it’s embarrassing. You're not a journalist but just a racist. That's all
Identity Attack0.1064171
Insult0.123407245
Profanity0.022354934
Threat0.007961469
Severe Toxicity0.004272461
Low Tox 0.22043827 Constructive 0.527 Policy_Critique
Jan 27, 2026 2 likes Inside Canada's Indian Invasion...

Perspective API Dimensions Reference

13 dimensions explained

Toxic (6)

Toxicity
— Rude, disrespectful, or unreasonable
Severe Toxicity
— Very hateful or aggressive
Identity Attack
— Targeting race, religion, gender, etc.
Insult
— Inflammatory or provocative language
Profanity
— Swear words or obscene language
Threat
— Intention to inflict pain or violence

Prosocial (7)

Affinity
— Agreement or shared understanding
Compassion
— Concern for others' wellbeing
Curiosity
— Desire to learn or understand more
Nuance
— Acknowledges complexity or multiple perspectives
Personal Story
— Shares personal experience
Reasoning
— Evidence-based or logical argumentation
Respect
— Politeness and consideration for others
Data sources: comment_perspective_scores, comment_embeddings, and view_comment_sentiment · Scores are probability values (0–1) from Google's Perspective API via Communalytic.