Analysis and Support of Lifestyle via Emotions Using Social Media

Abstract

Abstract. Using recent insights from Cognitive, Affective and Social Neuroscience this paper addresses how affective states in social interactions can be used through social media to analyze and support behaviour for a certain lifestyle. A computational model is provided integrating mechanisms for the impact of one's emotions on behaviour, and for the impact of emotions of others on one's own emotion. The model is used to reason about and assess the state of a user with regard to a lifestyle goal (such as exercising frequently), based on extracted information about emotions exchanged in social interaction. Support is provided by proposing ways to affecting these social interactions, thereby indirectly influencing the impact of the emotions of others. An ambient intelligent system incorporating this has been implemented for the social medium Twitter.

Validating Automated Sentiment Analysis of Online Cognitive Behavioral Therapy Patient Texts: An Exploratory Study

“…Our choice for this domain-independent algorithm was a pragmatic one, since we are exploring a new domain where tailored algorithms have not yet been developed, and state-of-the-art algorithm’s like those developed by Google (Google, 2018) or IBM (IBM, 2018) have, at the time of writing, not been tailored to the Dutch language. The algorithm has previously been used in studies focusing on crime prediction, where it was used to identify aggressive Twitter messages (Gerritsen and van Breda, 2015), life-style support, where it was used to determine people’s attitude toward a lifestyle goal (van Breda et al, 2012), and a training application for football referees, where it was used to identify the language used by referees during conflicts with football players (Bosse et al, 2017). Though the systems that used the algorithm seemed to have potential following simulation studies and a preliminary evaluation, respectively, they are still under development, and none of the published studies specifically targeted the accuracy of the algorithm.…”

Online Sharing of Physical Activity: Does It Accelerate the Impact of a Health Promotion Program?

“…It is often difficult to adopt new behavior and adhere to it, but it has been shown that close social circles (such as family, friends, and co-workers) are helpful in sustaining a healthy lifestyle [8], [9]. In [10], the role of online social interactions is discussed in the context of developing and maintaining a healthy lifestyle, e.g. an ambient system can continuously monitor and help people to alter their social ties in order to sustain healthy behavior.…”