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: "Under a conservative government Michelle …" 3 comments
Go Michelle. Sad how nobody in the Liberal government is trying to solve this massive problem in advance. Why is it the Conservatives need to hound them? Clearly the Liberals need a babysitter to get …
Go Michelle. Sad how nobody in the Liberal government is trying to solve this massive problem in advance. Why is it the Conservatives need to hound them? Clearly the Liberals need a babysitter to get them to do their jobs
IRCC Names India in Study Permit Fraud | … · 92: Cluster #91
Close reading → Video sentiment →
Identity Attack0.018269362
Insult0.04207976
Profanity0.014054239
Threat0.007857903
Severe Toxicity0.0017929077
Low Tox 0.10913446 Low Con 0.205
Sep 30, 2025 IRCC Names India in Study …
Under a conservative government Michelle would fix it Vote smarter next time.
Under a conservative government Michelle would fix it Vote smarter next time.
'We do know that there's a lot of … · 1: Cluster #1
Close reading → Discourse → Video sentiment →
Identity Attack0.0039587705
Insult0.020579277
Profanity0.011441057
Threat0.0069387536
Severe Toxicity0.0009536743
Low Tox 0.040183347 Moderate Con 0.317 Call_To_Action
Feb 24, 2026 26 likes 'We do know that there's …
I typically do not agree with a lot of what the conservatives say, and I usually do not like anything that Michelle Rempel Garner says (or the way she says it). However, what she said …
I typically do not agree with a lot of what the conservatives say, and I usually do not like anything that Michelle Rempel Garner says (or the way she says it). However, what she said here, and the way she said it, makes complete sense. I was a bit disappointed that there are no actual numbers as to how much the government would save, but it doesn't seem like a bad idea to put the legislation in place, and whatever they save is a bonus. imho Be the Change You Wish to See in the World 💖
'We do know that there's a lot of … · 1: Cluster #1
Close reading → Discourse → Video sentiment →
Identity Attack0.0040512653
Insult0.011730902
Profanity0.011697251
Threat0.0062914654
Severe Toxicity0.00074863434
Low Tox 0.021314176 Constructive 0.763 Policy_Critique
Feb 23, 2026 11 likes 'We do know that there's …

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.