Climate Change, Disaster and Sentiment Analysis over Social Media Mining
Abstract
Accelerated climate change causes disasters and disrupts people living all over the globe. Disruptive climate events are often reflected in expressed sentiments of the people affected. Monitoring changes in these sentiments during and after disasters can reveal relationships between climate change and mental health. We developed a semantic web tool that uses linked data principles and semantic web technologies to integrate data from multiple sources and analyze them together. We are converting statistical data on climate change and disaster records obtained from the World Bank data catalog and the International Disaster Database into a Resource Description Framework (RDF) representation that was annotated with the RDF Data Cube vocabulary. We compare these data with a dataset of tweets that mention terms from the Emotion Ontology to get a sense of how disasters can impact the affected populations. This dataset is being gathered using an infrastructure we developed that extracts term uses in Twitter with controlled vocabularies. This data was also converted to RDF structure so that statistical data on the climate change and disasters is analyzed together with sentiment data. To visualize and explore relationship of the multiple data across the dimensions of time and location, we use the qb.js framework. We are using this approach to investigate the social and emotional impact of climate change. We hope that this will demonstrate the use of social media data as a valuable source of understanding on global climate change.
- Publication:
-
AGU Fall Meeting Abstracts
- Pub Date:
- December 2012
- Bibcode:
- 2012AGUFMIN51C1703L
- Keywords:
-
- 1630 GLOBAL CHANGE / Impacts of global change;
- 1970 INFORMATICS / Semantic web and semantic integration;
- 1974 INFORMATICS / Social networks;
- 4333 NATURAL HAZARDS / Disaster risk analysis and assessment