Bridging the Physical and the Digital Worlds of Learning Analytics in Educational Assessments through Human-AI Collaboration

187457-Thumbnail Image.png
Description
Experience, whether personal or vicarious, plays an influential role in shaping human knowledge. Through these experiences, one develops an understanding of the world, which leads to learning. The process of gaining knowledge in higher education transcends beyond the passive transmission

Experience, whether personal or vicarious, plays an influential role in shaping human knowledge. Through these experiences, one develops an understanding of the world, which leads to learning. The process of gaining knowledge in higher education transcends beyond the passive transmission of knowledge from an expert to a novice. Instead, students are encouraged to actively engage in every learning opportunity to achieve mastery in their chosen field. Evaluation of such mastery typically entails using educational assessments that provide objective measures to determine whether the student has mastered what is required of them. With the proliferation of educational technology in the modern classroom, information about students is being collected at an unprecedented rate, covering demographic, performance, and behavioral data. In the absence of analytics expertise, stakeholders may miss out on valuable insights that can guide future instructional interventions, especially in helping students understand their strengths and weaknesses. This dissertation presents Web-Programming Grading Assistant (WebPGA), a homegrown educational technology designed based on various learning sciences principles, which has been used by 6,000+ students. In addition to streamlining and improving the grading process, it encourages students to reflect on their performance. WebPGA integrates learning analytics into educational assessments using students' physical and digital footprints. A series of classroom studies is presented demonstrating the use of learning analytics and assessment data to make students aware of their misconceptions. It aims to develop ways for students to learn from previous mistakes made by themselves or by others. The key findings of this dissertation include the identification of effective strategies of better-performing students, the demonstration of the importance of individualized guidance during the reviewing process, and the likely impact of validating one's understanding of another's experiences. Moreover, the Personalized Recommender of Items to Master and Evaluate (PRIME) framework is introduced. It is a novel and intelligent approach for diagnosing one's domain mastery and providing tailored learning opportunities by allowing students to observe others' mistakes. Thus, this dissertation lays the groundwork for further improvement and inspires better use of available data to improve the quality of educational assessments that will benefit both students and teachers.
Date Created
2023
Agent

Automatic Programming Code Explanation Generation with Structured Translation Models

158027-Thumbnail Image.png
Description
Learning programming involves a variety of complex cognitive activities, from abstract knowledge construction to structural operations, which include program design,modifying, debugging, and documenting tasks. In this work, the objective was to explore and investigate the barriers and obstacles that programming

Learning programming involves a variety of complex cognitive activities, from abstract knowledge construction to structural operations, which include program design,modifying, debugging, and documenting tasks. In this work, the objective was to explore and investigate the barriers and obstacles that programming novice learners encountered and how the learners overcome them. Several lab and classroom studies were designed and conducted, the results showed that novice students had different behavior patterns compared to experienced learners, which indicates obstacles encountered. The studies also proved that proper assistance could help novices find helpful materials to read. However, novices still suffered from the lack of background knowledge and the limited cognitive load while learning, which resulted in challenges in understanding programming related materials, especially code examples. Therefore, I further proposed to use the natural language generator (NLG) to generate code explanations for educational purposes. The natural language generator is designed based on Long Short Term Memory (LSTM), a deep-learning translation model. To establish the model, a data set was collected from Amazon Mechanical Turks (AMT) recording explanations from human experts for programming code lines.

To evaluate the model, a pilot study was conducted and proved that the readability of the machine generated (MG) explanation was compatible with human explanations, while its accuracy is still not ideal, especially for complicated code lines. Furthermore, a code-example based learning platform was developed to utilize the explanation generating model in programming teaching. To examine the effect of code example explanations on different learners, two lab-class experiments were conducted separately ii in a programming novices’ class and an advanced students’ class. The experiment result indicated that when learning programming concepts, the MG code explanations significantly improved the learning Predictability for novices compared to control group, and the explanations also extended the novices’ learning time by generating more material to read, which potentially lead to a better learning gain. Besides, a completed correlation model was constructed according to the experiment result to illustrate the connections between different factors and the learning effect.
Date Created
2020
Agent

Constructing Knowledge Graph for Cybersecurity Education

156851-Thumbnail Image.png
Description
There currently exist various challenges in learning cybersecuirty knowledge, along with a shortage of experts in the related areas, while the demand for such talents keeps growing. Unlike other topics related to the computer system such as computer architecture and

There currently exist various challenges in learning cybersecuirty knowledge, along with a shortage of experts in the related areas, while the demand for such talents keeps growing. Unlike other topics related to the computer system such as computer architecture and computer network, cybersecurity is a multidisciplinary topic involving scattered technologies, which yet remains blurry for its future direction. Constructing a knowledge graph (KG) in cybersecurity education is a first step to address the challenges and improve the academic learning efficiency.

With the advancement of big data and Natural Language Processing (NLP) technologies, constructing large KGs and mining concepts, from unstructured text by using learning methodologies, become possible. The NLP-based KG with the semantic similarity between concepts has brought inspiration to different industrial applications, yet far from completeness in the domain expertise, including education in computer science related fields.

In this research work, a KG in cybersecurity area has been constructed using machine-learning-based word embedding (i.e., mapping a word or phrase onto a vector of low dimensions) and hyperlink-based concept mining from the full dataset of words available using the latest Wikipedia dump. The different approaches in corpus training are compared and the performance based on different similarity tasks is evaluated. As a result, the best performance of trained word vectors has been applied, which is obtained by using Skip-Gram model of Word2Vec, to construct the needed KG. In order to improve the efficiency of knowledge learning, a web-based front-end is constructed to visualize the KG, which provides the convenience in browsing related materials and searching for cybersecurity-related concepts and independence relations.
Date Created
2018
Agent

A Visual Analytics Process for Exploring Risk and Vulnerability in International Food Trade Networks

155940-Thumbnail Image.png
Description
The rise in globalization has led to regional climate events having an increased effect on global food security. These indirect first- and second-order effects are generally geographically disparate from the region experiencing the climate event. Without understanding the topology of

The rise in globalization has led to regional climate events having an increased effect on global food security. These indirect first- and second-order effects are generally geographically disparate from the region experiencing the climate event. Without understanding the topology of the food trade network, international aid may be naively directed to the countries directly experiencing the climate event and not to countries that will face potential food insecurity due to that event. This thesis focuses on the development of a visual analytics system for exploring second-order effects of climate change under the lens of global trade. In order to visualize how climate change impacts the world trade network of agricultural goods I have developed an interactive data visualization platform for analysis of the interaction between climate events and the trade network. The proposed visual analytics system focuses on visualizing current trade dependencies at a more granular level than the currently available tools and to aid in the identification of future vulnerabilities. To demonstrate the applicability of the tool, two case studies are described. The first case study focuses on the Chinese drought of 2011 and its impact on the global trade network and food security. The second case study will model the potential impact of a climate event affecting production in the United States, a large supplier of corn, to demonstrate the potential consequence of cascading effects in the global trade network.
Date Created
2017
Agent

Behavioral Pattern Mining and Modeling in Programming Problem Solving

155923-Thumbnail Image.png
Description
Online learning platforms such as massive online open courses (MOOCs) and

intelligent tutoring systems (ITSs) have made learning more accessible and personalized. These systems generate unprecedented amounts of behavioral data and open the way for predicting students’ future performance based on

Online learning platforms such as massive online open courses (MOOCs) and

intelligent tutoring systems (ITSs) have made learning more accessible and personalized. These systems generate unprecedented amounts of behavioral data and open the way for predicting students’ future performance based on their behavior, and for assessing their strengths and weaknesses in learning.

This thesis attempts to mine students’ working patterns using a programming problem solving system, and build predictive models to estimate students’ learning. QuizIT, a programming solving system, was used to collect students’ problem-solving activities from a lower-division computer science programming course in 2016 Fall semester. Differential mining techniques were used to extract frequent patterns based on each activity provided details about question’s correctness, complexity, topic, and time to represent students’ behavior. These patterns were further used to build classifiers to predict students’ performances.

Seven main learning behaviors were discovered based on these patterns, which provided insight into students’ metacognitive skills and thought processes. Besides predicting students’ performance group, the classification models also helped in finding important behaviors which were crucial in determining a student’s positive or negative performance throughout the semester.
Date Created
2017
Agent

Learning Object Oriented Programming Using Augmented Reality - A Case Study with Elementary School Students

155754-Thumbnail Image.png
Description
There is a demanding need to empower students from kindergarten through high school to learn computer science and be equipped with the computational thinking skills that they need in today's technology driven world. However, introducing computer programming to students can

There is a demanding need to empower students from kindergarten through high school to learn computer science and be equipped with the computational thinking skills that they need in today's technology driven world. However, introducing computer programming to students can be challenging, especially for those who aren't familiar with the nuances of code. Several popular tools are used in curriculum for K-12 students which utilize interactive and visualization approaches to engage young kids in learning computational concepts. Possibilities of using Augmented Reality (AR) in teaching programming to novices are explored in this work.

In this thesis Ogmented, an AR application is designed which includes interactive learning material that covers a range of fundamental Object-Oriented Programming (OOP) concepts. This work aims to exploit the idea to learn abstract concepts via AR by capitalizing the strength of visual-aided and interactive elements. A user study with a group of elementary school students is conducted. It explored how students operated the AR application with the interactive elements and how they wrote codes to solve programming problems. It was observed that students who followed instructions while taking tutorials were successfully able to write fragments of codes in exercise modules. Irrespective of their knowledge about programming, majority of students were able to write executable code snippets for concepts they were taught with use of Ogmented. This shares an initial insight on using AR in classroom to teach abstract programming concepts.
Date Created
2017
Agent

CodeReco - A Semantic Java Method Recommender

155690-Thumbnail Image.png
Description
The increasing volume and complexity of software systems and the growing demand of programming skills calls for efficient information retrieval techniques from source code documents. Programming related information seeking is often challenging for users facing constraints in knowledge and experience.

The increasing volume and complexity of software systems and the growing demand of programming skills calls for efficient information retrieval techniques from source code documents. Programming related information seeking is often challenging for users facing constraints in knowledge and experience. Source code documents contain multi-faceted semi-structured text, having different levels of semantic information like syntax, blueprints, interfaces, flow graphs, dependencies and design patterns. Matching user queries optimally across these levels is a major challenge for information retrieval systems. Code recommendations can help information seeking and retrieval by pro-actively sampling similar examples based on the users context. These recommendations can be beneficial in improving learning via examples or improving code quality by sampling best practices or alternative implementations.

In this thesis, an attempt is made to help programming related information seeking processes via pro-active code recommendations, and information retrieval processes by extracting structural-semantic information from source code. I present CodeReco, a system that recommends semantically similar Java method samples. Conventional code recommendations found in integrated development environments are primarily driven by syntactical compliance and auto-completion, whereas CodeReco is driven by similarities in use of language and structure-semantics. Methods are transformed to a vector space model and a novel metric of similarity is designed. Features in this vector space are categorized as belonging to types signature, structure, concept and language for user personalization.

Offline tests show that CodeReco recommendations cover broader programming concepts and have higher conceptual similarity with their samples. A user study was conducted where users rated Java method recommendations that helped them icomplete two programming problems. 61.5% users were positive that real time method recommendations are helpful, and 50% reported this would reduce time spent in web searches. The empirical utility of CodeReco’s similarity metric on those problems was compared with a purely language based similarity metric (baseline). Baseline received higher ratings from novices, arguably due to lack of structure-semantics in their samples while seeking recommendations.
Date Created
2017
Agent

Web-Based Programming Grading Assistant: An Investigation of the Role of Students Reviewing Behavior

155689-Thumbnail Image.png
Description
Paper assessment remains to be an essential formal assessment method in today's classes. However, it is difficult to track student learning behavior on physical papers. This thesis presents a new educational technology—Web Programming Grading Assistant (WPGA). WPGA not only serves

Paper assessment remains to be an essential formal assessment method in today's classes. However, it is difficult to track student learning behavior on physical papers. This thesis presents a new educational technology—Web Programming Grading Assistant (WPGA). WPGA not only serves as a grading system but also a feedback delivery tool that connects paper-based assessments to digital space. I designed a classroom study and collected data from ASU computer science classes. I tracked and modeled students' reviewing and reflecting behaviors based on the use of WPGA. I analyzed students' reviewing efforts, in terms of frequency, timing, and the associations with their academic performances. Results showed that students put extra emphasis in reviewing prior to the exams and the efforts demonstrated the desire to review formal assessments regardless of if they were graded for academic performance or for attendance. In addition, all students paid more attention on reviewing quizzes and exams toward the end of semester.
Date Created
2017
Agent

Bridging cyber and physical programming classes: an application of semantic visual analytics for programming exams

154605-Thumbnail Image.png
Description
With the advent of Massive Open Online Courses (MOOCs) educators have the opportunity to collect data from students and use it to derive insightful information about the students. Specifically, for programming based courses the ability to identify the specific areas

With the advent of Massive Open Online Courses (MOOCs) educators have the opportunity to collect data from students and use it to derive insightful information about the students. Specifically, for programming based courses the ability to identify the specific areas or topics that need more attention from the students can be of immense help. But the majority of traditional, non-virtual classes lack the ability to uncover such information that can serve as a feedback to the effectiveness of teaching. In majority of the schools paper exams and assignments provide the only form of assessment to measure the success of the students in achieving the course objectives. The overall grade obtained in paper exams and assignments need not present a complete picture of a student’s strengths and weaknesses. In part, this can be addressed by incorporating research-based technology into the classrooms to obtain real-time updates on students' progress. But introducing technology to provide real-time, class-wide engagement involves a considerable investment both academically and financially. This prevents the adoption of such technology thereby preventing the ideal, technology-enabled classrooms. With increasing class sizes, it is becoming impossible for teachers to keep a persistent track of their students progress and to provide personalized feedback. What if we can we provide technology support without adding more burden to the existing pedagogical approach? How can we enable semantic enrichment of exams that can translate to students' understanding of the topics taught in the class? Can we provide feedback to students that goes beyond only numbers and reveal areas that need their focus. In this research I focus on bringing the capability of conducting insightful analysis to paper exams with a less intrusive learning analytics approach that taps into the generic classrooms with minimum technology introduction. Specifically, the work focuses on automatic indexing of programming exam questions with ontological semantics. The thesis also focuses on designing and evaluating a novel semantic visual analytics suite for in-depth course monitoring. By visualizing the semantic information to illustrate the areas that need a student’s focus and enable teachers to visualize class level progress, the system provides a richer feedback to both sides for improvement.
Date Created
2016
Agent