Census-block-level-TSGI

<p> Harvard CGA Geotweet Census Archive is a subset of <a href="https://doi.org/10.7910/DVN/3NCMB6"> Harvard CGA Geotweet Archive v2.0 </a> enriched with nationwide census data. It contains the tweet and user identification records along with census variables and sentiment scores for more than 2 billion geo-tagged tweets from January 2012 to July 2023. The sentiment scores are derived from the BERT sentiment scores from the <a href=https://dataverse.harvard.edu/dataset.xhtml?persistentId=doi:10.7910/DVN/X2KJPC>Harvard CGA Geotweet Sentiment Archive</a>. This dataset is available to the academic community at large, unlike the <a href="https://doi.org/10.7910/DVN/3NCMB6">Harvard CGA Geotweet Archive v2.0 </a> which is under <a href="https://developer.twitter.com/en/developer-terms/agreement-and-policy">Twitter's redistribution policy</a> restriction for public sharing. It could serve as cross-validation data for publications that used data from <a href="https://doi.org/10.7910/DVN/3NCMB6">Harvard CGA Geotweet Archive v2.0 </a>.

<p>If you are interested in accessing this archive, please fill out our <a href="https://gis.harvard.edu/geotweet-request-form">Geotweet Request Form</a>. Before requesting or receiving Tweet IDs, requestors must agree to <a href="https://twitter.com/en/tos">Twitter's Terms of Service</a>, <a href="https://twitter.com/en/privacy">Twitter's Privacy Policy</a>, and <a href="https://developer.twitter.com/en/developer-terms/policy"> Twitter's Developer Policy </a>. Geotweets IDs data provided by CGA can only be used for not-for-profit research and academic purposes. Recipients may not share CGA provided Tweet IDs or content derived from them without written permission from the CGA.</p>

<p><strong>Citations:</strong></p>
<p>If you use the Geotweet Archive in your research please reference it: "<a href="https://doi.org/10.7910/DVN/KTRIJP">Harvard CGA Geotweet IDs Archive</a>".</p>

========================================================
<p>Schema of Geotweet Census Archive</p>

<p><strong>Field name____TYPE____Description</strong></p>

<p><strong>day</strong>----TEXT----The date of the tweet (YYYY-MM-DD)</p>

<p><strong>GEOID20</strong>----TEXT----Census block geoid</p>

<p><strong>tweet_count</strong>----INTEGER----Number of tweets in the census block</p>

<p><strong>user_count</strong>----INTEGER----Number of unique users in the census block</p>

<p><strong>avg_score</strong>----FLOAT----The average tweet sentiment score in the census block</p>

<p><strong>max_score</strong>----FLOAT----The maximum tweet sentiment score in the census block</p>

<p><strong>min_score</strong>----FLOAT----The minimum tweet sentiment score in the census block</p>

<p><strong>std_score</strong>----FLOAT----The standard deviation of tweet sentiment scores in the census block</p>

<p><strong>score_10q</strong>----FLOAT----The 10th quantile tweet sentiment score in the census block</p>

<p><strong>score_25q</strong>----FLOAT----The 25th quantile tweet sentiment score in the census block</p>

<p><strong>score_50q</strong>----FLOAT----The 50th quantile (median) tweet sentiment score in the census block</p>

<p><strong>score_75q</strong>----FLOAT----The 75th quantile tweet sentiment score in the census block</p>

<p><strong>score_90q</strong>----FLOAT----The 90th quantile tweet sentiment score in the census block</p>