AI analysis of complaint narratives yields trends for UNICEF programs

UNICEF's Evaluation Office found that AI analysis of feedback and complaint narratives by two UNICEF teams gave insights and trends that appeared specific enough for programs to use.

  • Not rated an organization

    The evaluator judged that one example report appeared usable by programs, and the report does not record any decision that drew on it.

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

Status
Reported benefit.
Evidence

foundstudiedreportedclaimed

An independent evaluation report supports the benefit.

The system’s part
Not isolated. The report says only that the teams started to use AI to identify patterns in large volumes of qualitative feedback. It names no tool or model and does not show that the system learns from data. The evaluator judged one output and did not compare it with manual analysis.
Not yet checked
LimitsCosts and harmsLearns from dataLater outcome

Download data Cite Suggest a correction

Benefit type
Improved Knowledge Discovery
System
AI analysis of feedback and complaint narratives used by UNICEF's GRM and SBC teams (unnamed tool)
Made by
Not named in the report
Used by
UNICEF's grievance redress mechanism (GRM) and social and behavior change (SBC) teams, in a country office that the passage does not name (the report's GRM and SBC examples are from UNICEF Afghanistan)
Where
Country office not named in the passage (the report's GRM and SBC examples are from Afghanistan)
Stage
In routine use
Date
, when the source was published
Kind
Benefit created
Broad benefit
Analyzing Data or Information, Processing Information
Collections
Scrutiny and findings
Last revised
1 November 2026

Sources

  1. Evaluation report, by authors with no tie to the system.

    UNICEF Evaluation Office. Evaluation of UNICEF's Accountability to Affected Populations: Evaluation report. Carried out by Itad. New York, March 2026. The evaluation covers 2020 to 2025.

    Both have started to use artificial intelligence (AI) to identify patterns in the large volumes of qualitative data that have been captured, relevant to each sector. The example report seen by the evaluator provided actionable insights and emerging trends that appeared detailed/specific enough to be usable by programmes.

Details

AI system

Workflow

The GRM and SBC teams captured the narrative text of feedback and complaint submissions. Both teams started to use AI to identify patterns in this qualitative data, relevant to each sector. The output was a report of insights and emerging trends for programs.

Follow-up

Conditions for replication

Feedback and complaints must be gathered at scale through a management information system. Programs must have the time and processes to act on what people say.

Entry details

Sector

Humanitarian accountability and community feedback.

Purpose

An unnamed developer built the AI tool to identify patterns in the large volumes of feedback and complaint narratives that UNICEF's GRM and SBC teams collect.

31 more questions 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 analysis of complaint narratives yields trends for UNICEF programs (AIBD-1165). Artificial Intelligence Benefits Database, edition of 1 November 2026. https://petervartanian.xyz/aibd/records/AIBD-1165.html (archived at https://doi.org/10.7910/DVN/AADSII, version 7.0)

BibTeX Data Field definitions