Date:
Mon, 12/11/201812:00-13:30
Location:
Levin building, Lecture Hall No. 8
Lecturer: Dr. Renana Peres, School of Business Administration, The Hebrew University
Abstract:
The research domain of Computational Social Studies describes social phenomena using models from Physics, Computer Science and Engineering. Specifically, I am interested in how social interactions are created, what is their dynamics over time, and how they accumulate to create population-level behaviors.
I will review the main research questions and techniques in the field, and focus on a recent study which models the eruption of online buzz in social systems.
Prior to their launch, many new products generate word of mouth (WOM) on social media. Such WOM typically increases toward the release date and contains sudden spikes. These spikes capture manifestations of peak consumer attention. We studied the emergence of spikes on over 90,000 pre-release online WOM messages on 157 Hollywood movies. We employ a robust filtering procedure to detect spikes, and test their dynamics, emergence, and content. The results indicate that pre-release spikes are widely prevalent: While some of them are event-driven, emerging in response to firm-created communications (e.g., trailer release), they are far more likely to emerge spontaneously. Content analysis reveals that WOM in spikes is more positive in sentiment and is more likely to deal with factual details than is WOM outside spikes. Pre-release WOM spikes also contribute significantly to the predictability of future product sales.
Abstract:
The research domain of Computational Social Studies describes social phenomena using models from Physics, Computer Science and Engineering. Specifically, I am interested in how social interactions are created, what is their dynamics over time, and how they accumulate to create population-level behaviors.
I will review the main research questions and techniques in the field, and focus on a recent study which models the eruption of online buzz in social systems.
Prior to their launch, many new products generate word of mouth (WOM) on social media. Such WOM typically increases toward the release date and contains sudden spikes. These spikes capture manifestations of peak consumer attention. We studied the emergence of spikes on over 90,000 pre-release online WOM messages on 157 Hollywood movies. We employ a robust filtering procedure to detect spikes, and test their dynamics, emergence, and content. The results indicate that pre-release spikes are widely prevalent: While some of them are event-driven, emerging in response to firm-created communications (e.g., trailer release), they are far more likely to emerge spontaneously. Content analysis reveals that WOM in spikes is more positive in sentiment and is more likely to deal with factual details than is WOM outside spikes. Pre-release WOM spikes also contribute significantly to the predictability of future product sales.