More Like this

1. Knowledge Annotation for Intelligent Textbooks

   https://doi.org/10.1007/s10758-021-09544-z  

   Wang, Mengdi; Chau, Hung; Thaker, Khushboo; Brusilovsky, Peter; He, Daqing (July 2021, Technology knowledge and learning)

   With the increased popularity of electronic textbooks, there is a growing interest in developing a new generation of “intelligent textbooks,” which have the ability to guide readers according to their learning goals and current knowledge. Intelligent textbooks extend regular textbooks by integrating machine-manipulable knowledge, and the most popular type of integrated knowledge is a list of relevant concepts mentioned in the textbooks. With these concepts, multiple intelligent operations, such as content linking, content recommendation, or student modeling, can be performed. However, existing automatic keyphrase extraction methods, even supervised ones, cannot deliver sufficient accuracy to be practically useful in this task. Manual annotation by experts has been demonstrated to be a preferred approach for producing high-quality labeled data for training supervised models. However, most researchers in the education domain still consider the concept annotation process as an ad-hoc activity rather than a carefully executed task, which can result in low-quality annotated data. Using the annotation of concepts for the Introduction to Information Retrieval textbook as a case study, this paper presents a knowledge engineering method to obtain reliable concept annotations. As demonstrated by the data we collected, the inter-annotator agreement gradually increased along with our procedure, and the concept annotations we produced led to better results in document linking and student modeling tasks. The contributions of our work include a validated knowledge engineering procedure, a codebook for technical concept annotation, and a set of concept annotations for the target textbook, which could be used as a gold standard in further intelligent textbook research. 

   more » « less
2. OpenDSA/Mastery Grids Exercise Interchange

   Manzoor, Hamza; Akhuseyinoglu, Kamil; Shaffer, Clifford; Brusilovsky, Peter (February 2019, Fourth SPLICE Workshop "CS Education Infrastructure for All II: Enabling the Change" at ACM SIGCSE 2019)

   OpenDSA is an e-Textbook project developed at Virginia Tech, which provides materials to support courses in a wide variety of Computer Science-related topics. OpenDSA primarily contains Java exercises. ACOS server which is a smart learning content server developed as a joint project of Aalto University and the University of Pittsburgh. It enhances the reusability of online learning activities by decoupling the content and the existing interoperability protocols including LTI. ACOS is capable of serving multiple smart contents including Python animations and exercises. In this project, we present steps toward integrating smart content served through ACOS into OpenDSA. Similarly, CodeWorkout is an open source system which helps students to practice small programming problems. Mastery Grids is also open source progress visualization environment which has open (social) learner model features designed at the University of Pittsburgh. In this project, we extended contents served by Mastery Grids by integrating CodeWorkout exercises and visualize student progress in an Open Learner Model. All of this has been possible because all of these tools support LTI, reiterating the importance of why the utilization of standards while developing applications is important. 

   more » « less
3. Concept-Level Design Analytics for Blended Courses

   https://doi.org/10.1007/978-3-030-29736-7_40  

   Albó, Laia; Barria-Pineda, Jordan; Brusilovsky, Peter; Hernández-Leo, Davinia (September 2019, Proceedings of 14th European Conference on Technology Enhanced Learning (EC-TEL 2019))

   Although many efforts are being made to provide educators with dashboards and tools to understand student behaviors within specific technological environments (learning analytics), there is a lack of work in supporting educators in making data-informed design decisions when designing a blended course and planning learning activities. In this paper, we introduce concept-level design analytics, a knowledge-based visualization, which uncovers facets of the learning activities that are being authored. The visualization is integrated into a (blended) learning design authoring tool, edCrumble. This new approach is explored in the context of a higher education programming course, where teaching assistants design labs and home practice sessions with online smart learning content on a weekly basis. We performed a within-subjects user study to compare the use of the design tool both with and without the visualization. We studied the differences in terms of cognitive load, design outcomes and user actions within the system to compare both conditions to the objective of evaluating the impact of using design analytics during the decision-making phase of course design. 

   more » « less
4. Animation Analytics in an Interactive Textbook for Material and Energy Balances

   Stone, S. J.; Crockett, B.; Xu, Kevin S.; Liberatore, M. W. (August 2022, ASEE Annual Conference proceedings)

   Interactive textbooks generate big data through student reading participation, including animations, question sets, and auto-graded homework. Animations are multi-step, dynamic visuals with text captions. By dividing new content into smaller chunks of information, student engagement is expected to be high, which aligns with tenets of cognitive load theory. Specifically, students’ clicks are recorded and measure usage, completion, and view time per step and for entire animations. Animation usage data from an interactive textbook for a chemical engineering course in Material and Energy Balances accounts for 60,000 animation views across 140+ unique animations. Data collected across five cohorts between 2016 and 2020 used various metrics to capture animation usage including watch and re-watch rates as well as the length of animation views. Variations in view rate and time were examined across content, parsed by book chapter, and five animation characterizations (Concept, Derivation, Figures and Plots, Physical World, and Spreadsheets). Important findings include: 1) Animation views were at or above 100% for all chapters and cohorts, 2) Median view time varies from 22 s (2-step) to 59 s (6-step) - a reasonable attention span for students and cognitive load, 3) Median view time for animations characterized as Derivation was the longest (40 s) compared to Physical World animations, which resulted in the shortest time (20 s). 

   more » « less
5. Marauder: Synergized Caching and Prefetching for Low-Risk Mobile App Acceleration

   https://doi.org/10.1145/3458864.3466866  

   Ramanujam, Murali; Madhyastha, Harsha V.; Netravali, Ravi (June 2021, 19th Annual International Conference on Mobile Systems, Applications, and Services)

   Low interaction response times are crucial to the experience that mobile apps provide for their users. Unfortunately, existing strategies to alleviate the network latencies that hinder app responsiveness fall short in practice. In particular, caching is plagued by challenges in setting expiration times that match when a resource's content changes, while prefetching hinges on accurate predictions of user behavior that have proven elusive. We present Marauder, a system that synergizes caching and prefetching to improve the speedups achieved by each technique while avoiding their inherent limitations. Key to Marauder is our observation that, like web pages, apps handle interactions by downloading and parsing structured text resources that entirely list (i.e., without needing to consult app binaries) the set of other resources to load. Building on this, Marauder introduces two low-risk optimizations directly from the app's cache. First, guided by cached text files, Marauder prefetches referenced resources during an already-triggered interaction. Second, to improve the efficacy of cached content, Marauder judiciously prefetches about-to-expire resources, extending cache lives for unchanged resources, and downloading updates for lightweight (but crucial) text files. Across a wide range of apps, live networks, interaction traces, and phones, Marauder reduces median and 90th percentile interaction response times by 27.4% and 43.5%, while increasing data usage by only 18%. 

   more » « less