Live on TV, Alive on Twitter: Quantifying Continuous Partial Attention of Viewers During Live Television Telecasts

Rohit Saxena, Savita Bhat, Niranjan Pedanekar

Abstract: Even while engaged in an attention-consuming activity such as watching TV, social media users often end up paying attention to one or more social media. This is an example of a behavioral phenomenon called Continuous Partial Attention (CPA). Quantification of user attention can be a valuable metric in understanding user behavior under scenarios where their attention is divided. In this study, we propose a generalized model to quantify CPA given a primary and a secondary task, also knows as a distraction. Given a history of distractions, we compute a temporal attention profile for a user while incorporating a penalty for continual distraction. We analyze the model using the scenario of TV viewers who tweeted while watching the ten episodes of the sixth season of the popular TV show 'Game of Thrones' (GoT). We calculate attention profiles and CPA of 438 prolific users who tweeted during each episode of the show. Using this metric, we classify these users into Attentive and Partially Attentive viewers. We compare users from both classes in terms of their attention profiles. We also compare their tweeting behavior during live telecast of GoT to their normal tweeting behavior. We examine CPA across users during an episode vis-a-vis important events in the episode. We find that the CPA metric captures the effects of volume and lengths of the tweets, as well as their temporal distribution.