Towards Understanding and Supporting Journalistic Practices Using Semi-Automated News Discovery Tools
Towards Understanding and Supporting Journalistic Practices Using Semi-Automated News Discovery Tools
复制标题
DOI：
10.1145/3479550
复制
发表时间：
2021-10
影响因子：
--
通讯作者：
N. Diakopoulos;Daniel Trielli;Grace Lee
中科院分区：
文献类型：
--
作者：
N. Diakopoulos;Daniel Trielli;Grace Lee
记者经常面临的挑战是监测庞大的信息环境，以确定哪些是有新闻价值和有兴趣向更广泛的受众报道。在被称为计算新闻发现的过程中，基于数据驱动算法分析的警报和线索可以将记者的注意力引导到更有可能具有新闻价值的事件、文档或数据中的异常模式。在本文中，我们原型这样的新闻发现工具，算法提示，我们设计的，以帮助记者找到有新闻价值的线索，在美国各级政府使用的算法决策系统。该工具将算法、众包和专家评估整合到一个集成界面中，旨在支持用户做出编辑决策，以确定要追求哪些新闻。然后，我们提出了一个评估我们的原型的基础上，与八名专业记者的扩展部署。我们的研究结果提供了深入了解新闻实践，这些新闻发现工具使和改造，并建议改进计算新闻发现工具设计的机会，以更好地支持这些实践。
Journalists are routinely challenged with monitoring vast information environments in order to identify what is newsworthy and of interest to report to a wider audience. In a process referred to as computational news discovery, alerts and leads based on data-driven algorithmic analysis can orient journalists' attention to events, documents, or anomalous patterns in data that are more likely to be newsworthy. In this paper we prototype one such news discovery tool, Algorithm Tips, which we designed to help journalists find newsworthy leads about algorithmic decision-making systems used across all levels of U.S. government. The tool incorporates algorithmic, crowdsourced, and expert evaluations into an integrated interface designed to support users in making editorial decisions about which news leads to pursue. We then present an evaluation of our prototype based on an extended deployment with eight professional journalists. Our findings offer insights into journalistic practices that are enabled and transformed by such news discovery tools, and suggest opportunities for improving computational news discovery tool designs to better support those practices.