God Class Research Articles

Improving accuracy of code smells detection using machine learning with data balancing techniques

Code smells indicate potential symptoms or problems in software due to inefficient design or incomplete implementation. These problems can affect software quality in the long-term. Code smell detection is fundamental to improving software quality and maintainability, reducing software failure risk, and helping to refactor the code. Previous works have applied several prediction methods for code smell detection. However, many of them show that machine learning (ML) and deep learning (DL) techniques are not always suitable for code smell detection due to the problem of imbalanced data. So, data imbalance is the main challenge for ML and DL techniques in detecting code smells. To overcome these challenges, this study aims to present a method for detecting code smell based on DL algorithms (Bidirectional Long Short-Term Memory (Bi-LSTM) and Gated Recurrent Unit (GRU)) combined with data balancing techniques (random oversampling and Tomek links) to mitigate data imbalance issue. To establish the effectiveness of the proposed models, the experiments were conducted on four code smells datasets (God class, data Class, feature envy, and long method) extracted from 74 open-source systems. We compare and evaluate the performance of the models according to seven different performance measures accuracy, precision, recall, f-measure, Matthew’s correlation coefficient (MCC), the area under a receiver operating characteristic curve (AUC), the area under the precision–recall curve (AUCPR) and mean square error (MSE). After comparing the results obtained by the proposed models on the original and balanced data sets, we found out that the best accuracy of 98% was obtained for the Long method by using both models (Bi-LSTM and GRU) on the original datasets, the best accuracy of 100% was obtained for the long method by using both models (Bi-LSTM and GRU) on the balanced datasets (using random oversampling), and the best accuracy 99% was obtained for the long method by using Bi-LSTM model and 99% was obtained for the data class and Feature envy by using GRU model on the balanced datasets (using Tomek links). The results indicate that the use of data balancing techniques had a positive effect on the predictive accuracy of the models presented. The results show that the proposed models can detect the code smells more accurately and effectively.

Optimizing LSTM for Code Smell Detection: The Role of Data Balancing

Code smells are specific patterns or characteristics in software code that indicate potential design or implementation problems. Identifying code smells has gained significant attention in software engineering. It is essential to address code smells to maintain high-quality software systems. Machine learning (ML) models, such as Long Short-Term Memory (LSTM), have been to detect code smells automatically based on source code features. However, the imbalanced distribution of code smells within software projects poses a challenge to the accuracy of these models. This study explores the role of data balancing methods in optimizing the accuracy of the LSTM model for code smell detection. We investigate different techniques for addressing the class imbalance problem, including random oversampling and synthetic minority oversampling techniques (SMOTE). We evaluate the performance of the LSTM model with and without data balancing methods using accuracy, precision, recall, f-measure, Matthew’s correlation coefficient (MCC), and the area under a receiver operating characteristic curve (AUC). Our experimental results, conducted on four code smell datasets (God class, data class, feature envy, and long method) extracted from 74 open-source systems, demonstrate the effectiveness of data balancing methods in improving the accuracy of the LSTM model for code smell detection. The results indicate that the use of data balancing methods had a positive effect on the predictive accuracy of the LSTM model. In addition, we compared our proposed method with state-of-the-art code smell detection approaches. The findings from the comparison indicate that our proposed method performs notably better than existing state-of the-art approaches across the majority of datasets.

Boosting and Comparing Performance of Machine Learning Classifiers with Meta-heuristic Techniques to Detect Code Smell

Background: Continuous modifications, suboptimal software design practices, and stringent project deadlines contribute to the proliferation of code smells. Detecting and refactoring these code smells are pivotal to maintaining complex and essential software systems. Neglecting them may lead to future software defects, rendering systems challenging to maintain, and eventually obsolete. Supervised machine learning techniques have emerged as valuable tools for classifying code smells without needing expert knowledge or fixed threshold values. Further enhancement of classifier performance can be achieved through effective feature selection techniques and the optimization of hyperparameter values. Aim: Performance measures of multiple machine learning classifiers are improved by fine tuning its hyperparameters using various type of meta-heuristic algorithms including swarm intelligent, physics, math, and bio-based etc. Their performance measures are compared to find the best meta-heuristic algorithm in the context of code smell detection and its impact is evaluated based on statistical tests. Method: This study employs sixteen contemporary and robust meta-heuristic algorithms to optimize the hyperparameters of two machine learning algorithms: Support Vector Machine (SVM) and k-nearest Neighbors (k-NN). The No Free Lunch theorem underscores that the success of an optimization algorithm in one application may not necessarily extend to others. Consequently, a rigorous comparative analysis of these algorithms is undertaken to identify the best-fit solutions for code smell detection. A diverse range of optimization algorithms, encompassing Arithmetic, Jellyfish Search, Flow Direction, Student Psychology Based, Pathfinder, Sine Cosine, Jaya, Crow Search, Dragonfly, Krill Herd, Multi-Verse, Symbiotic Organisms Search, Flower Pollination, Teaching Learning Based, Gravitational Search, and Biogeography-Based Optimization, have been implemented. Results: In the case of optimized SVM, the highest attained accuracy, AUC, and F-measure values are 98.75%, 100%, and 98.57%, respectively. Remarkably, significant increases in accuracy and AUC, reaching 32.22% and 45.11% respectively, are observed. For k-NN, the best accuracy, AUC, and F-measure values are all perfect at 100%, with noteworthy hikes in accuracy and ROC-AUC values, amounting to 43.89% and 40.83%, respectively. Conclusion: Optimized SVM exhibits exceptional performance with the Sine Cosine Optimization algorithm, while k-NN attains its peak performance with the Flower Optimization algorithm. Statistical analysis underscores the substantial impact of employing meta-heuristic algorithms for optimizing machine learning classifiers, enhancing their performance significantly. Optimized SVM excels in detecting the God Class, while optimized k-NN is particularly effective in identifying the Data Class. This innovative fusion automates the tuning process and elevates classifier performance, simultaneously addressing multiple longstanding challenges.

Code smells in pull requests: An exploratory study

AbstractThe quality of a pull request is the primary factor integrators consider for its acceptance or rejection. Code smells indicate sub‐optimal design or implementation choices in the source code that often lead to a fault‐prone outcome, threatening the quality of pull requests. This study explores code smells in 21k pull requests from 25 popular Java projects. We find that both accepted (37%) and rejected (44%) pull requests have code smells, affected mainly by god classes and long methods. Besides, we observe that smelly pull requests are more complex and challenging to understand as they have significantly large sizes, long latency times, more discussion and review comments, and are submitted by contributors with less experience. Our results show that features used in previous studies for pull request acceptance prediction could be potentially employed to predict smell in incoming pull requests. We propose a dynamic approach to predict the presence of such code smells in the newly added pull requests. We evaluate our approach on a dataset of 25 Java projects extracted from GitHub. We further conduct a benchmark study to compare the performance of eight machine learning classifiers. Results of the benchmark study show that XGBoost is the best‐performing classifier for smell prediction.

A study of dealing class imbalance problem with machine learning methods for code smell severity detection using PCA-based feature selection technique

Detecting code smells may be highly helpful for reducing maintenance costs and raising source code quality. Code smells facilitate developers or researchers to understand several types of design flaws. Code smells with high severity can cause significant problems for the software and may cause challenges for the system's maintainability. It is quite essential to assess the severity of the code smells detected in software, as it prioritizes refactoring efforts. The class imbalance problem also further enhances the difficulties in code smell severity detection. In this study, four code smell severity datasets (Data class, God class, Feature envy, and Long method) are selected to detect code smell severity. In this work, an effort is made to address the issue of class imbalance, for which, the Synthetic Minority Oversampling Technique (SMOTE) class balancing technique is applied. Each dataset's relevant features are chosen using a feature selection technique based on principal component analysis. The severity of code smells is determined using five machine learning techniques: K-nearest neighbor, Random forest, Decision tree, Multi-layer Perceptron, and Logistic Regression. This study obtained the 0.99 severity accuracy score with the Random forest and Decision tree approach with the Long method code smell. The model's performance is compared based on its accuracy and three other performance measurements (Precision, Recall, and F-measure) to estimate severity classification models. The impact of performance is also compared and presented with and without applying SMOTE. The results obtained in the study are promising and can be beneficial for paving the way for further studies in this area.

A Systematic Literature Review on the Code Smells Datasets and Validation Mechanisms

The accuracy reported for code smell-detecting tools varies depending on the dataset used to evaluate the tools. Our survey of 45 existing datasets reveals that the adequacy of a dataset for detecting smells highly depends on relevant properties such as the size, severity level, project types, number of each type of smell, number of smells, and the ratio of smelly to non-smelly samples in the dataset. Most existing datasets support God Class, Long Method, and Feature Envy, while six smells in Fowler and Beck's catalog are not supported by any datasets. We conclude that existing datasets suffer from imbalanced samples, lack of supporting severity level, and restriction to Java language.

Code Smell Detection Using Ensemble Machine Learning Algorithms

Code smells are the result of not following software engineering principles during software development, especially in the design and coding phase. It leads to low maintainability. To evaluate the quality of software and its maintainability, code smell detection can be helpful. Many machine learning algorithms are being used to detect code smells. In this study, we applied five ensemble machine learning and two deep learning algorithms to detect code smells. Four code smell datasets were analyzed: the Data class, the God class, the Feature-envy, and the Long-method datasets. In previous works, machine learning and stacking ensemble learning algorithms were applied to this dataset and the results found were acceptable, but there is scope of improvement. A class balancing technique (SMOTE) was applied to handle the class imbalance problem in the datasets. The Chi-square feature extraction technique was applied to select the more relevant features in each dataset. All five algorithms obtained the highest accuracy—100% for the Long-method dataset with the different selected sets of metrics, and the poorest accuracy, 91.45%, was achieved by the Max voting method for the Feature-envy dataset for the selected twelve sets of metrics.

Prioritization of god class design smell: A multi-criteria based approach

Context: Design smell Prioritization is a significant activity that tunes the process of software quality enhancement and raises its life cycle. Objective: A multi-criteria merge strategy for Design Smell prioritization is described. The strategy is exemplified with the case of God Class Design Smell. Method: An empirical adjustment of the strategy is performed using a dataset of 24 open source projects. Empirical evaluation was conducted in order to check how is the top ranked God Classes obtained by the proposed technique compared against the top ranked God class according to the opinion of developers involved in each of the projects in the dataset. Results: Results of the evaluation show the strategy should be improved. Analysis of the differences between projects where respondents answer correlates with the strategy and those projects where there is no correlation should be done.

Deep convolutional neural network model for bad code smells detection based on oversampling method

Code <span>smells refers to any symptoms or anomalies in the source code that shows violation of design principles or implementation. Early detection of bad code smells improves software quality. Nowadays several artificial neural network (ANN) models have been used for different topics in software engineering: software defect prediction, software vulnerability detection, and code clone detection. It is not necessary to know the source of the data when using ANN models but require large training sets. Data imbalance is the main challenge of artificial intelligence techniques in detecting the code smells. To overcome these challenges, the objective of this study is to presents deep convolutional neural network (D-CNN) model with synthetic minority over-sampling technique (SMOTE) to detect bad code smells based on a set of Java projects. We considered four code-smell datasets which are God class, data class, feature envy and long method and the results were compared based on different performance measures. Experimental results show that the proposed model with oversampling techniques can provide better performance for code smells detection and prediction results can be further improved when the model is trained with more datasets. Moreover, more epochs and hidden layers help increase the accuracy of the model.</span>

Automatic detection of Long Method and God Class code smells through neural source code embeddings

Code smells are structures in code that often harm its quality. Manually detecting code smells is challenging, so researchers proposed many automatic detectors. Traditional code smell detectors employ metric-based heuristics, but researchers have recently adopted a Machine-Learning (ML) based approach. This paper compares the performance of multiple ML-based code smell detection models against multiple metric-based heuristics for detection of God Class and Long Method code smells. We assess the effectiveness of different source code representations for ML: we evaluate the effectiveness of traditionally used code metrics against code embeddings (code2vec, code2seq, and CuBERT). This study is the first to evaluate the effectiveness of pre-trained neural source code embeddings for code smell detection to the best of our knowledge. This approach helped us leverage the power of transfer learning – our study is the first to explore whether the knowledge mined from code understanding models can be transferred to code smell detection. A secondary contribution of our research is the systematic evaluation of the effectiveness of code smell detection approaches on the same large-scale, manually labeled MLCQ dataset. Almost every study that proposes a detection approach tests this approach on the dataset unique for the study. Consequently, we cannot directly compare the reported performances to derive the best-performing approach.

Crowdsmelling: A preliminary study on using collective knowledge in code smells detection

Code smells are seen as major source of technical debt and, as such, should be detected and removed. However, researchers argue that the subjectiveness of the code smells detection process is a major hindrance to mitigate the problem of smells-infected code. We proposed the crowdsmelling approach based on supervised machine learning techniques, where the wisdom of the crowd (of software developers) is used to collectively calibrate code smells detection algorithms, thereby lessening the subjectivity issue. This paper presents the results of a validation experiment for the crowdsmelling approach. In the context of three consecutive years of a Software Engineering course, a total "crowd" of around a hundred teams, with an average of three members each, classified the presence of 3 code smells (Long Method, God Class, and Feature Envy) in Java source code. These classifications were the basis of the oracles used for training six machine learning algorithms. Over one hundred models were generated and evaluated to determine which machine learning algorithms had the best performance in detecting each of the aforementioned code smells. Good performances were obtained for God Class detection (ROC=0.896 for Naive Bayes) and Long Method detection (ROC=0.870 for AdaBoostM1), but much lower for Feature Envy (ROC=0.570 for Random Forrest). Obtained results suggest that crowdsmelling is a feasible approach for the detection of code smells, but further validation experiments are required to cover more code smells and to increase external validity.

A comparison of machine learning algorithms on design smell detection using balanced and imbalanced dataset: A study of God class

Design smell detection has proven to be a significant activity that has an aim of not only enhancing the software quality but also increasing its life cycle. This work investigates whether machine learning approaches can effectively be leveraged for software design smell detection. Additionally, this paper provides a comparatively study, focused on using balanced datasets, where it checks if avoiding dataset balancing can be of any influence on the accuracy and behavior during design smell detection. A set of experiments have been conducted-using 28 Machine Learning classifiers aimed at detecting God classes. This experiment was conducted using a dataset formed from 12,587 classes of 24 software systems, in which 1,958 classes were manually validated. Ultimately, most classifiers obtained high performances,-with Cat Boost showing a higher performance. Also, it is evident from the experiments conducted that data balancing does not have any significant influence on the accuracy of detection. This reinforces the application of machine learning in real scenarios where the data is usually imbalanced by the inherent nature of design smells. Machine learning approaches can effectively be used as a leverage for God class detection. While in this paper we have employed SMOTE technique for data balancing, it is worth noting that there exist other methods of data balancing and with other design smells. Furthermore, it is also important to note that application of those other methods may improve the results, in our experiments SMOTE did not improve God class detection. The results are not fully generalizable because only one design smell is studied with projects developed in a single programming language, and only one balancing technique is used to compare with the imbalanced case. But these results are promising for the application in real design smells detection scenarios as mentioned above and the focus on other measures, such as Kappa, ROC, and MCC, have been used in the assessment of the classifier behavior.

Approach of God Class Detection Based on Evolutionary and Semantic Features

Approach of God Class Detection Based on Evolutionary and Semantic Features

MARS: Detecting brain class/method code smell based on metric–attention mechanism and residual network

AbstractCode smell is the structural design defect that makes programs difficult to understand, maintain, and evolve. Existing works of code smell detection mainly focus on prevalent code smells, such as feature envy, god class, and long method. Few works have been done on detecting brain class/method. Furthermore, existing deep‐learning‐based approaches leverage the CNN model to improve accuracy by barely increasing the number of layers, which may cause a problem of gradient degradation. To this end, this paper proposes a novel approach called MARS to detect brain class/method. MARS improves the gradient degradation by employing an improved residual network. It increases the weight value of those important code metrics to label smelly samples by introducing a metric–attention mechanism. To support the training of MARS, a dataset called BrainCode is generated by extracting more than 270,000 samples from 20 real‐world applications. MARS is evaluated on BrainCode and compared to other machine‐learning‐based and deep‐learning‐based approaches. The experimental results demonstrate that the average accuracy of MARS is 2.01 % higher than that of the existing approaches, which improves state‐of‐the‐art.

Code Smell Identification As The Basis For Code Refactoring in The Agricultural Information System Portal Case Study at: Gilangharjo Village, Bantul Regency, Indonesia

Information system technology continues to evolve over time. Various fields of science including agriculture also utilize information system to improve quality and services in the agricultural sector. Indonesia is an agrarian country where most of the populations work in the agricultural sector. Based on this fact, the Indonesian government is also very supportive towards improving and developing technology in agriculture. Dutatani is one of the Agricultural Information Systems (SIP) that has been consistently developed since 2016 towards precision agriculture. One of the technologies developed is web-based technology which has many sub-systems in it. This raises the problem regarding system scalability wherein each sub-system is developed separately and uses a different development model. Each system uses a specific framework and a native. Therefore this study aims to identify which sub-systems are suitable to be developed and refactored to become a new agricultural information system portal. The identification process used a code smell and metric-based approach. The metrics used were Line of Code (LOC), Complexity, Lack of Cohesion of Methods (LCOM) and God Class. From the results of detection using a code smell, the code detected was 55.17%. This study also revealed a fact that code with a good structure would be easier to detect. Modular code that used a framework and was orderly structured could be read well by detection tools, and showed a high LCOM rate compared to structured and nativecode

Exploratory study of the impact of project domain and size category on the detection of the God class design smell

Design smell detection has proven to be an efficient strategy to improve software quality and consequently decrease maintainability expenses. This work explores the influence of the information about project context expressed as project domain and size category information, on the automatic detection of the god class design smell by machine learning techniques. A set of experiments using eight classifiers to detect god classes was conducted on a dataset containing 12, 587 classes from 24 Java projects. The results show that classifiers change their behavior when they are used on datasets that differ in these kinds of project information. The results show that god class design smell detection can be improved by feeding machine learning classifiers with this project context information.

Code Smells Detection and Visualization: A Systematic Literature Review

Context: Code smells (CS) tend to compromise software quality and also demand more effort by developers to maintain and evolve the application throughout its life-cycle. They have long been catalogued with corresponding mitigating solutions called refactoring operations. Objective: This SLR has a twofold goal: the first is to identify the main code smells detection techniques and tools discussed in the literature, and the second is to analyze to which extent visual techniques have been applied to support the former. Method: Over 83 primary studies indexed in major scientific repositories were identified by our search string in this SLR. Then, following existing best practices for secondary studies, we applied inclusion/exclusion criteria to select the most relevant works, extract their features and classify them. Results: We found that the most commonly used approaches to code smells detection are search-based (30.1%), and metric-based (24.1%). Most of the studies (83.1%) use open-source software, with the Java language occupying the first position (77.1%). In terms of code smells, God Class (51.8%), Feature Envy (33.7%), and Long Method (26.5%) are the most covered ones. Machine learning techniques are used in 35% of the studies. Around 80% of the studies only detect code smells, without providing visualization techniques. In visualization-based approaches several methods are used, such as: city metaphors, 3D visualization techniques. Conclusions: We confirm that the detection of CS is a non trivial task, and there is still a lot of work to be done in terms of: reducing the subjectivity associated with the definition and detection of CS; increasing the diversity of detected CS and of supported programming languages; constructing and sharing oracles and datasets to facilitate the replication of CS detection and visualization techniques validation experiments.

Analysing Agreement Among Different Evaluators in God Class and Feature Envy Detection

The automatic detection of Design Smells has evolved in parallel to the evolution of automatic refactoring tools. There was a huge rise in research activity regarding Design Smell detection from 2010 to the present. However, it should be noted that the adoption of Design Smell detection in real software development practice is not comparable to the adoption of automatic refactoring tools. On the basis of the assumption that it is the objectiveness of a refactoring operation as opposed to the subjectivity in definition and identification of Design Smells that makes the difference, in this paper, the lack of agreement between different evaluators when detecting Design Smells is empirically studied. To do so, a series of experiments and studies were designed and conducted to analyse the concordance in Design Smell detection of different persons and tools, including a comparison between them. This work focuses on two well known Design Smells : God Class and Feature Envy . Concordance analysis is based on the Kappa statistic for inter-rater agreement (particularly Kappa-Fleiss ). The results obtained show that there is no agreement in detection in general, and, in those cases where a certain agreement appears, it is considered to be a fair or poor degree of agreement, according to a Kappa-Fleiss interpretation scale. This seems to confirm that there is a subjective component which makes the raters evaluate the presence of Design Smells differently. The study also raises the question of a lack of training and experience regarding Design Smells .

Технический долг в жизненном цикле разработки ПО: запахи кода

This paper is dedicated to the review of the most popular code smells, which is one of the technical debt components, in addition to methods and instruments for their detection. We conduct a comparative analysis of multiple instruments such as DesigniteJava, PMD, SonarQube. We apply existing tools to set of open-source projects to deduce detection precision and coherence of the selected instruments. We highlight strengths and weaknesses of the approach based on metrics computation and threshold filtering that is used in instruments. Citing of code smells detected by the instruments shows low percentage of true positives (10% for god class and 20% for complex method). We perform literature review of papers suggesting enhancements of the standard approach and alternative approaches that doesn’t involve metrics. To assess the potential of alternative methods we introduce our long method detection prototype with a false positive filtering system based on machine learning methods.

God Class Refactoring Recommendation and Extraction Using Context based Grouping

Code smells are the indicators of the flaws in the design and development phases that decrease the maintainability and reusability of a system. A system with uneven distribution of responsibilities among the classes is generated by one of the most hazardous code smells called God Class. To address this threatening issue, an extract class refactoring technique is proposed that incorporates both cohesion and contextual aspects of a class. In this work, greater emphasis was provided on the code documentation to extract classes with higher contextual similarity. Firstly, the source code is analyzed to generate a set of cluster of extracted methods. Secondly, another set of clusters is generated by analyzing code documentation. Then, merging these two, a final cluster set is formed to extract the God Class. Finally, an automatic refactoring approach is also followed to build newly identified classes. Using two different metrics, a comparative result analysis is provided where it is shown that the cohesion among the classes is increased if the context is added in the refactoring process. Moreover, a manual inspection is conducted to ensure that the methods of the refactored classes are contextually organized. This recommendation of God Class extraction can significantly help the developers in minimizing the burden of refactoring on own their own and maintaining the software systems.