Trending: Social media analysis to monitor cannabis and synthetic cannabinoid use

描述（由申请人提供）：大麻仍然是美国最常用的精神活性物质之一，目前合法化政策的变化表明接受程度越来越高。与此同时，药物滥用者通过使用合成大麻素寻求类似的或更强烈的快感，合成大麻素是一种化学配方不断变化的新的特制药物，与不良健康影响有关，对公共健康构成重大挑战。根据NIDA RFA-CA-14-008提交（研究领域1），这项多PI研究建立在干预、治疗和成瘾研究中心的研究人员与赖特州立大学的俄亥俄州知识支持计算卓越中心之间的多学科合作基础上，开发了一个创新的软件平台eDrugTrends，这将有助于分析知识、态度、以及在网络论坛和Twitter上讨论的与使用大麻和合成大麻素有关的行为。到目前为止，还没有人开发出能够从这两个互补的社交媒体来源收集和半自动分析数据的计算机平台。我们将建立在我们的跨学科研究团队开发的现有基础设施上：Twitris，一个强大且高度可扩展的平台，旨在分析Twitter数据，以及PREDOSE，一个为我们的合作NIH资助（R21 DA 030571）开发的平台，用于分析非法使用丁丙诺啡的网络论坛数据。Twitris和PREDOSE的关键要素将使用语义网、自然语言处理和机器学习技术进行调整和增强，以推进对药物滥用研究的社交媒体数据的分析，从而最大限度地响应RFA。具体目标是：1）开发一个综合软件平台eDrugTrends，用于对大麻和合成大麻素使用的社交媒体数据（Twitter和网络论坛）的主题、情感、时空和社交网络维度进行半自动化处理和可视化。2)将eDrugTrends部署到：a）使用Twitter和网络论坛数据，确定并比较美国各地区与大麻和合成大麻素使用相关的知识，态度和行为趋势，这些地区具有不同的大麻合法化政策。B）分析社交网络特征，并确定Twitter上大麻和合成大麻素相关讨论的关键影响者（意见领袖）。eDrugTrends的开发将提高该领域的技术和方法能力，我们对该平台的部署将向该领域通报有关大麻、合成大麻素和其他药物使用的新趋势。eDrugTrends将通过提供一种工具来提供更及时的干预措施和政策应对措施，以应对大麻和合成大麻素使用及其相关危害的变化，从而对公共卫生产生重大影响。

DESCRIPTION (provided by applicant): Cannabis remains one of the most commonly used psychoactive substances in the U.S., and current changes in legalization policy indicate broadening acceptability. At the same time, substance abusers have sought similar, or more enhanced highs, through use of synthetic cannabinoids, new designer drugs with constantly changing chemical formulations that have been linked to adverse health effects and present significant challenges to public health. Submitted in response to NIDA RFA-CA-14-008 (Research Area 1), this multi-PI study builds on multidisciplinary collaboration between the researchers in the Center for Interventions, Treatment, and Addictions Research, and the Ohio Center of Excellence in Knowledge-enabled Computing at Wright State University to develop an innovative software platform, eDrugTrends, that will facilitate analysis of trends in knowledge, attitudes, and behaviors related to the use of cannabis and synthetic cannabinoids as discussed on Web forums and Twitter. To date, no one has developed a computer platform capable of collecting and semi-automatically analyzing data from these two complementary social media sources. We will build on the existing infrastructure developed by our interdisciplinary research team: Twitris, a robust and highly scalable platform designed to analyze Twitter data, and PREDOSE, a platform developed for our collaborative NIH grant (R21 DA030571) to analyze Web forum data on illegal buprenorphine use. Key elements of Twitris and PREDOSE will be adapted and enhanced using Semantic Web, Natural Language Processing, and Machine Learning techniques to advance the analysis of social media data for drug abuse research and is thus maximally responsive to the RFA. The Specific Aims are to: 1) Develop a comprehensive software platform, eDrugTrends, for semi-automated processing and visualization of thematic, sentiment, spatio-temporal, and social network dimensions of social media data (Twitter and Web forums) on cannabis and synthetic cannabinoid use. 2) Deploy eDrugTrends to: a) Identify and compare trends in knowledge, attitudes, and behaviors related to cannabis and synthetic cannabinoid use across U.S. regions with different cannabis legalization policies using Twitter and Web forum data. b) Analyze social network characteristics and identify key influencers (opinions leaders) in cannabis and synthetic cannabinoid-related discussions on Twitter. The development of eDrugTrends will advance the field's technological and methodological capabilities, and our deployment of the platform will inform the field on new trends regarding the use of cannabis, synthetic cannabinoids and other drugs. eDrugTrends will have high public health impact by providing a tool that can be used to inform more timely interventions and policy responses to changes in cannabis and synthetic cannabinoid use and associated harms.