Sentiment-adjusted-by-demographics-SAD-Index

• Background: Social media offers a unique lens to observe users’ emotions and subjective feelings toward critical events or topics and has been widely used to investigate public sentiment during crises. However, social media use varies across demographic groups, with younger people being more inclined to use social media than the older population. This digital divide could lead to biases in data representativeness, causing a persistent challenge in research based on social media data. The dataset, Sentiment Adjusted by Demographics (SAD) index, provides an adjusted measurement of public sentiment towards COVID-19 using Twitter data through post-stratification method.

• Post-stratification method: Feel free to download and try the code example for the post-stratification method named "CodeExample_post-stratification method.py". The corresponding data example for this code is available as "Data_example.xlsx".

• The SAD dataset: The SAD index data is publicly available and encompasses daily, weekly, and monthly SAD indexes at the state level in the U.S. for the years 2020 and 2021, with file names "SAD_state_daily.xlsx", "SAD_state_weekly.xlsx", and "SAD_monthly_weekly.xlsx" respectively.

• NaN Values: NaN values in the dataset indicate the absence of COVID-19-related tweets posted in the corresponding state and time period.

• For more details: For more comprehensive details, kindly refer to the paper titled "Sensing the Pulse of the Pandemic: Geovisualizing the Demographic Disparities of Public Sentiment toward COVID-19 through Social Media".

• Citation: If you utilize this dataset, kindly cite the aforementioned paper.