electricsheepafrica/africa-climate-change-opinion-survey

---
annotations_creators:
- no-annotation
language_creators:
- found
language:
- en
license: other
multilinguality:
- monolingual
size_categories:
- 1K<n<10K
source_datasets:
- original
task_categories:
- tabular-classification
- tabular-regression
task_ids: []
tags:
- africa
- humanitarian
- hdx
- electric-sheep-africa
- climate-weather
- environment
- alb
- dza
- asm
- ago
- aia
pretty_name: "Climate Change Opinion Survey"
dataset_info:
splits:
- name: train
num_examples: 4112
- name: test
num_examples: 1028
---

# Climate Change Opinion Survey

**Publisher:** AI for Good at Meta · **Source:** [HDX](https://data.humdata.org/dataset/climate-change-opinion-survey) · **License:** `other-pd-nr` · **Updated:** 2026-03-26

---

## Abstract

In partnership with Yale, Meta launched a climate change opinion survey that explores public climate change knowledge, attitudes, policy preferences, and behaviors. 2023 aggregated survey responses now available.

The 2022 survey includes respondents from nearly 200 countries and territories. We are sharing country level data from this survey, providing policymakers, research institutions, and nonprofits with an international view of public climate change opinion.

For more information please see https://ai.meta.com/ai-for-good/datasets/climate-change-opinion-survey/

If you're interested in becoming a research partner and accessing record level data, please email [e-mail].

Each row in this dataset represents first-level administrative unit observations. Data was last updated on HDX on 2026-03-26. Geographic scope: **ALB, DZA, ASM, AGO, AIA, ATG, ARG, ARM, and 185 others**.

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

---

## Dataset Characteristics

| | |
|---|---|
| **Domain** | Climate and environment |
| **Unit of observation** | First-level administrative unit observations |
| **Rows (total)** | 5,140 |
| **Columns** | 11 (4 numeric, 7 categorical, 0 datetime) |
| **Train split** | 4,112 rows |
| **Test split** | 1,028 rows |
| **Geographic scope** | ALB, DZA, ASM, AGO, AIA, ATG, ARG, ARM, and 185 others |
| **Publisher** | AI for Good at Meta |
| **HDX last updated** | 2026-03-26 |

---

## Variables

**Geographic** — `region` (Europe, Asia, Southwest Asia & North Africa), `country_code` (hk, jp, no), `country` (Hong Kong, Japan, Norway).

**Outcome / Measurement** — `pct` (range 0.0–86.5244).

**Identifier / Metadata** — `esa_source` (HDX), `esa_processed` (2026-04-04).

**Other** — `response` (I have not done this, I have done this, Not applicable), `freq` (range 0.0–2155.7138), `n` (range 12.4363–2836.0), `prop` (range 0.0–0.8652), `variable` (barriers_heatpump_haventadopted, barriers_ev_haventadopted, barriers_solar_haventadopted).

---

## Quick Start

```python
from datasets import load_dataset

ds = load_dataset("electricsheepafrica/africa-climate-change-opinion-survey")
train = ds["train"].to_pandas()
test = ds["test"].to_pandas()

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

---

## Schema

| Column | Type | Null % | Range / Sample Values |
|---|---|---|---|
| `region` | object | 0.0% | Europe, Asia, Southwest Asia & North Africa |
| `country_code` | object | 0.0% | hk, jp, no |
| `country` | object | 0.0% | Hong Kong, Japan, Norway |
| `response` | object | 0.0% | I have not done this, I have done this, Not applicable |
| `freq` | float64 | 0.0% | 0.0 – 2155.7138 (mean 100.6589) |
| `n` | float64 | 0.0% | 12.4363 – 2836.0 (mean 608.2886) |
| `prop` | float64 | 0.0% | 0.0 – 0.8652 (mean 0.1557) |
| `pct` | float64 | 0.0% | 0.0 – 86.5244 (mean 15.5693) |
| `variable` | object | 0.0% | barriers_heatpump_haventadopted, barriers_ev_haventadopted, barriers_solar_haventadopted |
| `esa_source` | object | 0.0% | HDX |
| `esa_processed` | object | 0.0% | 2026-04-04 |

---

## Numeric Summary

| Column | Min | Max | Mean | Median |
|---|---|---|---|---|
| `freq` | 0.0 | 2155.7138 | 100.6589 | 39.2444 |
| `n` | 12.4363 | 2836.0 | 608.2886 | 551.0772 |
| `prop` | 0.0 | 0.8652 | 0.1557 | 0.0955 |
| `pct` | 0.0 | 86.5244 | 15.5693 | 9.5545 |

---

## 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`. 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 AI for Good at Meta 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 193 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/climate-change-opinion-survey) for the publisher's own methodology notes and caveats.

---

## Citation

```bibtex
@dataset{hdx_africa_climate_change_opinion_survey,
title = {Climate Change Opinion Survey},
author = {AI for Good at Meta},
year = {2026},
url = {https://data.humdata.org/dataset/climate-change-opinion-survey},
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.*

annotations_creators:
- 无注释（no-annotation）
language_creators:
- 现有资源获取（found）
language:
- 英语（en）
license:
- 其他（other）
multilinguality:
- 单语言（monolingual）
size_categories:
- 1000<n<10000
source_datasets:
- 原始数据集（original）
task_categories:
- 表格分类（tabular-classification）
- 表格回归（tabular-regression）
task_ids: []
tags:
- 非洲（africa）
- 人道主义（humanitarian）
- 人道主义数据交换（Humanitarian Data Exchange，HDX）
- electric-sheep-africa
- 气候与天气（climate-weather）
- 环境（environment）
- ALB（阿尔巴尼亚）
- DZA（阿尔及利亚）
- ASM（美属萨摩亚）
- AGO（安哥拉）
- AIA（安圭拉）
pretty_name: "气候变化意见调查（Climate Change Opinion Survey）"
dataset_info:
splits:
- name: 训练集（train）
num_examples: 4112
- name: 测试集（test）
num_examples: 1028

# 气候变化意见调查（Climate Change Opinion Survey）

**发布方**：Meta旗下AI向善项目（AI for Good at Meta） · **来源**：[人道主义数据交换（Humanitarian Data Exchange，HDX）](https://data.humdata.org/dataset/climate-change-opinion-survey) · **授权协议**：`other-pd-nr` · **更新时间**：2026-03-26

---

## 摘要

本数据集与耶鲁大学合作，由Meta发起一项气候变化意见调查，旨在探究公众对气候变化的认知、态度、政策偏好与行为习惯。2023年的汇总调查结果现已公开。

2022年的调查覆盖了近200个国家与地区的受访者。本数据集分享了该调查的国家级层面数据，为政策制定者、研究机构与非营利组织提供全球公众气候变化意见的全景视角。

如需了解更多信息，请访问 https://ai.meta.com/ai-for-good/datasets/climate-change-opinion-survey/

若您有意成为研究合作伙伴并获取单条记录级别的数据，请发送邮件至[e-mail]。

本数据集的每一行均代表一级行政单元的观测数据。本数据集最后一次在人道主义数据交换（HDX）平台更新的时间为2026年3月26日。地理覆盖范围：**ALB、DZA、ASM、AGO、AIA、ATG、ARG、ARM及另外185个国家/地区**。

*本数据集由[Electric Sheep Africa](https://huggingface.co/electricsheepafrica)整理为适配机器学习的Parquet格式（Parquet）。*

---

## 数据集特征

| | |
|---|---|
| **领域** | 气候与环境 |
| **观测单元** | 一级行政单元观测数据 |
| **总样本行数** | 5140 |
| **列数** | 11列（4列数值型，7列分类型，0列日期型） |
| **训练集划分** | 4112行 |
| **测试集划分** | 1028行 |
| **地理覆盖范围** | ALB、DZA、ASM、AGO、AIA、ATG、ARG、ARM及另外185个国家/地区 |
| **发布方** | Meta旗下AI向善项目 |
| **HDX平台最后更新时间** | 2026-03-26 |

---

## 变量说明

**地理类变量**：`region`（区域，可选值：欧洲、亚洲、西亚与北非）、`country_code`（国家代码，示例值：hk、jp、no）、`country`（国家/地区名称，示例值：中国香港、日本、挪威）。

**结果/测量类变量**：`pct`（百分比，取值范围：0.0~86.5244）。

**标识符/元数据类变量**：`esa_source`（数据来源，值为HDX）、`esa_processed`（数据处理时间，值为2026-04-04）。

**其他变量**：`response`（调查回复选项，可选值：我未采取该行动、我已采取该行动、不适用）、`freq`（频率值，取值范围：0.0~2155.7138）、`n`（样本量，取值范围：12.4363~2836.0）、`prop`（占比，取值范围：0.0~0.8652）、`variable`（变量名称，示例值：barriers_heatpump_haventadopted、barriers_ev_haventadopted、barriers_solar_haventadopted）。

---

## 快速上手

python
from datasets import load_dataset

ds = load_dataset("electricsheepafrica/africa-climate-change-opinion-survey")
train = ds["train"].to_pandas()
test = ds["test"].to_pandas()

print(train.shape)
train.head()

---

## 数据模式

| 列名 | 数据类型 | 空值占比 | 取值范围/示例值 |
|---|---|---|---|
| `region` | 字符串型 | 0.0% | 欧洲、亚洲、西亚与北非 |
| `country_code` | 字符串型 | 0.0% | hk、jp、no |
| `country` | 字符串型 | 0.0% | 中国香港、日本、挪威 |
| `response` | 字符串型 | 0.0% | 我未采取该行动、我已采取该行动、不适用 |
| `freq` | 64位浮点型 | 0.0% | 0.0~2155.7138（均值：100.6589） |
| `n` | 64位浮点型 | 0.0% | 12.4363~2836.0（均值：608.2886） |
| `prop` | 64位浮点型 | 0.0% | 0.0~0.8652（均值：0.1557） |
| `pct` | 64位浮点型 | 0.0% | 0.0~86.5244（均值：15.5693） |
| `variable` | 字符串型 | 0.0% | barriers_heatpump_haventadopted、barriers_ev_haventadopted、barriers_solar_haventadopted |
| `esa_source` | 字符串型 | 0.0% | HDX |
| `esa_processed` | 字符串型 | 0.0% | 2026-04-04 |

---

## 数值型变量统计摘要

| 列名 | 最小值 | 最大值 | 均值 | 中位数 |
|---|---|---|---|---|
| `freq` | 0.0 | 2155.7138 | 100.6589 | 39.2444 |
| `n` | 12.4363 | 2836.0 | 608.2886 | 551.0772 |
| `prop` | 0.0 | 0.8652 | 0.1557 | 0.0955 |
| `pct` | 0.0 | 86.5244 | 15.5693 | 9.5545 |

---

## 数据整理流程

原始数据通过康卡恩综合知识存档网络应用程序编程接口（Comprehensive Knowledge Archive Network API，CKAN API）从HDX平台下载，并转换为Parquet格式（Parquet）。列名统一转换为小写并标准化为蛇形命名法（snake_case）。常见的缺失值标记（`N/A`、`null`、`none`、`-`、`unknown`、`no data`、`#N/A`）被统一替换为`NaN`。本数据集以固定随机种子（42）按照80/20的比例划分为训练集与测试集，并以Snappy压缩的Parquet格式存储。

---

## 数据集局限性

- 本数据集源自Meta旗下AI向善项目，尚未由Electric Sheep Africa（ESA）进行独立验证。
- 自动化数据清洗无法修正原始调查中存在的错报值、定义不一致或抽样偏差问题。
- 本数据集覆盖193个国家；不同国家/地区的地理与方法学差异可能影响跨国数据的可比性。
- 如需了解发布方提供的方法学说明与免责声明，请参阅[HDX平台原始数据集页面](https://data.humdata.org/dataset/climate-change-opinion-survey)。

---

## 引用格式

bibtex
@dataset{hdx_africa_climate_change_opinion_survey,
title = {Climate Change Opinion Survey},
author = {AI for Good at Meta},
year = {2026},
url = {https://data.humdata.org/dataset/climate-change-opinion-survey},
note = {Repackaged for machine learning by Electric Sheep Africa (https://huggingface.co/electricsheepafrica)}
}

---

*[Electric Sheep Africa](https://huggingface.co/electricsheepafrica) — 非洲机器学习数据集基础设施服务商，尼日利亚拉各斯。*