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: "Cette politicienne prend des cas …" 1 comment
Cette politicienne prend des cas d’abus sans en dire combien de cas. Et sans fournir la solution quant à savoircommment on peut différencier lesquels sont légitimes et lesquels sont bogues comme elle dit,
Cette politicienne prend des cas d’abus sans en dire combien de cas. Et sans fournir la solution quant à savoircommment on peut différencier lesquels sont légitimes et lesquels sont bogues comme elle dit,
'We do know that there's a lot of … · 1: Cluster #1
Close reading → Discourse → Video sentiment →
Identity Attack0.0046987277
Insult0.24928534
Profanity0.018529098
Threat0.0054839733
Severe Toxicity0.0031280518
Low Tox 0.19599396 Moderate Con 0.351 Policy_Critique
Feb 24, 2026 '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.