权益分类	功能权益	普通用户	{{item.name}}会员
{{category.name}}	{{benefitItem.name}}

Collaborative Research: Updating the Militarized Dispute Data Through Crowdsourcing: MID5

协作研究：通过众包更新军事化争端数据：MID5

基本信息

批准号：
1528409
负责人：
Glenn Palmer
金额：
$ 69.04万
依托单位：
Pennsylvania State Univ University Park
依托单位国家：
美国
项目类别：
Continuing Grant
财政年份：
2015
资助国家：
美国
起止时间：
2015-09-15 至 2019-08-31
项目状态：
已结题

来源：
https://www.nsf.gov/awardsearch/showAward?AWD_ID=1528409&HistoricalAwards=false
关键词：
Collaborative Research Updating Militarized Dispute

项目摘要

General Summary The Correlates of War Project's Militarized Interstate Dispute (MID) Data is the most prominent and heavily used data collection in the study of international conflict. The most recent version (MID4) was released in 2014 and brings the period covered to 1816-2010. The MID4 project utilized automated text classification procedures to make the process of identifying relevant news stories more efficient. Over the course of that project, the PIs determined the primary bottleneck in the workflow was the coding of those news documents. To address this inefficiency, The PIs completed a pilot project to determine whether crowdsourcing techniques could be used to code these documents. In the pilot, non-expert workers were paid small sums to read documents and to answer sets of questions, the answers to which were used to identify features of possible militarized incidents (the events that comprise MIDs). A systematic comparison of the crowdsourced responses with those of MID4 Project's trained coders revealed that the crowdsourced codings were completely accurate for 68 percent of the news reports coded; more importantly, high agreement among crowd responses on specific reports was strongly associated with correct coding. This enables the PIs to detect which documents require further expert involvement. As a result, the PIs can produce a majority of the MID data in near-realtime and at limited financial cost. These procedures are applied on the MID5 Project, which will update the MID data for the period 2011-2017.Technical Summary The MID5 project workflow begins with document retrieval from LexisNexis and document classification using the software and methods implemented in MID4. We discard the negatively classified documents, and proceed to extract metadata from the positively classified documents including the document title, the news agency that published the report, the date, and any actors mentioned in the text. Crowd workers are recruited through Amazon's Mechanical Turk and paid a wage to read one of these documents and answer a line of simple, objective questions about it. The questionnaire is predefined, but some extracted metadata is automatically inserted into the questionnaire to improve the quality of responses. Several workers complete a questionnaire for each document, leaving the PIs with problems of aggregation: how to combine multiple worker responses, possibly regarding multiple related questions, into usable data necessary to code the militarized incident. In the pilot study, the PIs show that Bayesian networks are the most effective way to achieve this aggregation. Recently, the PIs have made advances in semi-supervised text classification with hybrid, Deep Restricted Boltzmann Machines, which outperform previous methods in this task.

一般摘要战争相关项目的军事化州际争端 (MID) 数据是国际冲突研究中最突出且使用最多的数据集合。最新版本 (MID4) 于 2014 年发布，涵盖的时期为 1816 年至 2010 年。 MID4 项目利用自动文本分类程序来提高识别相关新闻报道的过程的效率。在该项目的过程中，PI 确定工作流程中的主要瓶颈是这些新闻文档的编码。为了解决效率低下的问题，PI 完成了一个试点项目，以确定是否可以使用众包技术对这些文档进行编码。在试点中，非专业工作人员获得少量报酬来阅读文件并回答一系列问题，这些问题的答案被用来识别可能的军事化事件（构成 MID 的事件）的特征。对众包响应与 MID4 项目训练有素的编码员的响应进行系统比较后发现，众包编码对于 68% 的新闻报道来说是完全准确的；更重要的是，人群对特定报告的反应高度一致与正确编码密切相关。这使得 PI 能够检测哪些文档需要进一步的专家参与。因此，PI 可以以有限的财务成本近乎实时地生成大部分 MID 数据。这些程序适用于 MID5 项目，该项目将更新 2011-2017 年期间的 MID 数据。技术摘要 MID5 项目工作流程首先从 LexisNexis 进行文档检索，然后使用 MID4 中实现的软件和方法进行文档分类。我们丢弃负面分类的文件，并继续从正面分类的文件中提取元数据，包括文件标题、发布报告的新闻机构、日期以及文本中提到的任何参与者。人群工作人员是通过亚马逊的 Mechanical Turk 招募的，并支付工资来阅读其中一份文件并回答一系列简单、客观的问题。调查问卷是预定义的，但一些提取的元数据会自动插入到调查问卷中，以提高答复质量。多名工作人员针对每个文档完成一份调查问卷，这给 PI 留下了聚合问题：如何将多个工作人员的回答（可能涉及多个相关问题）组合成对军事化事件进行编码所需的可用数据。在试点研究中，PI 表明贝叶斯网络是实现这种聚合的最有效方法。最近，PI 在使用混合深度受限玻尔兹曼机的半监督文本分类方面取得了进展，在该任务中优于以前的方法。

项目成果

期刊论文数量（7）

专著数量（0）

科研奖励数量（0）

会议论文数量（0）

专利数量（0）

Learning a Deep Hybrid Model for Semi-Supervised Text Classification

DOI：
10.18653/v1/d15-1053
发表时间：
2015-09
期刊：
影响因子：
0
作者：
Alexander Ororbia;C. Lee Giles;D. Reitter
通讯作者：
Alexander Ororbia;C. Lee Giles;D. Reitter

Event Ordering with a Generalized Model for Sieve Prediction Ranking

使用筛预测排序的广义模型进行事件排序

DOI：
发表时间：
2017
期刊：
Proceedings of the 8th International Joint Conference on Natural Language Processing
影响因子：
0
作者：
McDowell, William;Chambers, Nathaniel;Ororbia II, Alexander G.;Reitter, David
通讯作者：
Reitter, David

A Framework for Computational Models of Human Memory

人类记忆计算模型的框架