Evaluating software quality in use using user reviews mining

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.