CSI for Computer Science Education

CS Ed Visual Analytics: the system empowers students to track on programming learning performances in semantic level. We integrate online quizzes performances and in-class quizzes and exams' semantic information in order to provide detailed and personalized feedback to students. Aim to remind students don't just focus on "scores" but look beyond the question-answers-and-scores, become responsible to their learning.

Publication: LAK'16, ICALT'16, Computers in Human Behavior'16

Navigation Support for Online Discussion Forums: Online programming communities are widely used by programmers for troubleshooting or various problem solving tasks. Large and ever increasing volume of posts on these communities demands more efforts to read and comprehend thus making it harder to find relevant information. We designed and studied an alternate approach by using interactive network visualization to represent relevant search results for online programming discussion forums. Results show that users were able to identify relevant information more precisely via visual interface as compared to traditional list based approach. Network visualization demonstrated effective search-result navigation support to facilitate user’s tasks and improved query quality for successive queries. Subjective evaluation also showed that visualizing search results conveys more semantic information in efficient manner and makes searching more effective.

Predictive Modeling in Programming Discussion Forums: The massive volumes of forum threads harbor tremendous amounts of information, but at the same time increase the complexity of search and navigation. In this project, we make use of programming discussions’ syntactic, semantic and social features to model content associated with learning activities based on the ICAP learning framework attempting to detect useful content for learning programming in a large scale of questions and answers, while at the same time experiment with an artificial intelligence to detect learning-inductive content.

Publication: LAK'15, CSCL'15

Programming Information Seeking Assistant: Online programming discussion forums have grown increasingly and have formed sizable repositories of problem solving-solutions. We investigate programming learners’ information seeking behaviors from online discussion forums. We design engines to collect students’ information seeking processes, including query formulation, refinement, results examination, and reading processes. We model these behaviors and conduct sequence pattern mining.

Publication: EDM'16, ICALT'16, HT'18

Social Interaction Pattern Mining in Online Discussion Forums: We apply multiple sentiment analyses on discussion forum comments. We data mine social interaction patterns and engineer features to automatically predict post content goodness. Publication: HT'16

Programming Grading Assistant (PGA):

We design an auto-grading mobile application, which explores several computational techniques and attempts to solve a real world problem - grading mass paper-based programming exams. We design, develop and evaluate several algorithms: hand-written code recognition, mixed printed and hand-written code recognition, adaptive recognition algorithm, semi-auto grading and auto-grading algorithms. The tool is designed to harness multi facets of learning analytics from physical to digital spaces.

Publication: ECTEL'16 [link][slides]; SIGCSE'17

Web Programming Grading Assistant (WPGA):

It is a web-based grading platform that:

+ supports mass grading paper-based quizzes or exams;

+ harnesses multi facets of learning analytics from physical to digital space;

+ delivers efficient and rich feedback to students;

+ enhances graders' grading coherence and efficiency.

[more detail...]

Publication: LAK'17, CROSS-LAK'17, TETC'17, EC-TEL'18, ICCE'18

CS (Exam) StudyGuide Genie: we design an intelligent web service to adaptively guide students prepare for CS exams and monitor their learning processes. StudyGuide Genie provides students interfaces to gather notes and actively monitor their learning.

Publication: ICALT'16

Quiz of the day: we design a platform that allows students to sign up receiving daily programming quiz from us. We apply distributed and reflective practices strategy to help students get exposed to programming concepts & problem-solving everyday. If you are interested in this, we welcome you to shoot us an email, contact PI: Dr. Hsiao directly.

+ supports multiple choices quizzes authoring, delivery, and self-assessment;

+ provides voluntary daily quiz and distributed and reflective practices;

+ embeds multiple visual analytics (social, progress, knowledge-based);

+ offers adaptive readings/quizzes recommendations, peer feedback.

Publication: FIE'17, CSEDM'18, FIE'18, LAK'19, SIGCSE'20

Ogmented: we design a visual and textual integrated programming environment with Augmented Reality (AR). The goal is to contextualize the abstract concepts by creating, modifying and interacting with AR objects through the learning and programming process. If you are interested in this, we welcome you to shoot us an email, contact PI: Dr. Hsiao directly.

Publication: IUI'19, iLRN'20