electricsheepafrica/africa-coronavirus-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
task_ids: []
tags:
- africa
- humanitarian
- hdx
- electric-sheep-africa
- covid-19
- epidemics-outbreaks
- health
- ken
- nga
- zaf
pretty_name: "Community knowledge and perceptions of Coronavirus COVID-19 in Sub-Saharan Africa"
dataset_info:
splits:
- name: train
num_examples: 1073
- name: test
num_examples: 268
---

# Community knowledge and perceptions of Coronavirus COVID-19 in Sub-Saharan Africa

**Publisher:** Mobile Accord, Inc. (GeoPoll) · **Source:** [HDX](https://data.humdata.org/dataset/coronavirus-in-sub-saharan-africa) · **License:** `cc-by` · **Updated:** 2025-04-09

---

## Abstract

This data is from GeoPoll's study on knowledge and perceptions of the recent coronavirus outbreak in South Africa, Kenya, and Nigeria.

Each row in this dataset represents country-level aggregates. Data was last updated on HDX on 2025-04-09. Geographic scope: **KEN, NGA, ZAF**.

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

---

## Dataset Characteristics

| | |
|---|---|
| **Domain** | Food security and nutrition |
| **Unit of observation** | Country-level aggregates |
| **Rows (total)** | 1,342 |
| **Columns** | 51 (8 numeric, 43 categorical, 0 datetime) |
| **Train split** | 1,073 rows |
| **Test split** | 268 rows |
| **Geographic scope** | KEN, NGA, ZAF |
| **Publisher** | Mobile Accord, Inc. (GeoPoll) |
| **HDX last updated** | 2025-04-09 |

---

## Variables

**Geographic** — `country` (Kenya, Nigeria, South Africa), `symptoms` (Yes, No, Not sure), `symptoms2_fever` (Yes, No), `symptoms2_bleeding` (No, Yes), `symptoms2_vomiting` (No, Yes) and 10 others.

**Demographic** — `agegroup` (25-34, 15-24, 35+), `gender` (Male, Female), `modetransmission_being_near_infected_person`, `modetransmission_touching_an_infected_person`, `informationsources_government_messages`.

**Outcome / Measurement** — `cases` (Yes - There are confirmed cases, No - There are no confirmed cases, Not sure).

**Identifier / Metadata** — `preventativemeasures_avoid_public_transport`, `govtconfidence` (range 1.0–5.0), `globalconfidence` (range 1.0–5.0), `informationsources_newspapers`, `informationsources_tv` and 5 others.

**Other** — `adm_1` (Gauteng, KwaZulu-Natal, Nairobi), `awareness` (Yes, No), `levelconcern` (range 1.0–5.0), `broadcast2` (range 1.0–1.0), `modetransmission_air` and 15 others.

---

## Quick Start

```python
from datasets import load_dataset

ds = load_dataset("electricsheepafrica/africa-coronavirus-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% | Kenya, Nigeria, South Africa |
| `agegroup` | object | 0.0% | 25-34, 15-24, 35+ |
| `gender` | object | 0.0% | Male, Female |
| `adm_1` | object | 0.0% | Gauteng, KwaZulu-Natal, Nairobi |
| `awareness` | object | 0.0% | Yes, No |
| `cases` | object | 5.0% | Yes - There are confirmed cases, No - There are no confirmed cases, Not sure |
| `levelconcern` | float64 | 5.0% | 1.0 – 5.0 (mean 4.2957) |
| `symptoms` | object | 5.0% | Yes, No, Not sure |
| `symptoms2_fever` | object | 29.0% | Yes, No |
| `symptoms2_bleeding` | object | 29.0% | No, Yes |
| `symptoms2_vomiting` | object | 29.0% | No, Yes |
| `symptoms2_cough` | object | 29.0% | |
| `symptoms2_shortness_of_breath` | object | 29.0% | |
| `symptoms2_diarrhoea` | object | 29.0% | |
| `symptoms2_none_of_the_above` | object | 29.0% | |
| `broadcast2` | float64 | 5.0% | 1.0 – 1.0 (mean 1.0) |
| `modetransmission_being_near_infected_person` | object | 5.0% | |
| `modetransmission_touching_an_infected_person` | object | 5.0% | |
| `modetransmission_air` | object | 5.0% | |
| `modetransmission_drinking_water` | object | 5.0% | |
| `modetransmission_surfaces` | object | 5.0% | |
| `modetransmission_other` | object | 5.0% | |
| `modetransmission_don_t_know` | object | 5.0% | |
| `riskawareness` | object | 5.0% | |
| `placegreatestrisk` | object | 33.7% | |
| `virusprevention` | object | 5.0% | |
| `preventativemeasures_avoid_public_places` | object | 31.0% | |
| `preventativemeasures_avoid_public_transport` | object | 31.0% | |
| `preventativemeasures_avoid_physical_contact` | object | 31.0% | |
| `preventativemeasures_increase_hygiene` | object | 31.0% | |
| `broadcast3` | float64 | 5.0% | 1.0 – 1.0 (mean 1.0) |
| `govtconfidence` | float64 | 5.0% | 1.0 – 5.0 (mean 2.9898) |
| `globalconfidence` | float64 | 5.0% | 1.0 – 5.0 (mean 3.342) |
| `financial` | object | 5.0% | |
| `foodavailability` | object | 5.0% | |
| `concerns` | object | 5.0% | |
| `informationsources_newspapers` | object | 5.0% | |
| `informationsources_tv` | object | 5.0% | |
| `informationsources_radio` | object | 5.0% | |
| `informationsources_social_media` | object | 5.0% | |
| `informationsources_friends_family` | object | 5.0% | |
| `informationsources_government_messages` | object | 5.0% | |
| `whatsapp` | object | 5.0% | |
| `whatsappinformation` | object | 29.1% | |
| `mediacommunication` | float64 | 5.0% | 1.0 – 5.0 (mean 4.011) |
| `globalcommunication` | float64 | 5.0% | 1.0 – 5.0 (mean 4.2016) |
| `govtcommunication` | float64 | 5.0% | 1.0 – 5.0 (mean 3.8808) |
| `outsidehelp` | object | 5.0% | |
| `chineseworkers` | object | 5.0% | |
| `esa_source` | object | 0.0% | |
| `esa_processed` | object | 0.0% | |

---

## Numeric Summary

| Column | Min | Max | Mean | Median |
|---|---|---|---|---|
| `levelconcern` | 1.0 | 5.0 | 4.2957 | 5.0 |
| `broadcast2` | 1.0 | 1.0 | 1.0 | 1.0 |
| `broadcast3` | 1.0 | 1.0 | 1.0 | 1.0 |
| `govtconfidence` | 1.0 | 5.0 | 2.9898 | 3.0 |
| `globalconfidence` | 1.0 | 5.0 | 3.342 | 3.0 |
| `mediacommunication` | 1.0 | 5.0 | 4.011 | 5.0 |
| `globalcommunication` | 1.0 | 5.0 | 4.2016 | 5.0 |
| `govtcommunication` | 1.0 | 5.0 | 3.8808 | 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`. 8 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.
- The following columns have >20% missing values and should be treated with caution in modelling: `symptoms2_fever`, `symptoms2_bleeding`, `symptoms2_vomiting`, `symptoms2_cough`, `symptoms2_shortness_of_breath`, `symptoms2_diarrhoea`, `symptoms2_none_of_the_above`, `placegreatestrisk`....
- This dataset spans 3 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/coronavirus-in-sub-saharan-africa) for the publisher's own methodology notes and caveats.

---

## Citation

```bibtex
@dataset{hdx_africa_coronavirus_in_sub_saharan_africa,
title = {Community knowledge and perceptions of Coronavirus COVID-19 in Sub-Saharan Africa},
author = {Mobile Accord, Inc. (GeoPoll)},
year = {2025},
url = {https://data.humdata.org/dataset/coronavirus-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.*