electricsheepafrica/africa-covid19-impacts-and-vaccine-acceptance-in-sub-saharan-africa

---
annotations_creators:
- no-annotation
language_creators:
- found
language:
- en
license: cc-by-4.0
multilinguality:
- monolingual
size_categories:
- 1K<n<10K
source_datasets:
- original
task_categories:
- tabular-classification
- tabular-regression
- other
task_ids: []
tags:
- africa
- humanitarian
- hdx
- electric-sheep-africa
- covid-19
- demographics
- disease
- economics
- geodata
- health
- socioeconomics
- vaccination-immunization
- civ
- cod
- ken
- moz
- nga
pretty_name: "COVID19 Impacts and Vaccine Acceptance in sub-Saharan Africa"
dataset_info:
splits:
- name: train
num_examples: 2399
- name: test
num_examples: 599
---

# COVID19 Impacts and Vaccine Acceptance in sub-Saharan Africa

**Publisher:** Mobile Accord, Inc. (GeoPoll) · **Source:** [HDX](https://data.humdata.org/dataset/covid19-impacts-and-vaccine-acceptance-in-sub-saharan-africa) · **License:** `cc-by` · **Updated:** 2025-04-10

---

## Abstract

This study was conducted by SMS in late November in Côte D'Ivoire, DRC, Kenya, Mozambique, Nigeria, and South Africa. Topics covered include the ongoing impacts of COVID-19 on finances, physical and mental health, and spending on goods. Additionally, the study covers perceptions of vaccine safety and effectiveness and willingness to take a COVID-19 vaccine. Sample size of 500/country, nationally representative by age, gender, and location (ADM1). To request sub-national data please contact [e-mail]

Each row in this dataset represents country-level aggregates. Data was last updated on HDX on 2025-04-10. Geographic scope: **CIV, COD, KEN, MOZ, NGA, ZAF**.

*Curated into ML-ready Parquet format by [Electric Sheep Africa](https://huggingface.co/electricsheepafrica).*

---

## Dataset Characteristics

| | |
|---|---|
| **Domain** | Public health |
| **Unit of observation** | Country-level aggregates |
| **Rows (total)** | 2,999 |
| **Columns** | 28 (1 numeric, 27 categorical, 0 datetime) |
| **Train split** | 2,399 rows |
| **Test split** | 599 rows |
| **Geographic scope** | CIV, COD, KEN, MOZ, NGA, ZAF |
| **Publisher** | Mobile Accord, Inc. (GeoPoll) |
| **HDX last updated** | 2025-04-10 |

---

## Variables

**Geographic** — `country` (Cote D'Ivoire, Mozambique, DRC), `physical_health` (About the same, A little better, A little worse), `concern_over_expenses`, `country_economy`, `mobile_money_usage` and 4 others.

**Demographic** — `age_group` (15 - 25, 36+, 26 - 35), `gender` (Female, Male), `personal_finances`.

**Outcome / Measurement** — `income_since_june` (Decreased a lot, Decreased a bit, No change).

**Identifier / Metadata** — `covid_vaccine`, `covid_vaccine_concern`, `esa_source`, `esa_processed`.

**Other** — `routine_change` (A great deal, Very little, Quite a bit), `return_to_normal` (Very little, Quite a bit, Somewhat), `return_to_normal_prediction` (First half of 2021, I have already, Second half of 2021), `emotional_health` (A little worse, About the same, A little better), `biggest_challenge` (Finances, Staying home, Emotional wellbeing) and 6 others.

---

## Quick Start

```python
from datasets import load_dataset

ds = load_dataset("electricsheepafrica/africa-covid19-impacts-and-vaccine-acceptance-in-sub-saharan-africa")
train = ds["train"].to_pandas()
test = ds["test"].to_pandas()

print(train.shape)
train.head()
```

---

## Schema

| Column | Type | Null % | Range / Sample Values |
|---|---|---|---|
| `country` | object | 0.0% | Cote D'Ivoire, Mozambique, DRC |
| `age_group` | object | 0.0% | 15 - 25, 36+, 26 - 35 |
| `gender` | object | 0.0% | Female, Male |
| `routine_change` | object | 0.0% | A great deal, Very little, Quite a bit |
| `return_to_normal` | object | 0.0% | Very little, Quite a bit, Somewhat |
| `return_to_normal_prediction` | object | 0.0% | First half of 2021, I have already, Second half of 2021 |
| `physical_health` | object | 0.0% | About the same, A little better, A little worse |
| `emotional_health` | object | 0.0% | A little worse, About the same, A little better |
| `biggest_challenge` | object | 0.0% | Finances, Staying home, Emotional wellbeing |
| `trust_in_information` | int64 | 0.0% | 1.0 – 5.0 (mean 3.6612) |
| `income_since_june` | object | 0.0% | Decreased a lot, Decreased a bit, No change |
| `concern_over_expenses` | object | 0.0% | |
| `economic_impact_length` | object | 0.0% | |
| `country_economy` | object | 0.0% | |
| `personal_finances` | object | 0.0% | |
| `spending_essentials` | object | 0.0% | |
| `spending_nonessentials` | object | 0.0% | |
| `online_shopping` | object | 0.0% | |
| `mobile_money_usage` | object | 0.0% | |
| `holiday_spending` | object | 0.0% | |
| `vaccine_safety` | object | 0.0% | |
| `vaccine_effectiveness` | object | 0.0% | |
| `covid_vaccine` | object | 0.0% | |
| `covid_vaccine_concern` | object | 0.0% | |
| `vaccine_availability` | object | 0.0% | |
| `vaccine_delivery` | object | 0.0% | |
| `esa_source` | object | 0.0% | |
| `esa_processed` | object | 0.0% | |

---

## Numeric Summary

| Column | Min | Max | Mean | Median |
|---|---|---|---|---|
| `trust_in_information` | 1.0 | 5.0 | 3.6612 | 5.0 |

---

## Curation

Raw data was downloaded from HDX via the CKAN API and converted to Parquet. Column names were lowercased and standardised to snake_case. Common missing-value markers (`N/A`, `null`, `none`, `-`, `unknown`, `no data`, `#N/A`) were unified to `NaN`. 2 column(s) with >80% missing values were removed: `otherchallenge`, `concernother`. 1 exact duplicate rows were removed. The dataset was split 80/20 into train and test partitions using a fixed random seed (42) and saved as Snappy-compressed Parquet.

---

## Limitations

- Data originates from Mobile Accord, Inc. (GeoPoll) and has not been independently validated by ESA.
- Automated cleaning cannot correct for misreported values, definitional inconsistencies, or sampling bias in the original collection.
- This dataset spans 6 countries; geographic and methodological inconsistencies across national boundaries may affect cross-country comparability.
- Refer to the [original HDX dataset page](https://data.humdata.org/dataset/covid19-impacts-and-vaccine-acceptance-in-sub-saharan-africa) for the publisher's own methodology notes and caveats.

---

## Citation

```bibtex
@dataset{hdx_africa_covid19_impacts_and_vaccine_acceptance_in_sub_saharan_africa,
title = {COVID19 Impacts and Vaccine Acceptance in sub-Saharan Africa},
author = {Mobile Accord, Inc. (GeoPoll)},
year = {2025},
url = {https://data.humdata.org/dataset/covid19-impacts-and-vaccine-acceptance-in-sub-saharan-africa},
note = {Repackaged for machine learning by Electric Sheep Africa (https://huggingface.co/electricsheepafrica)}
}
```

---

*[Electric Sheep Africa](https://huggingface.co/electricsheepafrica) — Africa's ML dataset infrastructure. Lagos, Nigeria.*