Cheng Zheng1, Wei Wang1, Sean D Young2,3. 1. Department of Computer Science, University of California, Los Angeles. 2. Department of Emergency Medicine. 3. Department of Informatics, University of California, Irvine, California, USA.
Abstract
OBJECTIVES: Community popular opinion leaders have played a critical role in HIV prevention interventions. However, it is often difficult to identify these 'HIV influencers' who are qualified and willing to promote HIV campaigns, especially online, because social media influencers change frequently. We sought to use an iterative deep learning framework to automatically discover HIV-related online social influencers. DESIGN AND METHOD: Out of 1.15 million Twitter users' data from March 2018 to March 2020, we extracted tweets from 1099 Twitter users who had mentioned the keywords 'HIV' or 'AIDS'. Two Twitter users determined to be 'online HIV influencers' based on their conversation topics and engagement were hand-picked by domain experts and used as a seed training dataset. We modelled social influence and discovered new potential influencers based on these seeds using a graph neural network model. We tested the model's precision and recall compared with other baseline model approaches. We validated the results through manual verification. RESULTS: The model identified 23 new (manually verified) HIV-related influencers, including health and research organizations and local HIV advocates across the United States. Our proposed model achieved the highest accuracy/recall, with an average improvement of 38.5% over the other baseline models. CONCLUSION: Results suggest that iterative deep learning models can be used to automatically identify new and changing key HIV-related influencers online. We discuss the implications and potential of HIV researchers/departments applying this approach across online big data (e.g. hundreds of millions of social media posts per day) to help promote HIV prevention campaigns to affected communities.
OBJECTIVES: Community popular opinion leaders have played a critical role in HIV prevention interventions. However, it is often difficult to identify these 'HIV influencers' who are qualified and willing to promote HIV campaigns, especially online, because social media influencers change frequently. We sought to use an iterative deep learning framework to automatically discover HIV-related online social influencers. DESIGN AND METHOD: Out of 1.15 million Twitter users' data from March 2018 to March 2020, we extracted tweets from 1099 Twitter users who had mentioned the keywords 'HIV' or 'AIDS'. Two Twitter users determined to be 'online HIV influencers' based on their conversation topics and engagement were hand-picked by domain experts and used as a seed training dataset. We modelled social influence and discovered new potential influencers based on these seeds using a graph neural network model. We tested the model's precision and recall compared with other baseline model approaches. We validated the results through manual verification. RESULTS: The model identified 23 new (manually verified) HIV-related influencers, including health and research organizations and local HIV advocates across the United States. Our proposed model achieved the highest accuracy/recall, with an average improvement of 38.5% over the other baseline models. CONCLUSION: Results suggest that iterative deep learning models can be used to automatically identify new and changing key HIV-related influencers online. We discuss the implications and potential of HIV researchers/departments applying this approach across online big data (e.g. hundreds of millions of social media posts per day) to help promote HIV prevention campaigns to affected communities.
Authors: Sean D Young; William G Cumberland; Roch Nianogo; Luis A Menacho; Jerome T Galea; Thomas Coates Journal: Lancet HIV Date: 2015-01 Impact factor: 12.767
Authors: Bolin Cao; Somya Gupta; Jiangtao Wang; Lisa B Hightow-Weidman; Kathryn E Muessig; Weiming Tang; Stephen Pan; Razia Pendse; Joseph D Tucker Journal: J Med Internet Res Date: 2017-11-24 Impact factor: 5.428