Learning Curve Analysis for Programming

Rivers, Kelly; Harpstead, Erik; Koedinger, Ken

doi:10.1145/2960310.2960333

Cited by 52 publications

(42 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In programming, this includes recording program versions that are not considered finished, enabling a process-oriented analysis. Applications for textbased programming include large-scale investigations of programming mistakes in the BlueJ programming environment [17], clustering of program versions of novice programmers solving a specific problem [18], investigations of a state model for programming behaviour [19], and learning curve analysis for programming concepts [20].…”

Section: Related Workmentioning

confidence: 99%

Towards the Use of Slice-based Cohesion Metrics with Learning Analytics to Assess Programming Skills

Kesselbacher

Bollin

2021

2021 Third International Workshop on Software Engineering Education for the Next Generation (SEENG)

View full text Add to dashboard Cite

In programming education, it makes a difference whether you are dealing with beginners or advanced students. As our future students will become even more tech-savvy, it is necessary to assess programming skills appropriately and quickly to protect them from boredom and optimally support the learning process. In this work, we advocate for the use of slice-based cohesion metrics to assess the process of program construction in a learning analytics setting. We argue that semantically related parts during program construction are an essential part of programming skills. Therefore, we propose using cohesion metrics on the level of variables to identify programmers' trains of thought based on the cohesion of semantically related parts during program construction.

show abstract

Section: Related Workmentioning

confidence: 99%

Towards the Use of Slice-based Cohesion Metrics with Learning Analytics to Assess Programming Skills

Kesselbacher

Bollin

2021

2021 Third International Workshop on Software Engineering Education for the Next Generation (SEENG)

View full text Add to dashboard Cite

show abstract

“…This concept is relatively easy to learn since the initial error rate is 0.63, which after five more attempts, decreases to 0.23. Like Rivers et al [231], the evidence shows that students learned how to use any function call and are not learning different concepts for every new function. The learning curves from all high-quality concepts are steeper than those in the other two categories, showing more and faster learning.…”

Section: Cognitive Validitymentioning

confidence: 62%

“…Rivers et al [231] applied learning curve analysis to programming data to determine which programming elements students struggle with the most when learning Python. The analyzed KCs were extracted automatically from the Python Abstract Syntax Tree.…”

Section: Related Workmentioning

confidence: 99%

“…Each activity is designed to train one or more KCs related to Python programming. The conceptual model 2 was automatically derived using the Python parser (similar to Rivers et al [231]). In MG, there are five types of learning activities; however, only two are considered problem-solving activities with an adequate level of difficulty.…”

Section: Datamentioning

confidence: 99%

“…A deeper analysis can be done by classifying the learning curves. Rivers et al [231] use five categories: little-data (not enough data), already-learned (start and end with low error rates), no-learning (start and end with high error rates and no downward trend), still-learning (start and end with high error rates with a downward trend), and good-learning (start high but end with low error rates). With this classification, there are two learning curves classified as no-learning ("exception" and Section 6.4 -Results and Analysis | 127 "iteration").…”

Section: Cognitive Validitymentioning

confidence: 99%

See 2 more Smart Citations

Extraction of Knowledge Models from Textbooks

Chacón¹

View full text Add to dashboard Cite

Many adaptive educational systems and other artificial intelligence applications rely on high-quality knowledge representations. Still, knowledge acquisition remains the primary bottleneck hindering large-scale deployment and adoption of knowledge-based systems. One path to scalable knowledge extraction is using digital textbooks, given their domain-oriented content, structure, and availability. This dissertation presents a unified approach for automatically extracting high-quality and domain-specific knowledge models from digital textbooks. The proposed approach leverages the authors’ knowledge encoded in the textbooks’ elements that facilitate navigation and understanding of the material (table of contents, index, formatting styles) to create knowledge models. The proposed workflow first extracts initial information elements from the textbooks: the structure of chapters and subchapters using the Table of Content, the content of each section, and domain terminology from the back-of-the-book index. Then, new information is added: domain terms are linked to external entities in a knowledge graph (DBpedia) and are enriched with semantic content (e.g., abstracts and categories). Finally, the knowledge about the domain is refined by identifying the relevance of concepts to the target domain. The extracted knowledge is represented in a model using the Text Encoding Initiative. Multiple evaluations show that the extracted knowledge models have high levels of quality across several properties: accuracy, semantics, coverage, specificity, cognitive validity, and granularity. Additionally, the approach is effective in multiple domains—for example, statistics, ancient philosophy, and Python programming. Finally, there are many potential applications for the extracted knowledge models. This dissertation presents three different educational systems supported by the knowledge models.

show abstract

Better Model, Worse Predictions: The Dangers in Student Model Comparisons

Cechak

Pelánek

2021

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Learning Curve Analysis for Programming

Cited by 52 publications

References 15 publications

Towards the Use of Slice-based Cohesion Metrics with Learning Analytics to Assess Programming Skills

Towards the Use of Slice-based Cohesion Metrics with Learning Analytics to Assess Programming Skills

Extraction of Knowledge Models from Textbooks

Better Model, Worse Predictions: The Dangers in Student Model Comparisons

Contact Info

Product

Resources

About