Details
| Original language | English |
|---|---|
| Title of host publication | WebSci 2019 |
| Subtitle of host publication | Proceedings of the 11th ACM Conference on Web Science |
| Pages | 135-136 |
| Number of pages | 2 |
| ISBN (electronic) | 9781450362023 |
| Publication status | Published - 26 Jun 2019 |
| Event | 11th ACM Conference on Web Science, WebSci 2019 - Boston, United States Duration: 30 Jun 2019 → 3 Jul 2019 |
Abstract
We present an efficient graph-based method for filtering tweets relevant to a given breaking news from large tweet streams. Unlike existing models that either require manual effort, strong supervision, and/or not scalable, our method can automatically and effectively filter incoming relevant tweets starting from just a small number of past relevant tweets. Extensive experiments on both synthetic and real datasets show that our proposed method significantly outperforms other methods in filtering the relevant tweets while being as fast as the most efficient state-of-The-Art method.
ASJC Scopus subject areas
- Computer Science(all)
- Computer Networks and Communications
Cite this
- Standard
- Harvard
- Apa
- Vancouver
- BibTeX
- RIS
WebSci 2019: Proceedings of the 11th ACM Conference on Web Science. 2019. p. 135-136.
Research output: Chapter in book/report/conference proceeding › Conference contribution › Research › peer review
}
TY - GEN
T1 - Efficient Tracking of Breaking News in Twitter
AU - Hoang, Tuan Anh
AU - Nguyen, Thi Huyen
AU - Nejdl, Wolfgang
PY - 2019/6/26
Y1 - 2019/6/26
N2 - We present an efficient graph-based method for filtering tweets relevant to a given breaking news from large tweet streams. Unlike existing models that either require manual effort, strong supervision, and/or not scalable, our method can automatically and effectively filter incoming relevant tweets starting from just a small number of past relevant tweets. Extensive experiments on both synthetic and real datasets show that our proposed method significantly outperforms other methods in filtering the relevant tweets while being as fast as the most efficient state-of-The-Art method.
AB - We present an efficient graph-based method for filtering tweets relevant to a given breaking news from large tweet streams. Unlike existing models that either require manual effort, strong supervision, and/or not scalable, our method can automatically and effectively filter incoming relevant tweets starting from just a small number of past relevant tweets. Extensive experiments on both synthetic and real datasets show that our proposed method significantly outperforms other methods in filtering the relevant tweets while being as fast as the most efficient state-of-The-Art method.
UR - http://www.scopus.com/inward/record.url?scp=85069527255&partnerID=8YFLogxK
U2 - 10.1145/3292522.3326058
DO - 10.1145/3292522.3326058
M3 - Conference contribution
AN - SCOPUS:85069527255
SP - 135
EP - 136
BT - WebSci 2019
T2 - 11th ACM Conference on Web Science, WebSci 2019
Y2 - 30 June 2019 through 3 July 2019
ER -