Collaborative Research: Enabling Robust Learning with Conceptual Personalization Technologies

针对个别学生独特的学习需求并以他们的先验知识为基础的个性化教学对于支持有效的科学学习至关重要。该项目的主要目标是使用自然语言技术通过个性化策略支持稳健的学习。该项目是科罗拉多大学、大学大气研究公司和犹他大学之间的三机构合作项目。它有两个目标：技术目标是创建与领域无关的技术来创建个性化算法。学习科学的目标是衡量这些算法对学习的影响。该项目侧重于稳健学习，即学习支持转移和元认知技能的提升。主题是地球科学和生物学。所提议的技术将按如下方式运行。首先，系统使用最先进的统计自然语言处理方法（主要是潜在语义分析）来自动处理学习资源（主要是文本），以创建领域知识图谱。这包括自动识别核心概念。其次，在学习过程中，系统将分析学生的论文，动态构建学生回答的领域知识图（以及对学生理解的评估）。系统使用图形匹配技术评估学生的反应，包括确定遗漏或误解了哪些概念。最后，系统使用推荐引擎方法来推荐可以帮助学生理解材料的网络资源。对于学习评估，该项目采用 2（技术或无）× 2（研究领域）混合研究设计，使用 40 名学生作为样本。该项目的目的是使科学学习和教学更加有效。该项目利用了一套丰富的新工具来分析文本材料。这些工具具有多种功能。它们最初允许对文本课程材料进行分析，以自动开发文本中嵌入的核心概念的描述。然后，这些工具会评估学生撰写的关于核心材料的论文，以确定他们个人的理解水平。然后，这些工具向个别学生提供有关遗漏或误解概念的反馈。该反馈包括对构成学习课程的文本材料的引用以及对其他互联网资源的引用，学生可以使用这些资源来更好地理解生物学和自然科学中的科学概念。这项研究建立在 15 年文本语义分析工作的基础上。这项研究意义重大，因为它适用于任何学科领域，而且由于它是自动化的，因此可以在全国范围内推广。

Personalized instruction instruction that targets individual students' unique learning needs and builds upon their prior knowledge is critical for supporting effective science learning. The primary goal in this project is to support robust learning with personalization strategies using natural language technologies. The project is a three-institution collaboration between the University of Colorado, the University Corporation for Atmospheric Research, and the University of Utah. It has two objectives: the technology objective is to create domain-independent techniques to create personalization algorithms. The learning science objective is to measure the effect of these algorithms on learning. The project focuses on robust learning, i.e., learning the supports transfer and the promotion of meta-cognitive skills. The subject matter is earth science and biology. The proposed techonology would operate as follows. Firstly, the system uses state-of-the-art statistical natural language processing methods (mainly latent semantic analysis) to automatically process learning resources (primarily texts) in order to create a domain knowledge map. This includes automatically identifying core concepts. Secondly, during learning sessions, the system would analyze students' essays to dynamically construct a domain knowledge map of the students' responses (and an assessment of student understanding). Using graph matching techniques, the system evaluates the student's response, including determining what concepts were missing or misunderstood. Finally, the system uses recommendation engine methods to suggest web resources that could help the student understand the material. For learning assessment, the project uses a 2 (technology or none) by 2 (domain of study) mixed research design using a sample of 40 students.The intent of this project is to make science learning and teaching more effective. The project draws upon a rich set of new tools for analyzing textual materials. The tools serve several functions. They initially allow the analysis of text course materials to automatically develop a description of the core concepts embedded in the texts. The tools then assess essays that the students write about the core materials to determine their individual level of understanding. The tools then provide feedback to the individual students regarding missing or misunderstood concepts. This feedback includes references to the text materials that comprise the course of study and references to additional internet resources that the individual students can use to better understand scientific concepts in biology and earch sciences. This research builds upon 15 years of work on semantic analysis of texts. The research is significant because it works for any subject area and, since it is automated, it can scale nationwide.