Analytics of Software, GAmes And Repository Data (ASGAARD) lab's repositories
CLIPxGamePhysics
This repository will contain code for the paper "CLIP meets GamePhysics: Towards bug identification in gameplay videos using zero-shot transfer learning"
canvas-visual-bugs-testbed
Visual testing framework for PixiJS applications
21-markos-test_case_similarity_technique-code
Repository with the source code of our technique to analyze a test suite and find similar test cases written in natural language
21-markos-test_case_improvement_framework-code
Repository with the source code of our experiments for an automated NLP-based framework to improve test cases written in natural language
done-20-markos-dota2_win_prediction-code
Project to investigate win prediction models for Dota 2 and factors that explain such predictions
dota2-prediction-models
Repository with code for building, evaluating and explaining Dota 2 prediction models for team victory. Submitted to the artifact evaluation track of the 16th AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment - AIIDE 2020
done-21-arthur-gamedev_qa_websites-code
Replication package for the paper "An Empirical Study of Q&A Websites for Game Developers"
MLBindings
Replication package for the paper "Bridging the Language Gap: An Empirical Study of Bindings for Open Source Machine Learning Libraries in Software Package Ecosystems"
natural-language-test-prioritization
Repository with the source code of our experiments for a multi-objective prioritization approach to optimize the execution of natural language test cases of a game.
sentiment-analysis-Steam_reviews
Repository with data from our study on the causes for misclassifications Steam game reviews
done-21-arthur-duplicate_gamedev_questions-code
Replication package for the paper "Analyzing techniques for duplicate detection on Q&A websites for game development"
echotest-benchmark
Files necessary for creating benchmark videos for EchoTest in Unity
OverfitGuard
Replication package of the paper "Keeping Deep Learning Models in Check: A History-Based Approach to Mitigate Overfitting"
dataset-and-model-management
An Exploratory Study of Dataset and Model Management in Open Source Machine Learning Applications