Leveraging In-Context Online Discussion of Course Materials to Enhance Student Engagement and Learning

利用课程材料的上下文在线讨论来增强学生的参与和学习

• 批准号: 1915724
• 负责人: Marc Facciotti
• 金额: $ 127.12万
• 依托单位: University of California-Davis
• 依托单位国家: 美国
• 项目类别: Standard Grant
• 财政年份: 2019
• 资助国家: 美国
• 起止时间: 2019-10-01 至 2024-09-30
• 项目状态: 已结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=1915724&HistoricalAwards=false
• 关键词: Leveraging; Context; Online; Discussion; Course

With support from NSF's Improving Undergraduate STEM Education: Education and Human Resources (IUSE: EHR) program, this project aims to serve the national interest by enhancing the value of online learning environments. Teaching and learning are increasingly happening online. Interactive texts and videos delivered through the Internet have the potential to lower the cost of content delivery, promote greater learning than traditional methods of content delivery, and provide more personalized and equitable access to education. To be successful and broadly adopted, however, any new online educational platform must provide greater value for the students and instructors than the technologies that it replaces. One promising idea to enhance the value of online learning environments is to leverage their ability to enable interactivity between students and instructors by using "smart" interactive technologies that can provide customized feedback to both groups. In this project, researchers at the University of California, Davis and Massachusetts Institute of Technology will build new understandings of how student engagement with online content can be shaped to enhance learning. Student engagement will be captured in short written notes, comments, and questions that students place in the margins of documents, web pages, and videos. By capturing feedback about how students feel about and engage with online resources, instructors will be able to modify digital resources and restructure classroom time to be more effective. Students will get an opportunity to engage with and reflect more deeply on the course content, connect with other students to discuss course content, and engage the instructor in new ways. The project will improve students' and instructors' experiences with online content, increase the value of online content delivery, and contribute to the personalization of online resources.The investigators will build upon NotaBene, a system that allows students to discuss online course content (PDFs, websites, and YouTube videos) in the margins of those content sources. The investigators will gather information about student engagement by mining the discussion content in the margins and will present information about student engagement to instructors, help the instructors make use of this information for class design and for interacting with students, and test the hypothesis that increasing engagement leads to better learning outcomes. The analytical models in the research will consider three distinct types of engagement: emotional engagement (a measure of how students feel about what they are interacting with online; e.g., interest;curiosity; confusion; boredom); cognitive engagement (a measure of how deeply students are thinking about what they are interacting with); and temporal engagement (a measure of how much time students are spending interacting with different parts of the online content). Collecting these three measures of engagement will allow the investigators not only to look at each type of engagement independently but also to uncover how they are interrelated. Understanding the interplay between these types of engagement should enable instructors to respond with more finely tuned and effective interventions. The enhancements to NotaBene, the accompanying visualization tools, and the analyses that result from this project will give students and instructors greater insight into how students are learning from online content, and this insight will enable instructional and content corrections to overcome barriers to learning and facilitate greater student engagement online. NSF's IUSE: EHR program supports research and development projects to improve the effectiveness of STEM education for all students. Through the Engaged Student Learning track, the program supports the creation, exploration, and implementation of promising practices and tools.This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.

在NSF的改善本科STEM教育：教育和人力资源（IUSE：EHR）计划的支持下，该项目旨在通过提高在线学习环境的价值来服务于国家利益。教学和学习越来越多地发生在网上。通过互联网提供的交互式文本和视频有可能降低内容提供的成本，比传统的内容提供方法促进更多的学习，并提供更个性化和公平的教育机会。然而，要想获得成功并被广泛采用，任何新的在线教育平台都必须为学生和教师提供比其所取代的技术更大的价值。提高在线学习环境价值的一个有希望的想法是利用它们的能力，通过使用“智能”交互技术，为学生和教师提供定制的反馈，从而实现学生和教师之间的互动。在这个项目中，加州大学戴维斯分校和马萨诸塞州学院的研究人员将对学生如何参与在线内容以促进学习建立新的理解。学生的参与将被记录在简短的书面笔记，评论和问题中，学生将放在文档，网页和视频的边缘。通过获取学生对在线资源的感受和参与度的反馈，教师将能够修改数字资源并重组课堂时间，以提高效率。学生将有机会参与并更深入地反思课程内容，与其他学生联系以讨论课程内容，并以新的方式与教师互动。该项目将改善学生和教师对在线内容的体验，增加在线内容交付的价值，并有助于在线资源的个性化。调查人员将建立在NotaBene的基础上，NotaBene是一个允许学生在这些内容源的边缘讨论在线课程内容（PDF，网站和YouTube视频）的系统。调查人员将通过挖掘页边空白中的讨论内容来收集有关学生参与度的信息，并将有关学生参与度的信息呈现给教师，帮助教师利用这些信息进行课堂设计和与学生互动，并测试增加参与度会导致更好的学习成果的假设。研究中的分析模型将考虑三种不同类型的参与：情感参与（衡量学生对在线互动的感受;例如，利息;好奇心;混乱;无聊）;认知参与度（衡量学生对他们正在与之互动的内容的思考程度）;以及时间参与度（衡量学生花费多少时间与在线内容的不同部分互动）。收集这三种参与措施将使调查人员不仅能够独立地看待每种类型的参与，而且还能揭示它们之间的相互关系。了解这些类型的参与之间的相互作用，应使教师作出反应，更微调和有效的干预。NotaBene的增强功能、随附的可视化工具以及该项目产生的分析将使学生和教师更深入地了解学生如何从在线内容中学习，这种洞察力将使教学和内容更正能够克服学习障碍，并促进学生在线参与。 NSF的IUSE：EHR计划支持研究和开发项目，以提高所有学生STEM教育的有效性。该奖项反映了NSF的法定使命，并通过使用基金会的知识价值和更广泛的影响审查标准进行评估，被认为值得支持。

项目成果

New Methods for Confusion Detection in Course Forums: Student, Teacher, and Machine

课程论坛中混淆检测的新方法：学生、教师和机器

• DOI: 10.1109/tlt.2021.3123266
• 发表时间: 2021
• 期刊: IEEE Transactions on Learning Technologies
• 影响因子: 3.7
• 作者: Geller, Shay A.;Gal, Kobi;Segal, Avi;Sripathi, Kamali;Kim, Hyunsoo G.;Facciotti, Marc T.;Igo, Michele;Hoernle, Nicholas;Karger, David
• 通讯作者: Karger, David

Confused and beyond: detecting confusion in course forums using students' hashtags

困惑与超越：使用学生的主题标签检测课程论坛中的困惑

• DOI: 10.1145/3375462.3375485
• 发表时间: 2020
• 期刊: LAK '20: Proceedings of the Tenth International Conference on Learning Analytics & Knowledge
• 作者: Geller, Shay A.;Hoernle, Nicholas;Gal, Kobi;Segal, Avi;Zhang, Amy X.;Karger, David;Facciotti, Marc T.;Igo, Michele
• 通讯作者: Igo, Michele

lets-discuss: Analyzing student affect in course forums using emoji.

让讨论：使用表情符号分析学生在课程论坛中的影响。

• 发表时间: 2022
• 期刊: Proceedings of the 15th International Conference on Educational Data Mining
• 作者: Blobstein, A.;Gal, K.;Karger, D.;Facciotti, M.;Kim, H.;Almahmoud, J.;Sripathi, K.
• 通讯作者: Sripathi, K.

Spotlights: Designs for Directing Learners' Attention in a Large-Scale Social Annotation Platform

焦点：在大型社交注释平台中引导学习者注意力的设计

• DOI: 10.1145/3555598
• 发表时间: 2022
• 期刊: Proceedings of the ACM on Human-Computer Interaction
• 作者: Almahmoud, Jumana;Jahanbakhsh, Farnaz;Facciotti, Marc;Igo, Michele;Sripathi, Kamali;Gal, Kobi;Karger, David
• 通讯作者: Karger, David

Seeding Course Forums using the Teacher-in-the-Loop

使用教师在环中播种课程论坛

• DOI: 10.1145/3448139.3448142
• 发表时间: 2021
• 期刊: LAK21: 11th International Learning Analytics and Knowledge Conference
• 作者: Shusterman, Einat;Kim, Hyunsoo Gloria;Facciotti, Marc;Igo, Michele;Sripathi, Kamali;Karger, David;Segal, Avi;Gal, Kobi
• 通讯作者: Gal, Kobi