MigrationsKB: A Knowledge Base of Migration related annotated Tweets

MigrationsKB(MGKB) is a public Knowledge Base of anonymized Migration related annotated tweets. The MGKB currently contains over 200 thousand tweets, spanning over 9 years (January 2013 to July 2021), filtered with 11 European countries of the United Kingdom, Germany, Spain, Poland, France, Sweden, Austria, Hungary, Switzerland, Netherlands and Italy. Metadata information about the tweets, such as Geo information (place name, coordinates, country code). MGKB contains entities, sentiments, hate speeches, topics, hashtags, encrypted user mentions in RDF format. The schema of MGKB is an extension of TweetsKB for migrations related information. Moreover, to associate and represent the potential economic and social factors driving the migration flows such as eurostat, statista, etc. FIBO ontology was used. The extracted economic indicators, such as GDP Growth Rate, are connected with each Tweet in RDF using geographical and temporal dimensions. The user IDs and the tweet texts are encrypted for privacy purposes, while the tweet IDs are preserved.

For this version, the MGKB is delivered as a whole and separately by year. The extracted entities and topic words are also published.

Online SPARQL endpoint  https://mgkb.fiz-karlsruhe.de/sparql/

More information please refer to the website https://migrationskb.github.io/MGKB/.

Please contact Yiyi Chen (yiyi.chen@partner.kit.edu) for pretrained models (sentiment analysis/hate speech detection/ETM model) if necessary.