Success prediction of android applications in a novel repository using neural networks

Dehkordi, Mehrdad Razavi; Seifzadeh, Habib; Beydoun, Ghassan; Nadimi-Shahraki, Mohammad H.

doi:10.1007/s40747-020-00154-3

Cited by 11 publications

(6 citation statements)

References 33 publications

(37 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Alternatively, machine learning models such as Logistic Regression (LR) and Random Forest (RF) were built [ 45 , 46 ] for the same purpose. The different methods were noted as applying evolutionary techniques [ 47 ], statistical feature selection [ 48 ], Principal Component Analysis [ 49 ], and T-test analysis-based feature selection [ 50 ].…”

Section: Resultsmentioning

confidence: 99%

Machine Learning-Based Software Defect Prediction for Mobile Applications: A Systematic Literature Review

Jorayeva

Akbulut

Çatal

et al. 2022

Sensors

View full text Add to dashboard Cite

Software defect prediction studies aim to predict defect-prone components before the testing stage of the software development process. The main benefit of these prediction models is that more testing resources can be allocated to fault-prone modules effectively. While a few software defect prediction models have been developed for mobile applications, a systematic overview of these studies is still missing. Therefore, we carried out a Systematic Literature Review (SLR) study to evaluate how machine learning has been applied to predict faults in mobile applications. This study defined nine research questions, and 47 relevant studies were selected from scientific databases to respond to these research questions. Results show that most studies focused on Android applications (i.e., 48%), supervised machine learning has been applied in most studies (i.e., 92%), and object-oriented metrics were mainly preferred. The top five most preferred machine learning algorithms are Naïve Bayes, Support Vector Machines, Logistic Regression, Artificial Neural Networks, and Decision Trees. Researchers mostly preferred Object-Oriented metrics. Only a few studies applied deep learning algorithms including Long Short-Term Memory (LSTM), Deep Belief Networks (DBN), and Deep Neural Networks (DNN). This is the first study that systematically reviews software defect prediction research focused on mobile applications. It will pave the way for further research in mobile software fault prediction and help both researchers and practitioners in this field.

show abstract

Section: Resultsmentioning

confidence: 99%

Machine Learning-Based Software Defect Prediction for Mobile Applications: A Systematic Literature Review

Jorayeva

Akbulut

Çatal

et al. 2022

Sensors

View full text Add to dashboard Cite

show abstract

“…According to the official statistics of IDC website 1 , about 300.3 million smartphones were produced by manufacturers by the fourth quarter of 2022, 75.8% of which were smartphones with the Android operating system. The Android operating system has its own store, called Google Play Store, which includes all its produced apps by developers 2 [1,2]. The apps available in the store are downloaded by many users and Google Play Store users could comment on the desired application.…”

Section: Introductionmentioning

confidence: 99%

Dynamic PScore: A Dynamic Method to Prioritize User Reviews

Dehkordi,

Rastegari,

Najafabadi

et al. 2023

Preprint

Self Cite

View full text Add to dashboard Cite

Since the emergence of mobile apps, user reviews have been of great importance for app developers as they contain users’ sentiment, bugs and new requests. Due to the large number of reviews, it is a difficult, time-consuming and error-prone task to prioritize them manually. Having a tool or method for automated prioritization of reviews could save the development team’s time, help application development and maintenance cycle and prevent the development team’s errors. Various methods have been presented for prioritizing reviews, most of which have focused on old features that are no longer valid or ignored new features provided by the store. This study provides a method, called Dynamic PScore, for dynamic prioritization of reviews into five categories of hot, serious, pay attention, getting traction and not serious in the Google Play store. In this method, the score is calculated using ThumbsUp features (popularity of each review), extracting sentiment and considering the number of words in the review and, then, prioritization is done through the obtained score. To experimentally evaluate the proposed method in PPrior database, the corresponding score is calculated for each review and prioritization is done. Finally, the results indicate the presented method has the Accuracy and PSP of 99.94% and 99.86%, respectively, in prioritizing and scoring reviews and its prioritization accuracy has improved by 13.34% compared to recent research.

show abstract

“…Evolutionary computing is an important research direction in the field of artificial intelligence, and its algorithm, evolutionary algorithm, is a population-based search algorithm. Because of the excellent performance of evolutionary algorithm, it has been applied in diverse fields, such as path planning [1], shop scheduling [2], multi-agent system [3], networks planning [4], bi-level optimization [5], and symbolic regression [6].…”

Section: Introductionmentioning

confidence: 99%

Multiobjective multitasking optimization assisted by multidirectional prediction method

Dang

Gao

Gong

2022

Complex Intell. Syst.

View full text Add to dashboard Cite

Multiobjective multitasking optimization (MTO) is an emerging research topic in the field of evolutionary computation, which has attracted extensive attention, and many evolutionary multitasking (EMT) algorithms have been proposed. One of the core issues, designing an efficient transfer strategy, has been scarcely explored. Keeping this in mind, this paper is the first attempt to design an efficient transfer strategy based on multidirectional prediction method. Specifically, the population is divided into multiple classes by the binary clustering method, and the representative point of each class is calculated. Then, an effective prediction direction method is developed to generate multiple prediction directions by representative points. Afterward, a mutation strength adaptation method is proposed according to the improvement degree of each class. Finally, the predictive transferred solutions are generated as transfer knowledge by the prediction directions and mutation strengths. By the above process, a multiobjective EMT algorithm based on multidirectional prediction method is presented. Experiments on two MTO test suits indicate that the proposed algorithm is effective and competitive to other state-of-the-art EMT algorithms.

show abstract

Success prediction of android applications in a novel repository using neural networks

Cited by 11 publications

References 33 publications

Machine Learning-Based Software Defect Prediction for Mobile Applications: A Systematic Literature Review

Machine Learning-Based Software Defect Prediction for Mobile Applications: A Systematic Literature Review

Dynamic PScore: A Dynamic Method to Prioritize User Reviews

Multiobjective multitasking optimization assisted by multidirectional prediction method

Contact Info

Product

Resources

About