Publicly available social media archives facilitate research in a variety of fields, such as data science, sociology or the digital humanities, where Twitter has emerged as one of the most prominent sources. However, obtaining, archiving and annotating large amounts of tweets is costly. In this paper, we describe TweetsKB, a publicly available corpus of currently more than 1.5 billion tweets, spanning almost 5 years (Jan'13-Nov'17). Metadata information about the tweets as well as extracted entities, hashtags, user mentions and sentiment information are exposed using established RDF/S vocabularies. Next to a description of the extraction and annotation process, we present use cases to illustrate scenarios for entity-centric information exploration, data integration and knowledge discovery facilitated by TweetsKB.
%0 Conference Paper
%1 fafalios2018eswc
%A Fafalios, Pavlos
%A Iosifidis, Vasileios
%A Ntoutsi, Eirini
%A Dietze, Stefan
%B 15th Extended Semantic Web Conference (ESWC'18)
%D 2018
%I Springer
%K 2018 RDF alexandria entity_linking myown sentiment_analysis social_media social_media_archives twitter
%R https://doi.org/10.1007/978-3-319-93417-4_12
%T TweetsKB: A Public and Large-Scale RDF Corpus of Annotated Tweets
%U https://arxiv.org/pdf/1810.10308.pdf
%X Publicly available social media archives facilitate research in a variety of fields, such as data science, sociology or the digital humanities, where Twitter has emerged as one of the most prominent sources. However, obtaining, archiving and annotating large amounts of tweets is costly. In this paper, we describe TweetsKB, a publicly available corpus of currently more than 1.5 billion tweets, spanning almost 5 years (Jan'13-Nov'17). Metadata information about the tweets as well as extracted entities, hashtags, user mentions and sentiment information are exposed using established RDF/S vocabularies. Next to a description of the extraction and annotation process, we present use cases to illustrate scenarios for entity-centric information exploration, data integration and knowledge discovery facilitated by TweetsKB.
@inproceedings{fafalios2018eswc,
abstract = {Publicly available social media archives facilitate research in a variety of fields, such as data science, sociology or the digital humanities, where Twitter has emerged as one of the most prominent sources. However, obtaining, archiving and annotating large amounts of tweets is costly. In this paper, we describe TweetsKB, a publicly available corpus of currently more than 1.5 billion tweets, spanning almost 5 years (Jan'13-Nov'17). Metadata information about the tweets as well as extracted entities, hashtags, user mentions and sentiment information are exposed using established RDF/S vocabularies. Next to a description of the extraction and annotation process, we present use cases to illustrate scenarios for entity-centric information exploration, data integration and knowledge discovery facilitated by TweetsKB.},
added-at = {2018-04-17T17:24:22.000+0200},
author = {Fafalios, Pavlos and Iosifidis, Vasileios and Ntoutsi, Eirini and Dietze, Stefan},
biburl = {https://www.bibsonomy.org/bibtex/20095847f20bb14b1908af77ed7ec8f56/fafalios},
booktitle = {15th Extended Semantic Web Conference (ESWC'18)},
doi = {https://doi.org/10.1007/978-3-319-93417-4_12},
interhash = {eb5794090ca7fbdb1b156c9cde5c613b},
intrahash = {0095847f20bb14b1908af77ed7ec8f56},
keywords = {2018 RDF alexandria entity_linking myown sentiment_analysis social_media social_media_archives twitter},
publisher = {Springer},
timestamp = {2018-10-29T11:19:40.000+0100},
title = {TweetsKB: A Public and Large-Scale RDF Corpus of Annotated Tweets},
url = {https://arxiv.org/pdf/1810.10308.pdf},
year = 2018
}