Harvard CGA Geotweet Sentiment Archive

<p> Harvard CGA Geotweet Sentiment Archive is a subset of <a href="https://doi.org/10.7910/DVN/3NCMB6"> Harvard CGA Geotweet Archive v2.0 </a> enriched with a sentiment score. It contains the tweet identification records along with a sentiment score based on tweet text for about 4.3 billion geo-tagged tweets since 2019. This sentiment score was calculated using <a href="https://nlp.stanford.edu/seminar/details/jdevlin.pdf">Bidirectional Encoder Representations from Transformers</a>. More information about this methodology can be found in our Nature Paper on <a href="https://www.nature.com/articles/s41597-023-02572-7">Twitter Sentiment Geographical Index</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>message_id</strong>----TEXT----Tweet ID</p>

<p><strong>score</strong> ----FLOAT----BERT sentiment score</p>