CUES : Cyber-mediated Usable Emotional Sensors: Phase 2 Proposal

Cataclysmic changes in how we communicate in cyberspace are dramatically altering our society, allowing information to spread faster, farther, and with less assurance of its accuracy, and enabling groups to form and recruit members on-line to foster social divides. Organized social media manipulation has more than doubled since 2017, with at least 70 nation states employing computation assisted techniques to shape public opinion and create new groups.  Influence campaigns are used to sever trust in institutions, create fractures in society, polarize groups, and generate mass-hysteria, to alter elections and subvert policies, and to support criminal and terror activities. Often, those conducting these influences campaigns are assisted by the use of technologies such as bots, cybrogs, and memes, or they employ human trolls.  Identifying these influence campaigns, in particular the maneuvers used to conduct them, and the impact that they have on the individual or group being targeted is complex.  These influence campaigns involve altering both who is talking to whom and what they are talking about.  The information maneuvers forming this campaigns often involve emotional appeals propagated through and recognized by subconscious indicators of the actor’s emotional state.  Today such identification is done by analysts, reading and interpreting social media posts.  We propose to address these problems by creating a novel technology for influence campaigns that supports identification of maneuvers and assessing their impact from joint emotion and social perspective. This proposal is to develop, test, and make operational a scientifically sound approach for assessing information influence campaigns and their impact in ways that take account of the emotional state projected by the influencer and the consequent emotional state of those being influenced. A set of cyber-mediated usable emotional sensors (CUES), will be operationalized and used to improve the assessment of information maneuvers in social media – both identification and impact assessment. Social, cognitive and psychological principles are used to lay the groundwork for new metrics and technologies that employ a combination of dynamic network analytics, machine learning, and natural language processing techniques applied to social media data in which the emotional content has been assessed using these CUES.  The result will be an operational technology that supports automated assessment of information maneuvers using not just intelligent algorithms, but emotionally intelligent algorithms. The proposed CUES enabled technologies for identifying maneuvers and assessing their impact will be scalable, reusable, applicable to multiple media, operational across multiple languages.