avaapm/ecir2021

Tweet dataset utilized in ECIR 2021 Paper: Tweet Length Matters: A Comparative Analysis on Topic Detection in Microblogs.

Tweet Length Matters: A Comparative Analysis on Topic Detection in Microblogs

Published tweet dataset used in Tweet Length Matters: A Comparative Analysis on Topic Detection in Microblogs includes tweet id and corresponding topic number. Topic numbers encoded as follows:

Topic	Topic Number
BLM Movement	0
Covid-19	1
K-Pop	2
Bollywood	3
Gaming	4
U.S. Politics	5
Out-of-Topic	6

In total, there are 354,310 tweet instances.

Citation

If you make use of these tools, please cite following paper.

@inproceedings{DBLP:conf/ecir/SahinucT21,
  author = {Furkan {\c{S}}ahinu{\c{c}} and Cagri Toraman},
  title = {Tweet Length Matters: {A} Comparative Analysis on Topic Detection in Microblogs},
  booktitle = {Advances in Information Retrieval - 43rd European Conference on {IR} Research, {ECIR} 2021, Virtual Event, March 28 - April 1, 2021, Proceedings, Part {II}},
  series = {Lecture Notes in Computer Science},
  volume = {12657},
  pages = {471--478},
  publisher = {Springer},
  year = {2021},
  url = {https://doi.org/10.1007/978-3-030-72240-1\_50},
  doi = {10.1007/978-3-030-72240-1\_50},
}