I-Corps: Social Media Misinformation Interactive Dashboard

I-Corps：社交媒体错误信息交互式仪表板

• 批准号: 2223343
• 负责人: Zhijie Dong
• 金额: $ 5万
• 依托单位: Texas State University - San Marcos
• 依托单位国家: 美国
• 项目类别: Standard Grant
• 财政年份: 2022
• 资助国家: 美国
• 起止时间: 2022-05-01 至 2023-01-31
• 项目状态: 已结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=2223343&HistoricalAwards=false
• 关键词: Corps; Social; Media; Misinformation; Interactive

The broader impact/commercial potential of this I-Corps project is the development of an online dashboard with misinformation forecast trends and analysis to help address the misinformation endemic in America. Misinformation is a significant issue that may create confusion and misunderstanding about essential topics. Misinformation online may result in people questioning evidence-based medical guidance or refusing safe treatments. Understanding current misinformation content and trends supports both corporate entities and social media users. For corporations, th proposed suite of tools may show how misinformation impacts businesses by exploring and forecasting public sentiment concerning relevant misinformation topics. This analysis may provide value to these agencies by shifting resources from manual identification to analyzing the content and implications of misinformation posts. Individual users may be better equipped by understanding not only the major topics in misinformation but also an explanation of why this misinformation topic is being spread. Potential customers may be drawn to this proposed technology since information demand is met from grassroots organizations, which can be inconsistent with data quality. This I-Corps project is based on the development of automated data collection, data analytics, and deep learning methodologies. The goal is to develop an application and associated website that centralizes up-to-date misinformation content and metrics. Such a solution will provide potential customers with an enterprise-level system to help better understand the implications and types of misinformation spread across social media platforms. Currently, an array of tools to interact with misinformation content is under development. Pipelines are being constructed to channel and store raw data using the selenium framework for the collection step. Thesedata are stored locally and will act as the raw information to support the finalized dashboard. Deep learning models that are trained to identify text-based misinformation have been developed with the goal of expanding to image, sound, and video identification to address current social content trends. This Transformers framework also identifies sentiment on specified topic groups to support analysis. The proposed technology involves multiple research areas, including big data, natural language processing, artificial intelligence, and statistical analysis.This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.

这个I-Corps项目的更广泛的影响/商业潜力是开发具有错误信息预测趋势和分析的在线仪表板，以帮助解决美国的错误信息。错误信息是一个重要的问题，可能会引起对基本主题的混乱和误解。在线错误信息可能会导致人们质疑基于证据的医疗指导或拒绝安全治疗。了解当前的错误信息内容和趋势支持公司实体和社交媒体用户。对于公司而言，拟议的工具套件可能会通过探索和预测有关相关错误信息主题的公众情绪来表明误解如何影响企业。该分析可以通过将资源从手动识别转换为分析错误信息信息的内容和含义，从而为这些机构提供价值。单个用户不仅了解错误信息的主要主题，而且还解释了为什么这个错误信息主题正在传播。由于基层组织满足了信息需求，因此可能会吸引潜在客户，这可能与数据质量不一致。该I-Corps项目基于自动数据收集，数据分析和深度学习方法的开发。目标是开发一个应用程序和相关网站，该网站集中了最新的错误信息内容和指标。 这样的解决方案将为潜在客户提供企业级系统，以帮助更好地了解跨社交媒体平台的含义和错误信息的含义和类型。当前，正在开发与错误信息内容交互的一系列工具。正在为收集步骤的硒框架构建管道以通道和存储原始数据。 THESEDATA在本地存储，将充当支持最终仪表板的原始信息。已经开发了经过培训以识别基于文本的错误信息的深度学习模型，目的是扩展到图像，声音和视频标识，以解决当前的社会内容趋势。该变形金刚框架还确定了指定主题组的情感以支持分析。拟议的技术涉及多个研究领域，包括大数据，自然语言处理，人工智能和统计分析。该奖项反映了NSF的法定任务，并且使用基金会的智力优点和更广泛的影响审查标准，被认为值得通过评估来提供支持。