An Integrated Approach of Sensing Tobacco-Oriented Activities in Online Participatory Media

With the embracing of mobile Internet of Things, participatory media is becoming a new battlefield for tobacco wars. However, how to automatically collect and analyze the large-scale user-generated data that are relevant to tobacco in participatory media is still unexplored. In this paper, we propose an integrated approach of sensing collective activities in tobacco-related participatory media. Meanwhile, we compare the temporal patterns, topological patterns, and collective emotion patterns among protobacco, antitobacco, and quit-tobacco groups. Based on the proposed framework, a prototype was implemented to collect large-scale tobacco-related data sets from Facebook. This demonstrates that the proposed framework is feasible and reasonable. Our preliminary findings reveal that, first, tobacco-related content grows exponentially. In particular, the growth of the protobacco group follows the exponential law, whereas there is linear growth for the tobacco control group. Second, the connection between the tobacco control community and the tobacco cessation community is tight, whereas the nodes in the protobacco community are connected sparsely. Finally, the collective emotion in tobacco communities is negative.