Information Abstraction from Crises Related Tweets Using Recurrent Neural Network

Abstract : Social media has become an important open communication medium during crises. The information shared about a crisis in social media is massive, complex, informal and heterogeneous, which makes extracting useful information a difficult task. This paper presents a first step towards an approach for information extraction from large Twitter data. In brief, we propose a Recurrent Neural Network based model for text generation able to produce a unique text capturing the general consensus of a large collection of twitter messages. The generated text is able to capture information about different crises from tens of thousand of tweets summarized only in a 2000 characters text.
Document type :
Conference papers
Complete list of metadatas

Cited literature [23 references]  Display  Hide  Download

https://hal.inria.fr/hal-01557644
Contributor : Hal Ifip <>
Submitted on : Thursday, July 6, 2017 - 1:55:39 PM
Last modification on : Friday, December 1, 2017 - 1:16:25 AM
Long-term archiving on: Wednesday, January 24, 2018 - 7:26:24 PM

File

430537_1_En_38_Chapter.pdf
Files produced by the author(s)

Licence


Distributed under a Creative Commons Attribution 4.0 International License

Identifiers

Citation

Mehdi Ben Lazreg, Morten Goodwin, Ole-Christoffer Granmo. Information Abstraction from Crises Related Tweets Using Recurrent Neural Network. 12th IFIP International Conference on Artificial Intelligence Applications and Innovations (AIAI), Sep 2016, Thessaloniki, Greece. pp.441-452, ⟨10.1007/978-3-319-44944-9_38⟩. ⟨hal-01557644⟩

Share

Metrics

Record views

96

Files downloads

84