AI captures hate speech on radio for Liberia's iVerify fact-checkers

An evaluation for UNDP found that an AI application, integrated with iVerify, captured hate speech on radio and widened Liberia's monitoring in the 2023 elections.

  • Not rated an organization

    The evaluator found that the monitoring's scope widened but gives no count of radio items captured or acted on.

  • Not rated society

    The disinformation found during the elections is not attributed to the application.

Depth runs from 1, a convenience or time saved, to 5, a life or a livelihood preserved.

Status
Reported benefit.
Evidence

foundstudiedreportedclaimed

Only the evaluators support the benefit.

The system’s part
Not isolated. The evaluator describes an application that used artificial intelligence and an algorithm to automate the capture of hate speech on radio, citing the project's own progress report. The evaluator names no tool or model, gives no accuracy or volume figures and does not show that it learns from data. The 219 instances of disinformation are not attributed to it.
Limits
Not yet checked.
Costs and harms
Not yet checked.
Later
Not yet checked.

Download data Cite Suggest a correction

Benefit type
Increased Scalability
System
AI application for automated capture of hate speech on radio, integrated with UNDP's iVerify platform (application not named)
Made by
Not named in the evaluation (Peacebuilding Fund project on a peaceful electoral environment)
Used by
Local Voices Liberia (iVerify operator), with the National Elections Commission and UNDP
Where
Liberia
Stage
In a pilot
Date
Kind
Program
Broad benefit
Monitoring Processes, Materials, or Surroundings, Identifying Objects, Actions, and Events
Collections
Scrutiny and findings
Last revised
31 October 2026

Sources

  1. Evaluation report, by an evaluator that the makers or users commissioned.

    Nelson, S. Midterm Evaluation Completion, Liberian Electoral Support Project (LESP): Final Report. Independent evaluation commissioned by UNDP Liberia, 9 April 2025. Published in the UNDP and UN Evaluation Group repositories.

    The PBF peaceful electoral environment project contributed to this monitoring effort by integrating a digital application using artificial intelligence (AI) and an algorithm to automate the capturing of hate speech on radio platforms, which was integrated with the iVerify platform.
    This expanded the scope of its monitoring and type of information collected.

Details

AI system

Workflow

A Peacebuilding Fund project integrated an AI application for capturing hate speech on radio with iVerify. Local Voices Liberia ran iVerify for the 2023 elections with a USD 45,360 grant. The National Elections Commission worked with iVerify to answer disinformation in real time.

Follow-up

Conditions for replication

A trusted national group must run the platform. Fact-checks must come quickly enough to defuse viral claims.

Entry details

Sector

Electoral integrity / hate speech monitoring.

Purpose

An unnamed developer built the application for a Peacebuilding Fund project to automate the capture of hate speech on Liberian radio and feed it into iVerify.

Not yet checked: model, release, provider, role, configuration, inputs and outputs, autonomy, human oversight, AI contribution, beneficiaries, reach, distribution and access, duration, every measurement question, every money question, ownership and control, dependencies, cross-border connections, geopolitical implications, replication attempts, availability, institutional decision, grounds, action and result, success criterion, every evidence question, observed or intended, alternative assessments, related entries, other identifiers, category mappings.

Cite this record

Peter H. Vartanian. (2026). AI captures hate speech on radio for Liberia's iVerify fact-checkers (AIBD-0700). Artificial Intelligence Benefits Database, edition of 31 October 2026. https://petervartanian.xyz/aibd/records/AIBD-0700.html (archived at https://doi.org/10.7910/DVN/AADSII, version 4.0)

BibTeX Data Field definitions