Social Media Analytics for Effective and Efficient Event Detection

用于有效且高效事件检测的社交媒体分析

• 批准号: 523332-2018
• 负责人: Keselj, Vlado
• 金额: $ 1.82万
• 依托单位: Dalhousie University
• 依托单位国家: 加拿大
• 项目类别: Engage Grants Program
• 财政年份: 2018
• 资助国家: 加拿大
• 起止时间: 2018-01-01 至 2019-12-31
• 项目状态: 已结题
• 来源: https://www.nserc-crsng.gc.ca/ase-oro/Details-Detailles_eng.asp?id=655366
• 关键词: Social; Media; Analytics; Effective; Efficient

Social media an other real-time messaging applications represent valuable sources of real-time information that**remain untapped by many service operator. TRT Canada uses the social media sources to provide valuable**information to the clients, ground and aerial transportation industrial partners, as well as first responders and**other government services. The project is aimed at developing methodology for coping with high volume and**velocity of textual data and providing tools for detection and classification of new events and anomalies in the**feed.**The Dalhousie research team proposes to develop and evaluate some of the state-of-the-art methods in textual**analytics in text stream processing and neural network techniques, such ad deep learning and convolutional**neural network. The experiments are designed to measure effectiveness of these methods at detecting**anomalies and new events, event classification, and identification of event features, such as actors, locations,**and time characteristics.**Most of the funds will support graduate students working on the project.

社交媒体是另一种实时通讯应用程序，它代表着许多服务运营商尚未开发的实时信息的宝贵来源。TRT加拿大公司使用社交媒体资源向客户、地面和空中交通行业合作伙伴以及急救人员和**其他政府服务机构提供有价值的**信息。该项目旨在开发处理大量和**速度的文本数据的方法，并提供工具来检测和分类**提要中的新事件和异常。**Dalhousie研究团队建议开发和评估文本流处理和神经网络技术中的一些最先进的文本**分析方法，例如AD深度学习和卷积**神经网络。这些实验旨在测试这些方法在检测**异常和新事件、事件分类以及识别事件特征(如参与者、位置、**和时间特征)方面的有效性。**大部分资金将用于支持参与该项目的研究生。