Beyond positive or negative: Qualitative sentiment analysis of social media reactions to unexpected stressful events

Abstract

Sentiment analysis techniques are increasingly used to grasp reactions from social media users to unexpected and potentially stressful social events. This paper argues that, alongside assessments of the affective valence of social media content as negative or positive, there is a need for a deeper understanding of the context in which reactions are expressed and the specific functions that users' emotional states may reflect. To demonstrate this, we present a qualitative analysis of affective expressions on Twitter collected in Germany during the 2011 EHEC food contamination incident based on a coding scheme developed from Skinner et al.'s (2003) coping classification framework. Affective expressions of coping were found to be diverse not only in terms of valence but also in the adaptive functions they served: beyond the positive or negative tone, some people perceived the outbreak as a threat while others as a challenge to cope with. We discuss how this qualitative sentiment analysis can allow a better understanding of the way the overall situation is perceived-threat or challenge-and the resources that individuals experience having to cope with emerging demands.

Social media in emergency management: Twitter as a tool for communicating risks to the public

“…Using rumour theory, Oh et al (2013) established that it is not ambiguity in the content of tweets that results in rumours but rather ambiguity about the source or the context. Rumour may also be associated with unwanted attenuation of risk perceptions if, for example it drew attention away from officially sanctioned positions like the cause of food contamination or the treatment of subsequent illness (Gaspar et al, 2016). If faced with an inappropriate lack of concern, authorities would then wish to correct this analysis and intensify, or perhaps more accurately, de-attenuate, by ensuring that proportionate attention and concern was linked to appropriate actions and levels of vigilance.…”

“…For example, Twitter can be used for collective sense-making during civil unrest incidents (Heverin and Zach 2012), as a warning tool in natural disasters (Chatfield et al, 2013) or as means of coping with the stressful effects of a food contamination incident (Gaspar et al, 2016). Emergency activity on Twitter that starts with factual information can involve waves of public reaction that directly impact ongoing events, especially when they involve high uncertainty.…”

“…Public authorities such as the New York Fire Department were able to provide essential support and even target the rescue of victims through the effective use of their Twitter account (CNN, 2012). This is only one of the highly visible cases where the immediacy of Twitter has proven valuable in emergency communication; others include tsunamis, floods and man-made violent incidents like terrorist attacks or food contamination (AlSaggaf and Simmons, 2014;Gaspar et al, 2016;Heverin and Zach, 2012;Oh et al, 2013). Twitter Alerts (2015), the network's official warning system launched in 2013, helps users receive official emergency alerts from registered authorities such as police forces, ambulance services, meteorological and environment agencies.…”

Event classification and location prediction from tweets during disasters

“…Nowadays, information and communication technology (ICT) is being used widely during different phases of disaster for relief activities (Kabra and Ramesh 2015). Twitter plays a major role in informing people, acquiring their status information, and also gathering information on different rescue activities taking place during both, natural disasters (tsunamis/floods) and man-made disasters (terrorist attack/food contamination) (Al-Saggaf and Simmons 2015; Gaspar et al 2016;Heverin and Zach 2012;Oh et al 2013).…”

Comparative Study of Opinion Mining Tools

“…So, to analyse emotions is much more difficult task than opinion mining and appraisal theory. Lot of work is going on appraisal theory 8 as it is useful in sarcasm detection 9 , detecting stressful events, detecting abuse 10 and other various unlawful activities that can happen can be detected using social web.…”