Warit Leopairote

Bio: Warit Leopairote is an academic researcher from Chulalongkorn University. The author has contributed to research in topics: Software quality & Software construction. The author has an hindex of 2, co-authored 2 publications receiving 31 citations.

Evaluating software quality in use using user reviews mining

Abstract: Reviews of software from experienced users play an important role for software acquisition decision. In order to share their experiences, an online software recommendation system has been developed. This information is not only useful for users or customers, but it is also be used for evaluating the software. Since there are many of reviews are accumulated and expressed in both formal and informal written languages, it takes time for concluding the evaluation. Therefore, we are interested in an automatically process to extract software information attributes from the reviews in order to provide software review representation. One essential problem is the different sentiment of the same sentence in different environment. To solve this problem, rule-based classification is used as our machine learning model. In this research, software quality extracted from user perspective with respect to ISO 9126 is selected to be the characteristic model. We also propose a methodology for a software product reviews mining based on software quality ontology and a product software quality in use scores for software review representation. Our classification approach is applied from two lists of sentiment words (positive and negative words) combining with rule-based classification method. Our result yields four percent of the accuracy improvement from simple classification applied only two lists of sentiment words.

Software quality in use characteristic mining from customer reviews

Abstract: Reviews from customers who have experience with the software product are an important information decision making for software product acquisition. They usually appear on ecommerce websites or any online download market. If some products have a large number of reviews, customer may not have time to read all of them. Therefore, we need to extract software information characteristic from reviews in order to provide product review representation. Customer can further use it to compare one software product attributes and other products' attributes. Software product quality from user point of view may be used to characterize each software product. ISO 9126 is widely used among software engineer to assess software quality in use. It covers software quality model and contains the quality model characteristic from user perspective: effectiveness, productivity, safety and satisfaction. We propose a methodology for software product reviews mining based on software quality ontology constructed from ISO 9126 and a rule-based classification to finally produce software quality in use scores for software product Representation. The quality in use score for each software characteristic can be used to preliminary determine the quality of the software.

The use of machine learning algorithms in recommender systems: A systematic review

Abstract: Recommender systems use algorithms to provide users with product or service recommendations. Recently, these systems have been using machine learning algorithms from the field of artificial intelligence. However, choosing a suitable machine learning algorithm for a recommender system is difficult because of the number of algorithms described in the literature. Researchers and practitioners developing recommender systems are left with little information about the current approaches in algorithm usage. Moreover, the development of recommender systems using machine learning algorithms often faces problems and raises questions that must be resolved. This paper presents a systematic review of the literature that analyzes the use of machine learning algorithms in recommender systems and identifies new research opportunities. The goals of this study are to (i) identify trends in the use or research of machine learning algorithms in recommender systems; (ii) identify open questions in the use or research of machine learning algorithms; and (iii) assist new researchers to position new research activity in this domain appropriately. The results of this study identify existing classes of recommender systems, characterize adopted machine learning approaches, discuss the use of big data technologies, identify types of machine learning algorithms and their application domains, and analyzes both main and alternative performance metrics.

The Use of Machine Learning Algorithms in Recommender Systems: A Systematic Review

Abstract: Recommender systems use algorithms to provide users with product or service recommendations. Recently, these systems have been using machine learning algorithms from the field of artificial intelligence. However, choosing a suitable machine learning algorithm for a recommender system is difficult because of the number of algorithms described in the literature. Researchers and practitioners developing recommender systems are left with little information about the current approaches in algorithm usage. Moreover, the development of a recommender system using a machine learning algorithm often has problems and open questions that must be evaluated, so software engineers know where to focus research efforts. This paper presents a systematic review of the literature that analyzes the use of machine learning algorithms in recommender systems and identifies research opportunities for software engineering research. The study concludes that Bayesian and decision tree algorithms are widely used in recommender systems because of their relative simplicity, and that requirement and design phases of recommender system development appear to offer opportunities for further research.

On negative results when using sentiment analysis tools for software engineering research

Abstract: Recent years have seen an increasing attention to social aspects of software engineering, including studies of emotions and sentiments experienced and expressed by the software developers. Most of these studies reuse existing sentiment analysis tools such as SentiStrength and NLTK. However, these tools have been trained on product reviews and movie reviews and, therefore, their results might not be applicable in the software engineering domain. In this paper we study whether the sentiment analysis tools agree with the sentiment recognized by human evaluators (as reported in an earlier study) as well as with each other. Furthermore, we evaluate the impact of the choice of a sentiment analysis tool on software engineering studies by conducting a simple study of differences in issue resolution times for positive, negative and neutral texts. We repeat the study for seven datasets (issue trackers and Stack Overflow questions) and different sentiment analysis tools and observe that the disagreement between the tools can lead to diverging conclusions. Finally, we perform two replications of previously published studies and observe that the results of those studies cannot be confirmed when a different sentiment analysis tool is used.

A systematic literature review of open source software quality assessment models.

Abstract: Many open source software (OSS) quality assessment models are proposed and available in the literature. However, there is little or no adoption of these models in practice. In order to guide the formulation of newer models so they can be acceptable by practitioners, there is need for clear discrimination of the existing models based on their specific properties. Based on this, the aim of this study is to perform a systematic literature review to investigate the properties of the existing OSS quality assessment models by classifying them with respect to their quality characteristics, the methodology they use for assessment, and their domain of application so as to guide the formulation and development of newer models. Searches in IEEE Xplore, ACM, Science Direct, Springer and Google Search is performed so as to retrieve all relevant primary studies in this regard. Journal and conference papers between the year 2003 and 2015 were considered since the first known OSS quality model emerged in 2003. A total of 19 OSS quality assessment model papers were selected. To select these models we have developed assessment criteria to evaluate the quality of the existing studies. Quality assessment models are classified into five categories based on the quality characteristics they possess namely: single-attribute, rounded category, community-only attribute, non-community attribute as well as the non-quality in use models. Our study reflects that software selection based on hierarchical structures is found to be the most popular selection method in the existing OSS quality assessment models. Furthermore, we found that majority (47%) of the existing models do not specify any domain of application. In conclusion, our study will be a valuable contribution to the community and helps the quality assessment model developers in formulating newer models and also to the practitioners (software evaluators) in selecting suitable OSS in the midst of alternatives.

A systematic mapping study on crowdsourced requirements engineering using user feedback

Abstract: Crowdsourcing is an appealing concept for achieving good enough requirements and just‐in‐time requirements engineering (RE). A promising form of crowdsourcing in RE is the use of feedback ...