CED Sentiment Data

1.Introduction

This dashboard is aimed at providing a comprehensive data source that features the most important indicators related to the Chinese economy. The dashboard is divided into three sections, namely, sentiment data, high-frequency data, and low-frequency indicators. It will be updated on a monthly basis and the data can be downloaded directly from the webpage.

General context

The China Horizons project aims to contribute towards a better understanding of the Chinese economy and its impact on the global economy. The project seeks to achieve this goal by providing timely, accurate, and comprehensive data and analysis. The development of the dashboard is one of the tasks associated with this project, and it is expected to help researchers, policymakers, and other stakeholders to keep track of economic changes in China.

2.Methodological approach

China’s Economy Data (CED) Platform

The China’s Economy Data (CED) Platform is a web application that has been developed using the Python programming language. This platform is available online and provides users with access to a wide range of data related to the Chinese economy.

The CED platform has been designed to be user-friendly and intuitive, with a simple interface that makes it easy for users to navigate and access the data they need. It is a comprehensive platform that features data related to various aspects of the Chinese economy, such as consumer and investment sentiment, inflation, employment among others.

The platform is built on a robust database that is regularly updated with the latest economic data from various sources, including government agencies and international organizations. This ensures that users have access to accurate and up-to-date information.

Sentiment Data

The aim of this section is to collect  relevant data and analyze it in order to gauge the overall sentiment of consumers and investors towards the Chinese economy.

The consumer sentiment data has been derived by tracking user conversations on social media platform Weibo and analyzing them using the SNOWNLP sentiment analysis algorithm. This data has been collected across three main consumer categories - food, automobile, and fashion industry - and has been cleaned to remove irrelevant messages, ads, and noise. The sentiment has been calculated using the SnowNLP algorithm.

The investment sentiment data, on the other hand, has been calculated based on news articles published in the Chinese media and analyzed using the https://huggingface.co/uer/roberta-base-finetuned-jd-binary-chinese algorithm.

In addition to these, the China Horizons dashboard also includes the China Economic Policy Uncertainty Index, which has been calculated following the methodology presented by Hong-Kong Baptist University (https://cbade.hkbu.edu.hk/epu-mainland-china/). This index provides an indication of the level of uncertainty in the Chinese economy, and is an important indicator for investors and policymakers

High-frequency Data

In this section, we collect and process fast-changing publicly available data from different data sources such as National Bureau of Statistics, The People's Bank of China China Foreign Exchange Trade System

Low-frequency Data

Similarly to the High Frequency data we collect  the data that is publish quarterly or less often, and we transform it to the format required by the platform. Among low-frequency data sources, we can find:

Chinese Ministry of Financel, State Administration of Foreign Exchange & National Bureau of Statistics,The People's Bank of China, China Ministry of Human Resources and Social Security, CEIC.

3.Summary of activities and/or research findings

China’s Economy Data (CED) Platform

 platform that includes a dashboard, a database

Data Update Pipeline

a pipeline that ingests and processes the input data and updates the dashboard

4.Conclusions and future steps

The platform gives a clear vision of key economic indicators in China. It will be updated once a month.

5.Bibliographical references (if applicable)

Huang, Y., and Luk, P. (2019). “Measuring Economic Policy Uncertainty in China.” China Economic Review.

Zhou, Bingqian, Yuhan Zhu and Xiabing Mao. “Sentiment Analysis on Power Rationing Micro Blog Comments Based on SnowNLP-SVM-LDA Model.” Highlights in Science, Engineering and Technology (2022): n. pag.