Collaborative Research: Deliberative E-Rulemaking Decision Facilitation Project (DEER)

合作研究：审议性电子规则制定决策促进项目 (DEER)

• 批准号: 0713143
• 负责人: Peter Muhlberger
• 金额: $ 13.23万
• 依托单位: Texas Tech University
• 依托单位国家: 美国
• 项目类别: Continuing Grant
• 财政年份: 2007
• 资助国家: 美国
• 起止时间: 2007-09-15 至 2010-08-31
• 项目状态: 已结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=0713143&HistoricalAwards=false
• 关键词: Collaborative; Research; Deliberative; Rulemaking; Decision

This project will examine whether federal agency rulemaking can be improved with two innovations: a) multi-level deliberation (MLD), in which people discuss rulemakings in small groups that then select members to represent the group in a higher-level group and b) the combination of language technologies into an artificial discussion facilitation agent (DiFA). The project poses computer science challenges of combining several Natural Language Processing technologies (primarily Interactive QA, Dialogue Analysis, and Summarization) into a viable facilitation agent and in applying these technologies in an eclectic, multi-user discussion environment. We expect advances to be made within each component technology. For example, we hope to increase the utility of Dialogue Act tagging across applications and domains by using a set of general discussion tags for tracking and summarizing threads of discussion by combining dialogue structure and content analysis. We will also investigate how general our Question Answer approaches are. The social science herein breaks new ground in the nascent fields of e-rulemaking and democratic deliberation research. The project will advance research on measuring the quality of deliberation and the effects of deliberation and DiFA on individuals and communities. Research will involve four rulemaking experiments. The first three are subsets of the final one. The final 3X2 experiment crosses MLD, non-MLD deliberation, and non-deliberation with the presence or absence of DiFA. The success of the various conditions of these experiments will be measured using a multi-trait, multi-method approach that will include survey and focus group measures of agency official and participant perceptions and evaluations, a content analysis measure of the cognitive sophistication of rulemaking comments, both human-coded and automated content analyses of the quality of deliberation, measures of the impact of the deliberations on participants (knowledge, trust, citizenship), DiFA usage patterns, and continued participation in our user community.The federal agency rulemaking comment process represents an important potential avenues by which the American public can affect how it is governed. Such comments can make agency officials aware of likely adverse effects of the proposed rules. Unfortunately, the current rulemaking comment process faces a number of social and organizational problems including poorly informed and distrustful participants, lack of dialog among participants that could sharpen their reasoning, and problems of scale such as the large number of comments generated. Researchers believe that most rulemaking comments are low in quality or redundant?a product of form letters used by public interest groups. Rulemaking is not a plebiscite, but an effort to identify reasons to accept or modify proposed rules. This project will seek to address the problems of existing rulemaking by immersing rulemaking participants in small discussion groups that will be assisted by discussion facilitation software. The software will use cutting-edge technologies to help answer questions, summarize discussion, and provide feedback and suggestions on their discussion. Discussion itself will be organized into a hierarchy of representative groups to help the best ideas spread among participants and rise to the top. The value of the technology and of the deliberation methods will be thoroughly tested using experimental methods and data collected via surveys, focus groups, and by the software. The project will advance research in several areas. In computer science, it will seek to apply natural language technologies in a more general setting than before. The technology created could have broad application. It will also combine several technologies into a discussion facilitator that may be more widely used. The project will also advance research on democratic deliberation by improving and testing measures of deliberative quality and by adding to knowledge of how deliberation affects citizens.

该项目将研究是否可以通过两项创新来改进联邦机构的规则制定：a）多层审议（MLD），其中人们在小组中讨论规则制定，然后选择成员在更高级别的小组中代表该小组；b）将语言技术组合成人工讨论促进剂（DiFA）。 该项目提出了计算机科学的挑战，即将多种自然语言处理技术（主要是交互式 QA、对话分析和总结）结合到一个可行的促进代理中，并将这些技术应用在不拘一格的多用户讨论环境中。 我们期望每项组件技术都能取得进步。 例如，我们希望通过使用一组通用讨论标签来结合对话结构和内容分析来跟踪和总结讨论线索，从而提高跨应用程序和领域的对话行为标签的实用性。 我们还将调查我们的问答方法的普遍性。 这里的社会科学在电子规则制定和民主协商研究的新兴领域开辟了新天地。 该项目将推进衡量审议质量以及审议和 DiFA 对个人和社区影响的研究。 研究将涉及四项规则制定实验。 前三个是最后一个的子集。 最终的 3X2 实验将 MLD、非 MLD 深思熟虑和无深思熟虑与存在或不存在 DiFA 进行交叉。 这些实验的各种条件的成功将使用多特征、多方法的方法来衡量，其中包括对机构官员和参与者的看法和评估进行调查和焦点小组衡量，对规则制定评论的认知复杂程度进行内容分析衡量、对审议质量的人工编码和自动内容分析、审议对参与者影响的衡量（知识、信任、公民身份）、DiFA 使用模式以及对我们用户社区的持续参与。联邦机构规则制定评论流程代表美国公众可以影响其治理方式的重要潜在途径。 此类评论可以使机构官员意识到拟议规则可能产生的不利影响。 不幸的是，当前的规则制定评论过程面临着许多社会和组织问题，包括参与者信息匮乏和不信任、参与者之间缺乏可以提高推理能力的对话，以及产生大量评论等规模问题。 研究人员认为，大多数规则制定评论质量低下或多余——这是公共利益团体使用的套用信函的产物。 规则制定不是公民投票，而是努力确定接受或修改拟议规则的理由。 该项目将通过让规则制定参与者沉浸在小型讨论组中，并在讨论促进软件的协助下，寻求解决现有规则制定的问题。 该软件将使用尖端技术来帮助回答问题、总结讨论并针对讨论提供反馈和建议。 讨论本身将被组织成代表小组的层次结构，以帮助最好的想法在参与者之间传播并上升到顶层。 该技术和审议方法的价值将使用实验方法以及通过调查、焦点小组和软件收集的数据进行彻底测试。 该项目将推进多个领域的研究。 在计算机科学领域，它将寻求在比以前更普遍的环境中应用自然语言技术。 所创造的技术可能具有广泛的应用。 它还将把多种技术结合成一个可能被更广泛使用的讨论促进器。 该项目还将通过改进和测试协商质量的措施以及增加关于协商如何影响公民的知识来推进民主协商的研究。