PacSocial: Field Test Report Max Nanis max@pacsocial.com @x0xMaximus Ian Pearce ian@pacsocial.com @peeinears Tim Hwang tim@pacsocial.com @timhwang November 15, 2011 1 Introduction The Pacific Social Architecting Corporation (PacSo- cial) has been focused on the development of tech- nologies that enable large-scale shaping of social groupings and communities online. Our work has centered on the generation of socialbots – swarms of automated, intelligent identities on platforms like Facebook and Twitter that interact, encourage, and provoke communities towards certain behaviors. The vision of this technology is to enable operators to actively mold and shape the social topology of hu- man networks online to produce desired outcomes. The present report focuses on data that were col- lected during PacSocial’s most recent field test con- cerning socialbots designed to operate on Twitter. An integral part of its development cycle, PacSo- cial conducts such field tests regularly; the results of these tests help to benchmark performance and also guide further development. While past studies have shown that socialbots are efficient at fostering bot-human interaction on Twit- ter, this study is the second of two experiments aimed at assessing the ability of socialbots to in- fluence connection and interaction between two hu- man users. Primarily due to an experimental design flaw, we were unable to produce any significant re- sults from the first of these human-human connec- tion experiments. We addressed these design issues in the design of the present experiment, and for the first time we are able to show significant results con- cerning the ability of socialbots to influence human- human connection online. 2 Design & Methodology The purpose of this study is to analyze the extent to which socialbots can affect the tweet and follow be- havior within target groups of users on Twitter. To do this, we tracked the tweet and follow activity of 2700 Twitter users over the course of 54 days, from September 19 to November 12, 2011. For the first 33 days (the control period), no socialbots were deployed. That is, the control period is marked by the condition that users had no contact or interac- tion with our socialbots. Socialbots were deployed immediately following the control period, and we continued to track users’ activity over the next 21 days (the experimental period). To determine the socialbots’ effect on the target group, we com- pare user activity during the control period to that during the experimental period. Each user in the initial group of 2700 was ran- domly assigned to one of nine experimental groups. Each experimental group contained 300 users and one socialbot, making a total of nine socialbots: Bot a-i . A socialbot’s experimental group is called its target group. Socialbots were programmed to operate strategically in ways intended to foster con- nection between users in their respective target groups. A socialbot assesses the follow network of its target group and operates accordingly, utilizing tactics that involve following, mentioning, tweeting, and retweeting. 3 Results Metrics each fall into one of two categories. The first category (bot-human interaction) concerns the socialbots’ ability to connect to and interact with other users. The second category (human-human interaction) includes metrics that measure the so- cialbots’ ability to connect users to each other. 1