Cardiff University | Prifysgol Caerdydd ORCA
Online Research @ Cardiff 
WelshClear Cookie - decide language by browser settings

Sensing real-world events using Arabic Twitter posts

Alsaedi, Nasser, Burnap, Peter ORCID: https://orcid.org/0000-0003-0396-633X and Rana, Omer Farooq ORCID: https://orcid.org/0000-0003-3597-2646 2016. Sensing real-world events using Arabic Twitter posts. Presented at: International AAAI Conference on Web and Social Media (ICWSM), Cologne, Germany, 17-20 May 2016. Proceedings of the Tenth International AAAI Conference on Web and Social Media (ICWSM 2016). AAAI, pp. 515-518.

[thumbnail of 13016-57846-1-PB.pdf]
Preview
PDF - Published Version
Download (490kB) | Preview

Abstract

In recent years, there has been increased interest in event detection using data posted to social media sites. Automatically transforming user-generated content into information relating to events is a challenging task due to the short informal language used within the content and the variety oftopics discussed on social media. Recent advances in detecting real-world events in English and other languages havebeen published. However, the detection of events in the Arabic language has been limited to date. To address this task, wepresent an end-to-end event detection framework which comprises six main components: data collection, pre-processing, classification, feature selection, topic clustering and summarization. Large-scale experiments over millions of Arabic Twitter messages show the effectiveness of our approach for detecting real-world event content from Twitter posts.

Item Type: Conference or Workshop Item (Paper)
Date Type: Publication
Status: Published
Schools: Computer Science & Informatics
Data Innovation Research Institute (DIURI)
Subjects: Q Science > QA Mathematics > QA75 Electronic computers. Computer science
Q Science > QA Mathematics > QA76 Computer software
Publisher: AAAI
Related URLs:
Date of First Compliant Deposit: 2 August 2019
Last Modified: 01 Nov 2022 10:19
URI: https://orca.cardiff.ac.uk/id/eprint/91040

Citation Data

Cited 12 times in Scopus. View in Scopus. Powered By Scopus® Data

Actions (repository staff only)

Edit Item Edit Item

Downloads

Downloads per month over past year

View more statistics