Combining automatic and manual approaches: Towards a framework for discovering themes in disaster-related tweets

College

College of Liberal Arts

Department/Unit

Political Science

Document Type

Conference Proceeding

Source Title

WWW 2015 Companion - Proceedings of the 24th International Conference on World Wide Web

First Page

1239

Last Page

1244

Publication Date

5-18-2015

Abstract

In this paper, we present a framework that combines automatic and manual approaches to discover themes in disaster-related tweets. As case study, we decided to focus on tweets related to typhoon Haiyan, which caused billions of dollars in damages. We collected tweets from November 2013 to March 2014 and used the local typhoon name "Yolanda" as the filter. Data association was used to expand the tweet set and k-means clustering was then applied. Clusters with high number of instances were subjected to open coding for labeling. The Silhouette indices ranged from 0.27 to 0.50. Analyses reveal that the use of automated Natural Language Processing (NLP) approach has the potential to deal with huge volumes of tweets by clustering frequently occurring words and phrases. This complements the manual approach to surface themes from a more manageable set of tweet pool, allowing for a more nuanced analysis of tweets from a human expert. As application, the themes identified during open coding were used as labels to train a classifier system. Future work could explore on using topic models and focusing on specific content or issues, such as natural calamities and citizen's participation in addressing these.

html

Digitial Object Identifier (DOI)

10.1145/2740908.2742125

Disciplines

Computer Sciences | Emergency and Disaster Management | Models and Methods

Keywords

cNatural language processing (Computer science); Document clustering; Typhoon Haiyan, 2013; Microblogs

Upload File

wf_no

This document is currently not available here.

Share

COinS