R
RasidMonitoring hate speech and incitement against migrants and refugees in Libya
Rasid monitors hate speech and incitement against migrants, refugees and UN agencies in Libyan public content, built for protection actors and their partners.
The purpose is to document what is said about people, not to track who says it.
What passes through the platform — last 30 days
3,580classified against the codebook 78 sources read publicly
What a labelled item looks like
H3 Incitement to exclusionthe codebook class
S2 · Serioushow severe
MIG Migrants (general)who it targets
The post text — not shown here
Facebook · 14 Sept, 00:19the public source and when
claude-haiku-4-5-20251001 · human-adjudicated labelsand why: the model, its confidence, whether a human reviewed it
The text itself is not shown on this public page. Subscribers see a labelled excerpt, never an archive.
How it works
- 01CollectPublic posts and comments from Facebook groups and pages, TikTok, Telegram channels and groups, and X search. Author identities are hashed at capture.
- 02ClassifyEvery item is classified automatically against a published codebook: one class, a severity, and who is targeted.
- 03AdjudicateA human adjudicates a sample each round. Disagreements become written rulings in the codebook, and the agreement rate is published per class.
- 04AlertText rules — not the classifier — raise alerts: dated ultimatum, threat, call for violence, location exposure, statement attributed to an institution, volume spike.
Classes v0.2 + rulings 1–42
H1Dehumanisation / slurDehumanisation or a direct slur81% · 31
H2Incitement to violenceIncitement to a concrete violent act78% · 40
H3Incitement to exclusionIncitement to exclusion: that they leave, be expelled, or be denied55% · 94
H4Hostile generalisationA hostile generalisation that describes the group without demanding they go73% · 55
M1Misinformation — settlementSettlement misinformation: figures, grants, cards, secret deals73% · 37
M2Misinformation — otherOther misleading framing, including tying the group to an external plot42% · 24
P1Policy oppositionLegitimate opposition — to a policy, a government, or organisations—
C1Counter-speechCounter-speech: pushing back on the hostility itself80% · 20
N1NeutralOn-topic and neutral — news or a report97% · 38
N2Migrant voiceThe targeted group speaking for itself72% · 18
XUnusableOff topic — nothing to do with migrants or the campaign51% · 63
The last column is how often the model picked the same class as the human adjudicator, and how many labels that is measured from. Classes whose sample has not reached the floor show a dash rather than a number that cannot be measured.
Severity
S3An explicit call to kill, burn or attack; a dated ultimatum with weapons; approval under a real violence video
S2A slur, a call to expel or evict or denounce, a location exposure, a forged statement, an ultimatum without violence language
S1A hostile generalisation, mild contempt, a vague settlement claim, low reach
S0No severity — policy opposition, counter-speech, neutral, migrant voice, unusable
Targets
AFR Black AfricansSDN SudaneseTCD ChadiansNER NigeriensNGA NigeriansERI EritreansETH EthiopiansSOM SomalisEGY EgyptiansBGD BangladeshisSYR SyriansPSE PalestiniansMIG Migrants (general)UN UNGOV GovernmentACT Activists / Libyans who push back
What the platform will not do
- 01Author identities are hashed at capture. The platform holds no identities and offers no way to resolve them.
- 02No raw export. Subscribers see aggregates, labelled excerpts and alerts only.
- 03Locations of individuals and organisations are always withheld — the occurrence is shown, never the content.
- 04Every label carries the codebook version and the human/model agreement rate behind it.