An emotional step toward automated trust detection in crisis social media

ABSTRACT

To this date, research on crisis informatics has focused on the detection of trust in Twitter data through the use of message structure, sentiment, propagation and author. Little research has examined the usefulness of these messages in the crisis response domain. In this paper, we characterize tweets, which are perceived useful or trustworthy, and determine their main features as one possible dimension to identify useful messages in case of crisis. In addition, we examine perceived emotions of these messages and how the different emotions affect the perceived usefulness and trustworthiness. Our analysis is carried out on two datasets gathered from Twitter concerning Hurricane Sandy in 2012 and the Boston Bombings in 2013. The results indicate that there is a high correlation between trustworthiness and usefulness, and, interestingly, that there is a significant difference in the perceived emotions that contribute to each of these. Our findings are poised to impact how messages from social media data are analyzed for use in crisis response.

KEYWORDS:

• Twitter
• Sandy
• Hurricane
• Boston
• bombing
• trust
• usefulness
• sentiment
• emotion

Disclosure statement

No potential conflict of interest was reported by the authors.

Notes on contributors

Shane E. Halse is currently working on his PhD in IST at the Pennsylvania State University under the guidance of Dr Andrea Tapia. Shane’s volunteer work as a first responder has allowed him to provide unique insights and discover new methodologies to aid in the response phase of a crisis. This is done through leveraging his passion for both computer programming and crisis response by investigating the trustworthiness and usefulness of social media data. [email: [email protected]].

Dr Andria Tapia is an Associate Professor of Information Sciences and Technology and the Director of Graduate Programs at the Pennsylvania State University. Dr Tapia is a Sociologist with expertise in social research methods and social theory, which she applies to the study of information and communication technologies (ICT) and their context of development, implementation and use. Dr Tapia’s work contributes to the solution of one of the stickiest problems currently facing disaster response organizations: the organizational inability to take advantage of an abundance of citizen-produced social media data. Dr Tapia also researches on means by which local communities can better make use of collective technical action to provide for early warning and post-disaster recovery. Dr Tapia’s research has directly contributed to the policy-making bodies of the United Nations, the U.S. Obama Administration and the largest international relief and development organizations. As a US Fulbright scholar in Costa Rica, she studied the effects of a national-level legal mandate to coordinate and to share information upon the social and informational networks in the emergency response sector in Latin America. Dr Tapia maintains a Visiting Professorship in the Graduate Program on Emergency and Rick Management at the University of Costa Rica. Dr Tapia is a member and leader of the American Sociological Association’s Section on Information and Communication Technologies and the International Association for Information Systems for Crisis Response and Management. [email: [email protected]].

Anna Squicciarini is an Associate Professor in the College of Information Sciences and Technology at the Pennsylvania State University. Her research interests are in the realm of users’ privacy and access control. She also collaborates on research projects related to disaster response and micro-blogs analysis for data trustworthiness. [email: [email protected]].

Cornelia Caragea is an Assistant Professor in the Department of Computer Science and Engineering at the University of North Texas, where she directs the Machine Learning Research Laboratory. Her research interests are in machine learning, information retrieval, and natural language processing. She designed models that classify and aggregate tweets and text messages from disaster events such as Haiti earthquake and Hurricane Sandy so that NGOs and relief workers can easily access them. [email: [email protected]].