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
Clear all | Quick: Toxic (>0.5) Most constructive High toxicity (>0.7) Most liked
Active: "He is working like a …" 354 comments · Page 15 of 15
If we actually want solutions, we should be talking about things like real-time tracking for overstays, linking federal/provincial systems, funding enforcement properly, and setting penalties that are predictable and enforced. Bring in experts not random …
If we actually want solutions, we should be talking about things like real-time tracking for overstays, linking federal/provincial systems, funding enforcement properly, and setting penalties that are predictable and enforced. Bring in experts not random paper pushers for “gotcha” moments. Sessions like this aren’t about fixing the system, they’re about stoking outrage. And more often than not, it ends up targeting vulnerable groups instead of creating policy that actually works.
IRCC Names India in Study Permit Fraud | … · 1: Outliers
Close reading → Discourse → Video sentiment →
Identity Attack0.0013596712
Insult0.009146886
Profanity0.010467518
Threat0.006641001
Severe Toxicity0.00061035156
Low Tox 0.013948329 Constructive 0.599 Policy_Critique
Oct 3, 2025 IRCC Names India in Study …
I've always treated others as how I'd like to be treated. 😊at 54 I can say I've noticed that this doesn't work out so well. ❤Canada
I've always treated others as how I'd like to be treated. 😊at 54 I can say I've noticed that this doesn't work out so well. ❤Canada
Why Canadians Are Turning Against Immigrants. · 1: Outliers
Close reading → Discourse → Video sentiment →
Identity Attack0.004328749
Insult0.008348881
Profanity0.010313802
Threat0.0060778605
Severe Toxicity0.0006198883
Low Tox 0.0126288915 Constructive 0.747 Personal_Narrative
Aug 29, 2025 1 likes Why Canadians Are Turning Against …
Usually there's one person that owns a lot of businesses and sponsors like 30 of them to come work at gas stations, liquor stores, and corner markets.
Usually there's one person that owns a lot of businesses and sponsors like 30 of them to come work at gas stations, liquor stores, and corner markets.
Why Canadians Are Turning Against Immigrants. · 1: Outliers
Close reading → Discourse → Video sentiment →
Identity Attack0.0017388993
Insult0.007892879
Profanity0.010296722
Threat0.0063885585
Severe Toxicity0.0005674362
Low Tox 0.010618322 Moderate Con 0.425 Unverified_Claim
Dec 15, 2025 1 likes Why Canadians Are Turning Against …
Sounds like the system if finally working and working faster to protect the country.
Sounds like the system if finally working and working faster to protect the country.
Deportations From Canada at Their Highest Level in … · 1: Cluster #1
Close reading → Video sentiment →
Identity Attack0.0021088778
Insult0.0070758737
Profanity0.010211324
Threat0.0066215824
Severe Toxicity0.00061511993
Low Tox 0.009361716 Moderate Con 0.321
Dec 24, 2025 Deportations From Canada at Their …

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.