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: "Will there be a part …" 429 comments · Page 18 of 18
That was never part of the plan. I believe the intentions have been to populate Canada even though new jobs were not created, housing builds not increasing and infrastructure to support this population boom hasn't …
That was never part of the plan. I believe the intentions have been to populate Canada even though new jobs were not created, housing builds not increasing and infrastructure to support this population boom hasn't changed.
IRCC Names India in Study Permit Fraud | … · 15: Cluster #14
Close reading → Video sentiment →
Identity Attack0.002848835
Insult0.0075698765
Profanity0.009271945
Threat0.0059516393
Severe Toxicity0.00047683716
Low Tox 0.009613037 Constructive 0.573
Sep 29, 2025 IRCC Names India in Study …
It was all part of their plan. And it’s worked for many many years.
It was all part of their plan. And it’s worked for many many years.
IRCC Names India in Study Permit Fraud | … · 1: Outliers
Close reading → Discourse → Video sentiment →
Identity Attack0.001933138
Insult0.0067623714
Profanity0.010894509
Threat0.006699257
Severe Toxicity0.0006914139
Low Tox 0.008482091 Low Con 0.218 Unverified_Claim
Oct 1, 2025 IRCC Names India in Study …
Thank you for the video. I just took my test Jan 19/2026 got 19/20 on my first attempt. I read 2 chapters of discover Canada, found it was hard to follow and watched this video …
Thank you for the video. I just took my test Jan 19/2026 got 19/20 on my first attempt. I read 2 chapters of discover Canada, found it was hard to follow and watched this video 3 times instead. I took notes and read all the explanation with each questions. Wrote down the events according to timeline really helped. This video gave me a really solid foundation, but still had maybe 4-5 questions that wasn’t part of these questions.
Canadian Citizenship Test 2025 – 414 Real Past-Test … · 73: Cluster #72
Close reading → Video sentiment →
Identity Attack0.0022846176
Insult0.006353869
Profanity0.010108846
Threat0.0063238298
Severe Toxicity0.00054597855
Low Tox 0.0060631246 Constructive 0.698
Jan 20, 2026 2 likes Canadian Citizenship Test 2025 – …
This seems to nave become a problem because of the number of “new Canadians”. That’s the part your not suppose to say out loud but is the real problem in the American eye.
This seems to nave become a problem because of the number of “new Canadians”. That’s the part your not suppose to say out loud but is the real problem in the American eye.
· 1: Outliers
Close reading → Video sentiment →
Identity Attack0.00019084592
Insult0.00051859475
Profanity0.000032082033
Threat0.000029981105
Severe Toxicity0.0000019248057
Low Tox 0.0012512739
Dec 8, 2025

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.