ArmaTweet: Detecting Events by Semantic Tweet Analysis thumbnail
Pause
Mute
Subtitles
Playback speed
0.25
0.5
0.75
1
1.25
1.5
1.75
2
Full screen

ArmaTweet: Detecting Events by Semantic Tweet Analysis

Published on Jul 10, 20171224 Views

Armasuisse Science and Technology, the R&D agency for the Swiss Armed Forces, is developing a Social Media Analysis (SMA) system to help detect events such as natural disasters and terrorist activity

Related categories

Chapter list

Armatweet: detecting events by semantic tweet analysis 00:00
Table of contents00:04
Twitter event detection00:11
State of the art: Three kinds of approaches02:06
State of the art: Detecting unspecified events02:32
State of the art: Detecting predetermined events03:48
State of the art: Detecting specified events05:03
What keywords identify 'politicians dying'?06:01
Objective of semantic event detection07:00
Main idea: Use semantic search09:14
System architecture11:24
The role of natural language processing13:01
Knowledge graph structure15:49
User queries and time series extraction17:09
Time series analysis19:05
Evaluation challenges19:59
Evaluation methodology - 122:13
Evaluation methodology - 223:01
Precision results24:26
Conclusion25:40